Authors: Yuhe Wang
Abstract: This note presents an approach for estimating the spatial distribution of static properties in reservoir modeling using a nearest-neighbor neural network. The method leverages the strengths of neural networks in approximating complex, non-linear functions, particularly for tasks involving spatial interpolation. It incorporates a nearest-neighbor algorithm to capture local spatial relationships between data points and introduces randomization to quantify the uncertainty inherent in the interpolation process. This approach addresses the limitations of traditional geostatistical methods, such as Inverse Distance Weighting (IDW) and Kriging, which often fail to model the complex non-linear dependencies in reservoir data. By integrating spatial proximity and uncertainty quantification, the proposed method can improve the accuracy of static property predictions like porosity and permeability.
Authors: Junda Wu, Zhehao Zhang, Yu Xia, Xintong Li, Zhaoyang Xia, Aaron Chang, Tong Yu, Sungchul Kim, Ryan A. Rossi, Ruiyi Zhang, Subrata Mitra, Dimitris N. Metaxas, Lina Yao, Jingbo Shang, Julian McAuley
Abstract: Multimodal large language models (MLLMs) equip pre-trained large-language models (LLMs) with visual capabilities. While textual prompting in LLMs has been widely studied, visual prompting has emerged for more fine-grained and free-form visual instructions. This paper presents the first comprehensive survey on visual prompting methods in MLLMs, focusing on visual prompting, prompt generation, compositional reasoning, and prompt learning. We categorize existing visual prompts and discuss generative methods for automatic prompt annotations on the images. We also examine visual prompting methods that enable better alignment between visual encoders and backbone LLMs, concerning MLLM's visual grounding, object referring, and compositional reasoning abilities. In addition, we provide a summary of model training and in-context learning methods to improve MLLM's perception and understanding of visual prompts. This paper examines visual prompting methods developed in MLLMs and provides a vision of the future of these methods.
Authors: Honglin Qin, Hongye Zheng, Bingxing Wang, Zhizhong Wu, Bingyao Liu, Yuanfang Yang
Abstract: Currently, widely used first-order deep learning optimizers include non-adaptive learning rate optimizers and adaptive learning rate optimizers. The former is represented by SGDM (Stochastic Gradient Descent with Momentum), while the latter is represented by Adam. Both of these methods use exponential moving averages to estimate the overall gradient. However, estimating the overall gradient using exponential moving averages is biased and has a lag. This paper proposes an RSGDM algorithm based on differential correction. Our contributions are mainly threefold: 1) Analyze the bias and lag brought by the exponential moving average in the SGDM algorithm. 2) Use the differential estimation term to correct the bias and lag in the SGDM algorithm, proposing the RSGDM algorithm. 3) Experiments on the CIFAR datasets have proven that our RSGDM algorithm is superior to the SGDM algorithm in terms of convergence accuracy.
Authors: Zhizhong Wu
Abstract: Recommendation systems play a crucial role in helping users filter through vast amounts of information. However, traditional recommendation algorithms often overlook the integration and utilization of multi-source information, limiting system performance. Therefore, this study proposes a novel recommendation model, Knowledge Graph Attention-assisted Network (KGAT-AX). We first incorporate the knowledge graph into the recommendation model, introducing an attention mechanism to explore higher order connectivity more explicitly. By using multilayer interactive information propagation, the model aggregates information to enhance its generalization ability. Furthermore, we integrate auxiliary information into entities through holographic embeddings, aggregating the information of adjacent entities for each entity by learning their inferential relationships. This allows for better utilization of auxiliary information associated with entities. We conducted experiments on real datasets to demonstrate the rationality and effectiveness of the KGAT-AX model. Through experimental analysis, we observed the effectiveness and potential of KGAT-AX compared to other baseline models on public datasets. KGAT-AX demonstrates better knowledge information capture and relationship learning capabilities.
Authors: East Sun, Yan Wang, Lan Tian
Abstract: We introduce Block-Attention, an attention mechanism designed to address the increased inference latency in Retrieval-Augmented Generation (RAG) scenarios. Its main idea lies in dividing the input sequence into blocks, where each block calculates its key-value (KV) states independently except for the final block. In RAG scenarios, by defining each passage as a block, Block-Attention enables us to pre-compute the KV states for all passages and cache them in memory. The implementation involves block segmentation, positional encoding calculation, and fine-tuning the LLM to adapt to the Block-Attention mechanism. Experiments on four RAG benchmarks demonstrate that after block fine-tuning, the Block Attention model can achieve performance comparable to (68.4\% vs 67.9\% on Llama3) or even better (62.8\% vs 59.6\% on Mistral) than self-attention models. Notably, Block-Attention reduces the TTFT to a very low level. It only takes 45 ms to output the first token for an input sequence with a total length of 32K. Compared with the self-attention model, the time consumption is reduced by 98.7\%.
Authors: Yuzi Yan, Xingzhou Lou, Jialian Li, Yiping Zhang, Jian Xie, Chao Yu, Yu Wang, Dong Yan, Yuan Shen
Abstract: As Large Language Models (LLMs) continue to progress toward more advanced forms of intelligence, Reinforcement Learning from Human Feedback (RLHF) is increasingly seen as a key pathway toward achieving Artificial General Intelligence (AGI). However, the reliance on reward-model-based (RM-based) alignment methods introduces significant challenges due to the inherent instability and imperfections of Reward Models (RMs), which can lead to critical issues such as reward hacking and misalignment with human intentions. In this paper, we introduce a reward-robust RLHF framework aimed at addressing these fundamental challenges, paving the way for more reliable and resilient learning in LLMs. Our approach introduces a novel optimization objective that carefully balances performance and robustness by incorporating Bayesian Reward Model Ensembles (BRME) to model the uncertainty set of reward functions. This allows the framework to integrate both nominal performance and minimum reward signals, ensuring more stable learning even with imperfect reward models. Empirical results demonstrate that our framework consistently outperforms traditional RLHF across diverse benchmarks, showing improved accuracy and long-term stability. We also provide a theoretical analysis, demonstrating that reward-robust RLHF approaches the stability of constant reward settings, which proves to be effective in a stochastic-case analysis. Together, these contributions highlight the framework potential to enhance both the performance and stability of LLM alignment with RLHF.
Authors: PK Archhith, SK Thirumalaikumaran, Balasundaram Mohan, Saptharshi Basu
Abstract: Combustion is the primary process in gas turbine engines, where there is a need for efficient air-fuel mixing to enhance performance. High-shear swirl injectors are commonly used to improve fuel atomization and mixing, which are key factors in determining combustion efficiency and emissions. However, under certain conditions, combustors can experience thermoacoustic instability. In this study, a decision tree-based machine learning algorithm is used to classify combustion conditions by analyzing acoustic pressure and high-speed flame imaging from a counter-rotating high-shear swirl injector of a single can combustor fueled by methane. With a constant Reynolds number and varying equivalence ratios, the combustor exhibits both stable and unstable states. Characteristic features are extracted from the data using time series analysis, providing insight into combustion dynamics. The trained supervised machine learning model accurately classifies stable and unstable operations, demonstrating effective prediction of combustion conditions within the studied parameter range.
Authors: Mitra Bakhshi
Abstract: Incorporating the Forward Forward algorithm into neural network training represents a transformative shift from traditional methods, introducing a dual forward mechanism that streamlines the learning process by bypassing the complexities of derivative propagation. This method is noted for its simplicity and efficiency and involves executing two forward passes the first with actual data to promote positive reinforcement, and the second with synthetically generated negative data to enable discriminative learning. Our experiments confirm that the Forward Forward algorithm is not merely an experimental novelty but a viable training strategy that competes robustly with conventional multi layer perceptron (MLP) architectures. To overcome the limitations inherent in traditional saliency techniques, which predominantly rely on gradient based methods, we developed a bespoke saliency algorithm specifically tailored for the Forward Forward framework. This innovative algorithm enhances the intuitive understanding of feature importance and network decision-making, providing clear visualizations of the data features most influential in model predictions. By leveraging this specialized saliency method, we gain deeper insights into the internal workings of the model, significantly enhancing our interpretative capabilities beyond those offered by standard approaches. Our evaluations, utilizing the MNIST and Fashion MNIST datasets, demonstrate that our method performs comparably to traditional MLP-based models.
Authors: Jonathan Mbuya, Dieter Pfoser, Antonios Anastasopoulos
Abstract: This paper presents a novel approach for trajectory anomaly detection using an autoregressive causal-attention model, termed LM-TAD. This method leverages the similarities between language statements and trajectories, both of which consist of ordered elements requiring coherence through external rules and contextual variations. By treating trajectories as sequences of tokens, our model learns the probability distributions over trajectories, enabling the identification of anomalous locations with high precision. We incorporate user-specific tokens to account for individual behavior patterns, enhancing anomaly detection tailored to user context. Our experiments demonstrate the effectiveness of LM-TAD on both synthetic and real-world datasets. In particular, the model outperforms existing methods on the Pattern of Life (PoL) dataset by detecting user-contextual anomalies and achieves competitive results on the Porto taxi dataset, highlighting its adaptability and robustness. Additionally, we introduce the use of perplexity and surprisal rate metrics for detecting outliers and pinpointing specific anomalous locations within trajectories. The LM-TAD framework supports various trajectory representations, including GPS coordinates, staypoints, and activity types, proving its versatility in handling diverse trajectory data. Moreover, our approach is well-suited for online trajectory anomaly detection, significantly reducing computational latency by caching key-value states of the attention mechanism, thereby avoiding repeated computations.
Authors: Andrei Chernov
Abstract: Inspired by recent advancements in large language models (LLMs) for Natural Language Processing (NLP), there has been a surge in research focused on developing foundational models for time series forecasting. One approach involves training LLM architectures on tokenized time series data using cross-entropy loss. Although this method has demonstrated promising results, cross-entropy loss is primarily designed for classification tasks and does not account for the distance between classes. To address this limitation, we propose using the Wasserstein loss for such architectures. To validate our approach, we fine-tuned a foundational time series model on $22$ zero-shot datasets, comparing the performance of cross-entropy loss with that of Wasserstein loss. Our results demonstrate that replacing cross-entropy loss with Wasserstein loss significantly improves point estimation.
Authors: Bo Xiong
Abstract: Relational representation learning transforms relational data into continuous and low-dimensional vector representations. However, vector-based representations fall short in capturing crucial properties of relational data that are complex and symbolic. We propose geometric relational embeddings, a paradigm of relational embeddings that respect the underlying symbolic structures. Specifically, this dissertation introduces various geometric relational embedding models capable of capturing: 1) complex structured patterns like hierarchies and cycles in networks and knowledge graphs; 2) logical structures in ontologies and logical constraints applicable for constraining machine learning model outputs; and 3) high-order structures between entities and relations. Our results obtained from benchmark and real-world datasets demonstrate the efficacy of geometric relational embeddings in adeptly capturing these discrete, symbolic, and structured properties inherent in relational data.
Authors: Alexius Wadell, Anoushka Bhutani, Venkatasubramanian Viswanathan
Abstract: Molecular Foundation Models are emerging as powerful tools for accelerating molecular design, material science, and cheminformatics, leveraging transformer architectures to speed up the discovery of new materials and drugs while reducing the computational cost of traditional ab initio methods. However, current models are constrained by closed-vocabulary tokenizers that fail to capture the full diversity of molecular structures. In this work, we systematically evaluate thirteen chemistry-specific tokenizers for their coverage of the SMILES language, uncovering substantial gaps. Using N-gram language models, we accessed the impact of tokenizer choice on model performance and quantified the information loss of unknown tokens. We introduce two new tokenizers, smirk and smirk-gpe, which can represent the entirety of the OpenSMILES specification while avoiding the pitfalls of existing tokenizers. Our work highlights the importance of open-vocabulary modeling for molecular foundation models and the need for chemically diverse benchmarks for cheminformatics.
Authors: Rengan Xu, Junjie Yang, Yifan Xu, Hong Li, Xing Liu, Devashish Shankar, Haoci Zhang, Meng Liu, Boyang Li, Yuxi Hu, Mingwei Tang, Zehua Zhang, Tunhou Zhang, Dai Li, Sijia Chen, Gian-Paolo Musumeci, Jiaqi Zhai, Bill Zhu, Hong Yan, Srihari Reddy
Abstract: The integration of hardware accelerators has significantly advanced the capabilities of modern recommendation systems, enabling the exploration of complex ranking paradigms previously deemed impractical. However, the GPU-based computational costs present substantial challenges. In this paper, we demonstrate our development of an efficiency-driven approach to explore these paradigms, moving beyond traditional reliance on native PyTorch modules. We address the specific challenges posed by ranking models' dependence on categorical features, which vary in length and complicate GPU utilization. We introduce Jagged Feature Interaction Kernels, a novel method designed to extract fine-grained insights from long categorical features through efficient handling of dynamically sized tensors. We further enhance the performance of attention mechanisms by integrating Jagged tensors with Flash Attention. Our novel Jagged Flash Attention achieves up to 9x speedup and 22x memory reduction compared to dense attention. Notably, it also outperforms dense flash attention, with up to 3x speedup and 53% more memory efficiency. In production models, we observe 10% QPS improvement and 18% memory savings, enabling us to scale our recommendation systems with longer features and more complex architectures.
Authors: Nuo Chen, Ning Wu, Jianhui Chang, Jia Li
Abstract: Utilizing large language models (LLMs) for data augmentation has yielded encouraging results in mathematical reasoning. However, these approaches face constraints in problem diversity, potentially restricting them to in-domain/distribution data generation. To this end, we propose ControlMath, an iterative method involving an equation-generator module and two LLM-based agents. The module creates diverse equations, which the Problem-Crafter agent then transforms into math word problems. The Reverse-Agent filters and selects high-quality data, adhering to the "less is more" principle, achieving better results with fewer data points. This approach enables the generation of diverse math problems, not limited to specific domains or distributions. As a result, we collect ControlMathQA, which involves 190k math word problems. Extensive results prove that combining our dataset with in-domain datasets like GSM8K can help improve the model's mathematical ability to generalize, leading to improved performances both within and beyond specific domains.
Authors: Zicheng Fan, Chen-Chieh Feng, Filip Biljecki
Abstract: Street View Imagery (SVI) has emerged as a valuable data form in urban studies, enabling new ways to map and sense urban environments. However, fundamental concerns regarding the representativeness, quality, and reliability of SVI remain underexplored, e.g.\ to what extent can cities be captured by such data and do data gaps result in bias. This research, positioned at the intersection of spatial data quality and urban analytics, addresses these concerns by proposing a novel workflow to estimate SVI's feature-level coverage on urban environment. The workflow integrates the positional relationships between SVI and target features, as well as the impact of environmental obstructions. Expanding the domain of data quality to SVI, we introduce an indicator system that evaluates the extent of coverage, focusing on the completeness and frequency dimensions. Using London as a case study, three experiments are conducted to identify potential biases in SVI's ability to cover and represent urban features, with a focus on building facades. The research highlights the limitations of traditional spatial data quality metrics in assessing SVI, and variability of SVI coverage under different data acquisition practices. Tailored approaches that consider the unique metadata and horizontal perspective of SVI are also underscored. The findings suggest that while SVI offers valuable insights, it is no panacea -- its application in urban research requires careful consideration of data coverage and feature-level representativeness to ensure reliable results.
Authors: Mrinalini Mulukutla (Texas A&M University Materials Science and Engineering Department), Robert Robinson (Texas A&M University Materials Science and Engineering Department), Danial Khatamsaz (Texas A&M University Materials Science and Engineering Department), Brent Vela (Texas A&M University Materials Science and Engineering Department), Nhu Vu (Texas A&M University Materials Science and Engineering Department), Raymundo Arr\'oyave (Texas A&M University Materials Science and Engineering Department, Texas A&M University Mechanical Engineering Department)
Abstract: Materials design is a critical driver of innovation, yet overlooking the technological, economic, and environmental risks inherent in materials and their supply chains can lead to unsustainable and risk-prone solutions. To address this, we present a novel risk-aware design approach that integrates Supply-Chain Aware Design Strategies into the materials development process. This approach leverages existing language models and text analysis to develop a specialized model for predicting materials feedstock supply risk indices. To efficiently navigate the multi-objective, multi-constraint design space, we employ Batch Bayesian Optimization (BBO), enabling the identification of Pareto-optimal high entropy alloys (HEAs) that balance performance objectives with minimized supply risk. A case study using the MoNbTiVW system demonstrates the efficacy of our approach in four scenarios, highlighting the significant impact of incorporating supply risk into the design process. By optimizing for both performance and supply risk, we ensure that the developed alloys are not only high-performing but also sustainable and economically viable. This integrated approach represents a critical step towards a future where materials discovery and design seamlessly consider sustainability, supply chain dynamics, and comprehensive life cycle analysis.
Authors: Shaoqi Wang, Chunjie Yang, Siwei Lou
Abstract: Neural networks (NN) are extensively studied in cutting-edge soft sensor models due to their feature extraction and function approximation capabilities. Current research into network-based methods primarily focuses on models' offline accuracy. Notably, in industrial soft sensor context, online optimizing stability and interpretability are prioritized, followed by accuracy. This requires a clearer understanding of network's training process. To bridge this gap, we propose a novel NN named the Approximated Orthogonal Projection Unit (AOPU) which has solid mathematical basis and presents superior training stability. AOPU truncates the gradient backpropagation at dual parameters, optimizes the trackable parameters updates, and enhances the robustness of training. We further prove that AOPU attains minimum variance estimation (MVE) in NN, wherein the truncated gradient approximates the natural gradient (NG). Empirical results on two chemical process datasets clearly show that AOPU outperforms other models in achieving stable convergence, marking a significant advancement in soft sensor field.
Authors: Zilu Li, Guandao Yang, Qingqing Zhao, Xi Deng, Leonidas Guibas, Bharath Hariharan, Gordon Wetzstein
Abstract: This paper presents a method to leverage arbitrary neural network architecture for control variates. Control variates are crucial in reducing the variance of Monte Carlo integration, but they hinge on finding a function that both correlates with the integrand and has a known analytical integral. Traditional approaches rely on heuristics to choose this function, which might not be expressive enough to correlate well with the integrand. Recent research alleviates this issue by modeling the integrands with a learnable parametric model, such as a neural network. However, the challenge remains in creating an expressive parametric model with a known analytical integral. This paper proposes a novel approach to construct learnable parametric control variates functions from arbitrary neural network architectures. Instead of using a network to approximate the integrand directly, we employ the network to approximate the anti-derivative of the integrand. This allows us to use automatic differentiation to create a function whose integration can be constructed by the antiderivative network. We apply our method to solve partial differential equations using the Walk-on-sphere algorithm. Our results indicate that this approach is unbiased and uses various network architectures to achieve lower variance than other control variate methods.
Authors: Zesen Zhao, Shuowei Jin, Z. Morley Mao
Abstract: The proliferation of Large Language Models (LLMs) with varying capabilities and costs has created a need for efficient model selection in AI systems. LLM routers address this need by dynamically choosing the most suitable model for a given query based on task requirements and budget constraints. However, existing routers face challenges in scalability and real-time adaptation, particularly in high-volume online environments. We present Eagle, a novel LLM routing approach that combines global and local ELO ranking modules to overcome these limitations. By evaluating both general and specialized LLM abilities, Eagle provides a scalable, training-free solution that enhances model selection quality while reducing computational overhead. Our experiments across multiple datasets show Eagle consistently outperforms baseline methods, with improvements of up to 23.52 percent in Area Under Curve (AUC) scores. Moreover, Eagle demonstrates remarkable efficiency, requiring only 1/20 of baseline methods' time for initialization and 100 to 200 times faster incremental updates in online scenarios, making it well-suited for dynamic, high-volume online serving environments.
Authors: Lei Gao, Amir Ziashahabi, Yue Niu, Salman Avestimehr, Murali Annavaram
Abstract: Large Language Models (LLMs) have demonstrated exceptional performance in automating various tasks, such as text generation and summarization. Currently LLMs are trained and fine-tuned on large cloud server. Deploying and fine-tuning these models on resource-constrained edge devices remains a significant challenge due to their substantial memory and computational requirements. This paper introduces a resource-efficient zeroth-order optimization approach that lowers the barriers for fine-tuning LLMs in such constrained environments. Our method features a parallelized randomized gradient estimation (P-RGE) technique, which performs gradient estimation with high parallel efficiency. P-RGE leverages outer-loop and inner-loop parallelization to perform multiple function queries and forward passes in parallel, reducing the wall-clock end-to-end training time. By integrating this technique with parameter-efficient fine-tuning methods (e.g., LoRA) and on-device inference engines (e.g., ExecuTorch), we demonstrate efficient fine-tuning of LLMs on both server-side and edge devices. Experiments show that P-RGE achieves significant runtime speedups and memory savings while maintaining fine-tuning accuracy, which paves the way for more practical deployment of LLMs in real-time, on-device applications.
Authors: Yuxuan Li, Srijita Das, Matthew E. Taylor
Abstract: In recent times, Reinforcement learning (RL) has been widely applied to many challenging tasks. However, in order to perform well, it requires access to a good reward function which is often sparse or manually engineered with scope for error. Introducing human prior knowledge is often seen as a possible solution to the above-mentioned problem, such as imitation learning, learning from preference, and inverse reinforcement learning. Learning from feedback is another framework that enables an RL agent to learn from binary evaluative signals describing the teacher's (positive or negative) evaluation of the agent's action. However, these methods often make the assumption that evaluative teacher feedback is perfect, which is a restrictive assumption. In practice, such feedback can be noisy due to limited teacher expertise or other exacerbating factors like cognitive load, availability, distraction, etc. In this work, we propose the CANDERE-COACH algorithm, which is capable of learning from noisy feedback by a nonoptimal teacher. We propose a noise-filtering mechanism to de-noise online feedback data, thereby enabling the RL agent to successfully learn with up to 40% of the teacher feedback being incorrect. Experiments on three common domains demonstrate the effectiveness of the proposed approach.
Authors: Anastasiia Zakharova, Dmitriy Alexandrov, Maria Khodorchenko, Nikolay Butakov, Alexey Vasilev, Maxim Savchenko, Alexander Grigorievskiy
Abstract: Machine learning (ML) models trained on datasets owned by different organizations and physically located in remote databases offer benefits in many real-world use cases. State regulations or business requirements often prevent data transfer to a central location, making it difficult to utilize standard machine learning algorithms. Federated Learning (FL) is a technique that enables models to learn from distributed datasets without revealing the original data. Vertical Federated learning (VFL) is a type of FL where data samples are divided by features across several data owners. For instance, in a recommendation task, a user can interact with various sets of items, and the logs of these interactions are stored by different organizations. In this demo paper, we present \emph{Stalactite} - an open-source framework for VFL that provides the necessary functionality for building prototypes of VFL systems. It has several advantages over the existing frameworks. In particular, it allows researchers to focus on the algorithmic side rather than engineering and to easily deploy learning in a distributed environment. It implements several VFL algorithms and has a built-in homomorphic encryption layer. We demonstrate its use on a real-world recommendation datasets.
Authors: Xingrui Gu, Chuyi Jiang, Erte Wang, Zekun Wu, Qiang Cui, Leimin Tian, Lianlong Wu, Siyang Song, Chuang Yu
Abstract: Constrained by the lack of model interpretability and a deep understanding of human movement in traditional movement recognition machine learning methods, this study introduces a novel representation learning method based on causal inference to better understand human joint dynamics and complex behaviors. We propose a two-stage framework that combines the Peter-Clark (PC) algorithm and Kullback-Leibler (KL) divergence to identify and quantify causal relationships between joints. Our method effectively captures interactions and produces interpretable, robust representations. Experiments on the EmoPain dataset show that our causal GCN outperforms traditional GCNs in accuracy, F1 score, and recall, especially in detecting protective behaviors. The model is also highly invariant to data scale changes, enhancing its reliability in practical applications. Our approach advances human motion analysis and paves the way for more adaptive intelligent healthcare solutions.
Authors: Rahul Khorana, Marcus Noack, Jin Qian
Abstract: Developing robust physics-informed representations of chemical structures that enable models to learn topological inductive biases is challenging. In this manuscript, we present a representation of atomistic systems. We begin by proving that our representation satisfies all structural, geometric, efficiency, and generalizability constraints. Afterward, we provide a general algorithm to encode any atomistic system. Finally, we report performance comparable to state-of-the-art methods on numerous tasks. We open-source all code and datasets. The code and data are available at https://github.com/rahulkhorana/PolyatomicComplexes.
Authors: Ting Yan Fok, Nong Ye
Abstract: A knee point on a curve is the one where the curve levels off after an increase. In a computer system, it marks the point at which the system's performance is no longer improving significantly despite adding extra resources. Thus a knee point often represents an optimal point for decision. However, identifying knee points in noisy data is a challenging task. All previous works defined knee points based on the data in the original scale. However, in this work, we define knee points based on normalized data and provide a mathematical definition of curvature for normalized discrete data points, based on the mathematical definition of curvature for continuous functions. The impact of normalization exerted on curvature and the location of knee points are also discussed. Nevertheless, assessing the effectiveness of methods is difficult in the absence of ground truth data and benchmark datasets, which makes comparing existing methods challenging. In view of this, we create synthetic data that simulate real-world scenarios. We achieve this by selecting a set of functions that possess the required characteristics in this research and then introducing noise that satisfies the underlying distribution. In addition, we present a deep-learning approach and employ a Convolutional Neural Network (CNN) with a U-Net-like architecture, to accurately detect the knee point(s) of the underlying true distribution. The proposed model is evaluated against state-of-the-art methods. Experiments show that our network outperforms existing methods in all synthetic datasets, regardless of whether the samples have single or multiple knee points. In fact, our model achieves the best $F_{1}$ scores among all existing methods in all the test sets.
Authors: Wangyang Ying, Dongjie Wang, Xuanming Hu, Ji Qiu, Jin Park, Yanjie Fu
Abstract: Biomarker discovery is vital in advancing personalized medicine, offering insights into disease diagnosis, prognosis, and therapeutic efficacy. Traditionally, the identification and validation of biomarkers heavily depend on extensive experiments and statistical analyses. These approaches are time-consuming, demand extensive domain expertise, and are constrained by the complexity of biological systems. These limitations motivate us to ask: Can we automatically identify the effective biomarker subset without substantial human efforts? Inspired by the success of generative AI, we think that the intricate knowledge of biomarker identification can be compressed into a continuous embedding space, thus enhancing the search for better biomarkers. Thus, we propose a new biomarker identification framework with two important modules:1) training data preparation and 2) embedding-optimization-generation. The first module uses a multi-agent system to automatically collect pairs of biomarker subsets and their corresponding prediction accuracy as training data. These data establish a strong knowledge base for biomarker identification. The second module employs an encoder-evaluator-decoder learning paradigm to compress the knowledge of the collected data into a continuous space. Then, it utilizes gradient-based search techniques and autoregressive-based reconstruction to efficiently identify the optimal subset of biomarkers. Finally, we conduct extensive experiments on three real-world datasets to show the efficiency, robustness, and effectiveness of our method.
Authors: Xuanming Hu, Dongjie Wang, Wangyang Ying, Yanjie Fu
Abstract: Polymer property performance prediction aims to forecast specific features or attributes of polymers, which has become an efficient approach to measuring their performance. However, existing machine learning models face challenges in effectively learning polymer representations due to low-quality polymer datasets, which consequently impact their overall performance. This study focuses on improving polymer property performance prediction tasks by reconstructing an optimal and explainable descriptor representation space. Nevertheless, prior research such as feature engineering and representation learning can only partially solve this task since they are either labor-incentive or unexplainable. This raises two issues: 1) automatic transformation and 2) explainable enhancement. To tackle these issues, we propose our unique Traceable Group-wise Reinforcement Generation Perspective. Specifically, we redefine the reconstruction of the representation space into an interactive process, combining nested generation and selection. Generation creates meaningful descriptors, and selection eliminates redundancies to control descriptor sizes. Our approach employs cascading reinforcement learning with three Markov Decision Processes, automating descriptor and operation selection, and descriptor crossing. We utilize a group-wise generation strategy to explore and enhance reward signals for cascading agents. Ultimately, we conduct experiments to indicate the effectiveness of our proposed framework.
Authors: Liang Zhang, Jionghao Lin, John Sabatini, Conrad Borchers, Daniel Weitekamp, Meng Cao, John Hollander, Xiangen Hu, Arthur C. Graesser
Abstract: Learning performance data describe correct and incorrect answers or problem-solving attempts in adaptive learning, such as in intelligent tutoring systems (ITSs). Learning performance data tend to be highly sparse (80\%\(\sim\)90\% missing observations) in most real-world applications due to adaptive item selection. This data sparsity presents challenges to using learner models to effectively predict future performance explore new hypotheses about learning. This article proposes a systematic framework for augmenting learner data to address data sparsity in learning performance data. First, learning performance is represented as a three-dimensional tensor of learners' questions, answers, and attempts, capturing longitudinal knowledge states during learning. Second, a tensor factorization method is used to impute missing values in sparse tensors of collected learner data, thereby grounding the imputation on knowledge tracing tasks that predict missing performance values based on real observations. Third, a module for generating patterns of learning is used. This study contrasts two forms of generative Artificial Intelligence (AI), including Generative Adversarial Networks (GANs) and Generate Pre-Trained Transformers (GPT) to generate data associated with different clusters of learner data. We tested this approach on an adult literacy dataset from AutoTutor lessons developed for Adult Reading Comprehension (ARC). We found that: (1) tensor factorization improved the performance in tracing and predicting knowledge mastery compared with other knowledge tracing techniques without data augmentation, showing higher relative fidelity for this imputation method, and (2) the GAN-based simulation showed greater overall stability and less statistical bias based on a divergence evaluation with varying simulation sample sizes compared to GPT.
Authors: Pengju Wang, Bochao Liu, Dan Zeng, Chenggang Yan, Shiming Ge
Abstract: In practical scenarios, federated learning frequently necessitates training personalized models for each client using heterogeneous data. This paper proposes a backbone self-distillation approach to facilitate personalized federated learning. In this approach, each client trains its local model and only sends the backbone weights to the server. These weights are then aggregated to create a global backbone, which is returned to each client for updating. However, the client's local backbone lacks personalization because of the common representation. To solve this problem, each client further performs backbone self-distillation by using the global backbone as a teacher and transferring knowledge to update the local backbone. This process involves learning two components: the shared backbone for common representation and the private head for local personalization, which enables effective global knowledge transfer. Extensive experiments and comparisons with 12 state-of-the-art approaches demonstrate the effectiveness of our approach.
Authors: Ying Fan, Yilun Du, Kannan Ramchandran, Kangwook Lee
Abstract: Recent work has shown that Transformers trained from scratch can successfully solve various arithmetic and algorithmic tasks, such as adding numbers and computing parity. While these Transformers generalize well on unseen inputs of the same length, they struggle with length generalization, i.e., handling inputs of unseen lengths. In this work, we demonstrate that looped Transformers with an adaptive number of steps significantly improve length generalization. We focus on tasks with a known iterative solution, involving multiple iterations of a RASP-L operation - a length-generalizable operation that can be expressed by a finite-sized Transformer. We train looped Transformers using our proposed learning algorithm and observe that they learn highly length-generalizable solutions for various tasks.
Authors: Wenbo Yan, Ying Tan
Abstract: Spatial-temporal graph neural networks (STGNNs) have achieved significant success in various time series forecasting tasks. However, due to the lack of explicit and fixed spatial relationships in stock prediction tasks, many STGNNs fail to perform effectively in this domain. While some STGNNs learn spatial relationships from time series, they often lack comprehensiveness. Research indicates that modeling time series using feature changes as tokens reveals entirely different information compared to using time steps as tokens. To more comprehensively extract dynamic spatial information from stock data, we propose a Double-Path Adaptive-correlation Spatial-Temporal Inverted Transformer (DPA-STIFormer). DPA-STIFormer models each node via continuous changes in features as tokens and introduces a Double Direction Self-adaptation Fusion mechanism. This mechanism decomposes node encoding into temporal and feature representations, simultaneously extracting different spatial correlations from a double path approach, and proposes a Double-path gating mechanism to fuse these two types of correlation information. Experiments conducted on four stock market datasets demonstrate state-of-the-art results, validating the model's superior capability in uncovering latent temporal-correlation patterns.
Authors: Youqing Hua, Shuai Liu, Yiguang Hong, Karl Henrik Johansson, Guangchen Wang
Abstract: This paper considers the distributed online bandit optimization problem with nonconvex loss functions over a time-varying digraph. This problem can be viewed as a repeated game between a group of online players and an adversary. At each round, each player selects a decision from the constraint set, and then the adversary assigns an arbitrary, possibly nonconvex, loss function to this player. Only the loss value at the current round, rather than the entire loss function or any other information (e.g. gradient), is privately revealed to the player. Players aim to minimize a sequence of global loss functions, which are the sum of local losses. We observe that traditional multi-point bandit algorithms are unsuitable for online optimization, where the data for the loss function are not all a priori, while the one-point bandit algorithms suffer from poor regret guarantees. To address these issues, we propose a novel one-point residual feedback distributed online algorithm. This algorithm estimates the gradient using residuals from two points, effectively reducing the regret bound while maintaining $\mathcal{O}(1)$ sampling complexity per iteration. We employ a rigorous metric, dynamic regret, to evaluate the algorithm's performance. By appropriately selecting the step size and smoothing parameters, we demonstrate that the expected dynamic regret of our algorithm is comparable to existing algorithms that use two-point feedback, provided the deviation in the objective function sequence and the path length of the minimization grows sublinearly. Finally, we validate the effectiveness of the proposed algorithm through numerical simulations.
Authors: Yang Xu, Wenbin Lu, Rui Song
Abstract: Interference, a key concept in causal inference, extends the reward modeling process by accounting for the impact of one unit's actions on the rewards of others. In contextual bandit (CB) settings, where multiple units are present in the same round, potential interference can significantly affect the estimation of expected rewards for different arms, thereby influencing the decision-making process. Although some prior work has explored multi-agent and adversarial bandits in interference-aware settings, the effect of interference in CB, as well as the underlying theory, remains significantly underexplored. In this paper, we introduce a systematic framework to address interference in Linear CB (LinCB), bridging the gap between causal inference and online decision-making. We propose a series of algorithms that explicitly quantify the interference effect in the reward modeling process and provide comprehensive theoretical guarantees, including sublinear regret bounds, finite sample upper bounds, and asymptotic properties. The effectiveness of our approach is demonstrated through simulations and a synthetic data generated based on MovieLens data.
Authors: Xingping Xian, Jianlu Liu, Tao Wu, Lin Yuan, Chao Wang, Baiyun Chen
Abstract: Graph Neural Networks (GNNs) have garnered significant attention and have been extensively utilized across various domains. However, similar to other deep learning models, GNNs are often viewed as black-box models, making it challenging to interpret their prediction mechanisms. Current graph explanation techniques focus on identifying key nodes or edges, attributing the critical data features that drive model predictions. Nevertheless, these features do not independently influence the model's outcomes; rather, they interact with one another to collectively affect predictions. In this work, we propose a novel explanatory method GraphGI, which identifies the coalition with the highest interaction strength and presents it as an explanatory subgraph. Given a trained model and an input graph, our method explains predictions by gradually incorporating significant edges into the selected subgraph. We utilize game-theoretic interaction values to assess the interaction strength after edge additions, ensuring that the newly added edges confer maximum interaction strength to the explanatory subgraph. To enhance computational efficiency, we adopt effective approximation techniques for calculating Shapley values and game-theoretic interaction values. Empirical evaluations demonstrate that our method achieves superior fidelity and sparsity, maintaining the interpretability of the results at a comprehensible level.
Authors: Jixuan Cui, Jun Li, Zhen Mei, Yiyang Ni, Wen Chen, Zengxiang Li
Abstract: The challenge of data scarcity hinders the application of deep learning in industrial surface defect classification (SDC), as it's difficult to collect and centralize sufficient training data from various entities in Industrial Internet of Things (IIoT) due to privacy concerns. Federated learning (FL) provides a solution by enabling collaborative global model training across clients while maintaining privacy. However, performance may suffer due to data heterogeneity--discrepancies in data distributions among clients. In this paper, we propose a novel personalized FL (PFL) approach, named Adversarial Federated Consensus Learning (AFedCL), for the challenge of data heterogeneity across different clients in SDC. First, we develop a dynamic consensus construction strategy to mitigate the performance degradation caused by data heterogeneity. Through adversarial training, local models from different clients utilize the global model as a bridge to achieve distribution alignment, alleviating the problem of global knowledge forgetting. Complementing this strategy, we propose a consensus-aware aggregation mechanism. It assigns aggregation weights to different clients based on their efficacy in global knowledge learning, thereby enhancing the global model's generalization capabilities. Finally, we design an adaptive feature fusion module to further enhance global knowledge utilization efficiency. Personalized fusion weights are gradually adjusted for each client to optimally balance global and local features, tailored to their individual global knowledge learning efficacy. Compared with state-of-the-art FL methods like FedALA, the proposed AFedCL method achieves an accuracy increase of up to 5.67% on three SDC datasets.
Authors: Wei-Chang Yeh
Abstract: This paper presents a novel approach to enhance the Binary-Addition-Tree algorithm (BAT) by integrating incremental learning techniques. BAT, known for its simplicity in development, implementation, and application, is a powerful implicit enumeration method for solving network reliability and optimization problems. However, it traditionally struggles with dynamic and large-scale networks due to its static nature. By introducing incremental learning, we enable the BAT to adapt and improve its performance iteratively as it encounters new data or network changes. This integration allows for more efficient computation, reduced redundancy without searching minimal paths and cuts, and improves overall performance in dynamic environments. Experimental results demonstrate the effectiveness of the proposed method, showing significant improvements in both computational efficiency and solution quality compared to the traditional BAT and indirect algorithms, such as MP-based algorithms and MC-based algorithms.
Authors: Yuhang Yao, Jianyi Zhang, Junda Wu, Chengkai Huang, Yu Xia, Tong Yu, Ruiyi Zhang, Sungchul Kim, Ryan Rossi, Ang Li, Lina Yao, Julian McAuley, Yiran Chen, Carlee Joe-Wong
Abstract: Large language models are rapidly gaining popularity and have been widely adopted in real-world applications. While the quality of training data is essential, privacy concerns arise during data collection. Federated learning offers a solution by allowing multiple clients to collaboratively train LLMs without sharing local data. However, FL introduces new challenges, such as model convergence issues due to heterogeneous data and high communication costs. A comprehensive study is required to address these challenges and guide future research. This paper surveys Federated learning for LLMs (FedLLM), highlighting recent advances and future directions. We focus on two key aspects: fine-tuning and prompt learning in a federated setting, discussing existing work and associated research challenges. We finally propose potential research directions for federated LLMs, including pre-training and how LLMs can further enhance federated learning.
Authors: Ming Jin, Danni Zhang, Gangming Zhao, Changde Du, Jinpeng Li
Abstract: Electroencephalography (EEG)-based emotion recognition has gained significant traction due to its accuracy and objectivity. However, the non-stationary nature of EEG signals leads to distribution drift over time, causing severe performance degradation when the model is reused. While numerous domain adaptation (DA) approaches have been proposed in recent years to address this issue, their reliance on large amounts of target data for calibration restricts them to offline scenarios, rendering them unsuitable for real-time applications. To address this challenge, this paper proposes Evolvable Fast Adaptation (EvoFA), an online adaptive framework tailored for EEG data. EvoFA organically integrates the rapid adaptation of Few-Shot Learning (FSL) and the distribution matching of Domain Adaptation (DA) through a two-stage generalization process. During the training phase, a robust base meta-learning model is constructed for strong generalization. In the testing phase, a designed evolvable meta-adaptation module iteratively aligns the marginal distribution of target (testing) data with the evolving source (training) data within a model-agnostic meta-learning framework, enabling the model to learn the evolving trends of testing data relative to training data and improving online testing performance. Experimental results demonstrate that EvoFA achieves significant improvements compared to the basic FSL method and previous online methods. The introduction of EvoFA paves the way for broader adoption of EEG-based emotion recognition in real-world applications. Our code will be released upon publication.
Authors: Satvik Golechha, Dylan Cope, Nandi Schoots
Abstract: An approach to improve network interpretability is via clusterability, i.e., splitting a model into disjoint clusters that can be studied independently. We find pretrained models to be highly unclusterable and thus train models to be more modular using an ``enmeshment loss'' function that encourages the formation of non-interacting clusters. Using automated interpretability measures, we show that our method finds clusters that learn different, disjoint, and smaller circuits for CIFAR-10 labels. Our approach provides a promising direction for making neural networks easier to interpret.
Authors: Hanwen Zhang, Dusit Niyato, Wei Zhang, Changyuan Zhao, Hongyang Du, Abbas Jamalipour, Sumei Sun, Yiyang Pei
Abstract: With the advancement of generative artificial intelligence (GenAI) models, their capability to generate content is seeing significant enhancement, leading to widespread applications in the field of data generation and forecasting. Furthermore, GenAI has strong capabilities in data modeling and analysis, which enhances Internet of electric vehicles (IoEV) applications in various aspects. In this paper, we investigate and survey applications of GenAI in the IoEV. Specifically, we categorize GenAI for IoEV into four different layers namely, EV's battery layer, individual electric vehicle (EV) layer, smart grid with EV layer, and security layer. We first introduce various GenAI techniques used in each layer of IoEV applications. Subsequently, public datasets available for training the GenAI models are summarized. Finally, we provide recommendations for future directions. This survey not only categorizes the applications of GenAI in IoEV across different layers but also serves as a valuable resource for researchers and practitioners by highlighting the design and implementation challenges within each layer. Furthermore, it provides a roadmap for future research directions, enabling the development of more robust and efficient IoEV systems through the integration of advanced GenAI techniques.
Authors: Yooseok Lim, Inbeom Park, Sujee Lee
Abstract: Appropriate medication dosages in the intensive care unit (ICU) are critical for patient survival. Heparin, used to treat thrombosis and inhibit blood clotting in the ICU, requires careful administration due to its complexity and sensitivity to various factors, including patient clinical characteristics, underlying medical conditions, and potential drug interactions. Incorrect dosing can lead to severe complications such as strokes or excessive bleeding. To address these challenges, this study proposes a reinforcement learning (RL)-based personalized optimal heparin dosing policy that guides dosing decisions reliably within the therapeutic range based on individual patient conditions. A batch-constrained policy was implemented to minimize out-of-distribution errors in an offline RL environment and effectively integrate RL with existing clinician policies. The policy's effectiveness was evaluated using weighted importance sampling, an off-policy evaluation method, and the relationship between state representations and Q-values was explored using t-SNE. Both quantitative and qualitative analyses were conducted using the Medical Information Mart for Intensive Care III (MIMIC-III) database, demonstrating the efficacy of the proposed RL-based medication policy. Leveraging advanced machine learning techniques and extensive clinical data, this research enhances heparin administration practices and establishes a precedent for the development of sophisticated decision-support tools in medicine.
Authors: Haotian Ye, Haowei Lin, Jiaqi Han, Minkai Xu, Sheng Liu, Yitao Liang, Jianzhu Ma, James Zou, Stefano Ermon
Abstract: Given an unconditional diffusion model and a predictor for a target property of interest (e.g., a classifier), the goal of training-free guidance is to generate samples with desirable target properties without additional training. Existing methods, though effective in various individual applications, often lack theoretical grounding and rigorous testing on extensive benchmarks. As a result, they could even fail on simple tasks, and applying them to a new problem becomes unavoidably difficult. This paper introduces a novel algorithmic framework encompassing existing methods as special cases, unifying the study of training-free guidance into the analysis of an algorithm-agnostic design space. Via theoretical and empirical investigation, we propose an efficient and effective hyper-parameter searching strategy that can be readily applied to any downstream task. We systematically benchmark across 7 diffusion models on 16 tasks with 40 targets, and improve performance by 8.5% on average. Our framework and benchmark offer a solid foundation for conditional generation in a training-free manner.
Authors: Ziyang Wu, Fan Liu, Jindong Han, Yuxuan Liang, Hao Liu
Abstract: As various types of crime continue to threaten public safety and economic development, predicting the occurrence of multiple types of crimes becomes increasingly vital for effective prevention measures. Although extensive efforts have been made, most of them overlook the heterogeneity of different crime categories and fail to address the issue of imbalanced spatial distribution. In this work, we propose a Spatial-Temporal Mixture-of-Graph-Experts (ST-MoGE) framework for collective multiple-type crime prediction. To enhance the model's ability to identify diverse spatial-temporal dependencies and mitigate potential conflicts caused by spatial-temporal heterogeneity of different crime categories, we introduce an attentive-gated Mixture-of-Graph-Experts (MGEs) module to capture the distinctive and shared crime patterns of each crime category. Then, we propose Cross-Expert Contrastive Learning(CECL) to update the MGEs and force each expert to focus on specific pattern modeling, thereby reducing blending and redundancy. Furthermore, to address the issue of imbalanced spatial distribution, we propose a Hierarchical Adaptive Loss Re-weighting (HALR) approach to eliminate biases and insufficient learning of data-scarce regions. To evaluate the effectiveness of our methods, we conduct comprehensive experiments on two real-world crime datasets and compare our results with twelve advanced baselines. The experimental results demonstrate the superiority of our methods.
Authors: Yuanzhao Zhang, William Gilpin
Abstract: Time-series forecasting is a challenging task that traditionally requires specialized models custom-trained for the specific task at hand. Recently, inspired by the success of large language models, foundation models pre-trained on vast amounts of time-series data from diverse domains have emerged as a promising candidate for general-purpose time-series forecasting. The defining characteristic of these foundation models is their ability to perform zero-shot learning, that is, forecasting a new system from limited context data without explicit re-training or fine-tuning. Here, we evaluate whether the zero-shot learning paradigm extends to the challenging task of forecasting chaotic systems. Across 135 distinct chaotic dynamical systems and $10^8$ timepoints, we find that foundation models produce competitive forecasts compared to custom-trained models (including NBEATS, TiDE, etc.), particularly when training data is limited. Interestingly, even after point forecasts fail, foundation models preserve the geometric and statistical properties of the chaotic attractors, demonstrating a surprisingly strong ability to capture the long-term behavior of chaotic dynamical systems. Our results highlight the promises and pitfalls of foundation models in making zero-shot forecasts of chaotic systems.
Authors: Xinxing Zhou, Jiaqi Ye, Shubao Zhao, Ming Jin, Zhaoxiang Hou, Chengyi Yang, Zengxiang Li, Yanlong Wen, Xiaojie Yuan
Abstract: In the context of global energy strategy, accurate natural gas demand forecasting is crucial for ensuring efficient resource allocation and operational planning. Traditional forecasting methods struggle to cope with the growing complexity and variability of gas consumption patterns across diverse industries and commercial sectors. To address these challenges, we propose the first foundation model specifically tailored for natural gas demand forecasting. Foundation models, known for their ability to generalize across tasks and datasets, offer a robust solution to the limitations of traditional methods, such as the need for separate models for different customer segments and their limited generalization capabilities. Our approach leverages contrastive learning to improve prediction accuracy in real-world scenarios, particularly by tackling issues such as noise in historical consumption data and the potential misclassification of similar data samples, which can lead to degradation in the quaility of the representation and thus the accuracy of downstream forecasting tasks. By integrating advanced noise filtering techniques within the contrastive learning framework, our model enhances the quality of learned representations, leading to more accurate predictions. Furthermore, the model undergoes industry-specific fine-tuning during pretraining, enabling it to better capture the unique characteristics of gas consumption across various sectors. We conducted extensive experiments using a large-scale dataset from ENN Group, which includes data from over 10,000 industrial, commercial, and welfare-related customers across multiple regions. Our model outperformed existing state-of-the-art methods, demonstrating a relative improvement in MSE by 3.68\% and in MASE by 6.15\% compared to the best available model.
Authors: Leye Zhang, Xiangxiang Tian, Chengli Zhang, Hongjun Zhang
Abstract: Stable Diffusion fine-tuning technique is tried to assist bridge-type innovation. The bridge real photo dataset is built, and Stable Diffusion is fine tuned by using four methods that are Textual Inversion, Dreambooth, Hypernetwork and Lora. All of them can capture the main characteristics of dataset images and realize the personalized customization of Stable Diffusion. Through fine-tuning, Stable Diffusion is not only a drawing tool, but also has the designer's innovative thinking ability. The fine tuned model can generate a large number of innovative new bridge types, which can provide rich inspiration for human designers. The result shows that this technology can be used as an engine of creativity and a power multiplier for human designers.
Authors: Yang Zhao, Li Du, Xiao Ding, Kai Xiong, Ting Liu, Bing Qin
Abstract: Though demonstrating promising potential, LLMs' performance on complex tasks, such as advanced mathematics and complex disease diagnosis is still unsatisfactory. A key issue is the present LLMs learn in a data-driven schema, while the instruction dataset about these complex tasks is both scarce and hard to collect or construct. On the contrary, a prominent phenomenon is that LLMs can learn rather fast on those simpler tasks with adequate prior knowledge captured during pretraining stage. Thus, if the prerequisite and mechanism of such rapid generalization could be elucidated, it could be highly beneficial in enhancing the efficiency and effectiveness of the LLM's ability to learn complex tasks. Thus, in this paper, we employ a gradient-based method, to dissect the process that the SFT process adapts LLMs to downstream tasks via the perspective of attention patterns. We find that: (1) LLMs selectively activate task-specific attention heads during SFT; (2) activation patterns for complex tasks are combinations of basic task patterns; and (3) changes in a few parameters can significantly impact activation patterns after SFT on a small number of samples. Based on these insights, we conduct experiments to examine whether these conclusions could effectively enhance the efficiency and effectiveness of SFT, particularly in handling complex tasks and when instructional resources are scarce. Our research not only uncovers the underlying reasons behind LLMs' rapid learning and generalization mechanisms but also provides practical solutions for addressing data challenges in complex and specialized tasks.
Authors: Yuanzhe Jin, Adrian Carrasco-Revilla, Min Chen
Abstract: In developing machine learning (ML) models for text classification, one common challenge is that the collected data is often not ideally distributed, especially when new classes are introduced in response to changes of data and tasks. In this paper, we present a solution for using visual analytics (VA) to guide the generation of synthetic data using large language models. As VA enables model developers to identify data-related deficiency, data synthesis can be targeted to address such deficiency. We discuss different types of data deficiency, describe different VA techniques for supporting their identification, and demonstrate the effectiveness of targeted data synthesis in improving model accuracy. In addition, we present a software tool, iGAiVA, which maps four groups of ML tasks into four VA views, integrating generative AI and VA into an ML workflow for developing and improving text classification models.
Authors: Fangfang Li, Quanxue Gao, Ming Yang, Cheng Deng, Wei Xia
Abstract: The K-means one-step dimensionality reduction clustering method has made some progress in addressing the curse of dimensionality in clustering tasks. However, it combines the K-means clustering and dimensionality reduction processes for optimization, leading to limitations in the clustering effect due to the introduced hyperparameters and the initialization of clustering centers. Moreover, maintaining class balance during clustering remains challenging. To overcome these issues, we propose a unified framework that integrates manifold learning with K-means, resulting in the self-supervised graph embedding framework. Specifically, we establish a connection between K-means and the manifold structure, allowing us to perform K-means without explicitly defining centroids. Additionally, we use this centroid-free K-means to generate labels in low-dimensional space and subsequently utilize the label information to determine the similarity between samples. This approach ensures consistency between the manifold structure and the labels. Our model effectively achieves one-step clustering without the need for redundant balancing hyperparameters. Notably, we have discovered that maximizing the $\ell_{2,1}$-norm naturally maintains class balance during clustering, a result that we have theoretically proven. Finally, experiments on multiple datasets demonstrate that the clustering results of Our-LPP and Our-MFA exhibit excellent and reliable performance.
Authors: Kin Wai Lau, Yasar Abbas Ur Rehman, Pedro Porto Buarque de Gusm\~ao, Lai-Man Po, Lan Ma, Yuyang Xie
Abstract: Federated Learning (FL) has emerged as a privacy-preserving method for training machine learning models in a distributed manner on edge devices. However, on-device models face inherent computational power and memory limitations, potentially resulting in constrained gradient updates. As the model's size increases, the frequency of gradient updates on edge devices decreases, ultimately leading to suboptimal training outcomes during any particular FL round. This limits the feasibility of deploying advanced and large-scale models on edge devices, hindering the potential for performance enhancements. To address this issue, we propose FedRepOpt, a gradient re-parameterized optimizer for FL. The gradient re-parameterized method allows training a simple local model with a similar performance as a complex model by modifying the optimizer's gradients according to a set of model-specific hyperparameters obtained from the complex models. In this work, we focus on VGG-style and Ghost-style models in the FL environment. Extensive experiments demonstrate that models using FedRepOpt obtain a significant boost in performance of 16.7% and 11.4% compared to the RepGhost-style and RepVGG-style networks, while also demonstrating a faster convergence time of 11.7% and 57.4% compared to their complex structure.
Authors: Sukai Huang, Nir Lipovetzky, Trevor Cohn
Abstract: Vision-language models (VLMs) have gained traction as auxiliary reward models to provide more informative reward signals in sparse reward environments. However, our work reveals a critical vulnerability of this method: a small amount of noise in the reward signal can severely degrade agent performance. In challenging environments with sparse rewards, we show that reinforcement learning agents using VLM-based reward models without proper noise handling perform worse than agents relying solely on exploration-driven methods. We hypothesize that false positive rewards -- where the reward model incorrectly assigns rewards to trajectories that do not fulfill the given instruction -- are more detrimental to learning than false negatives. Our analysis confirms this hypothesis, revealing that the widely used cosine similarity metric, when applied to comparing agent trajectories and language instructions, is prone to generating false positive reward signals. To address this, we introduce BiMI (Binary Mutual Information), a novel noise-resilient reward function. Our experiments demonstrate that, BiMI significantly boosts the agent performance, with an average improvement ratio of 44.5\% across diverse environments with learned, non-oracle VLMs, thereby making VLM-based reward models practical for real-world applications.
Authors: Xiaoyu He, Chenlin Wu, Zike Li, Zibin Zheng
Abstract: Federated learning is a distributed learning framework which enables clients to train models individually and to upload their model updates for aggregation. The local training process heavily relies on distributed gradient descent techniques. In the situation where gradient information is not available, the gradients need to be estimated from zeroth-order information, which typically involves computing finite-differences along isotropic random directions. This method suffers from high estimation errors, as the geometric features of the objective landscape may be overlooked during the isotropic sampling. In this work, we propose a non-isotropic sampling method to improve the gradient estimation procedure. Gradients in our method are estimated in a subspace spanned by historical trajectories of solutions, aiming to encourage the exploration of promising regions and hence improve the convergence. We implement this method in zeroth-order federated settings, and show that the convergence rate aligns with existing ones while introducing no significant overheads in communication or local computation. The effectiveness of our proposal is verified on several numerical experiments in comparison to several commonly-used zeroth-order federated optimization algorithms.
Authors: Bo Yue, Jian Li, Guiliang Liu
Abstract: To obtain the optimal constraints in complex environments, Inverse Constrained Reinforcement Learning (ICRL) seeks to recover these constraints from expert demonstrations in a data-driven manner. Existing ICRL algorithms collect training samples from an interactive environment. However, the efficacy and efficiency of these sampling strategies remain unknown. To bridge this gap, we introduce a strategic exploration framework with provable efficiency. Specifically, we define a feasible constraint set for ICRL problems and investigate how expert policy and environmental dynamics influence the optimality of constraints. Motivated by our findings, we propose two exploratory algorithms to achieve efficient constraint inference via 1) dynamically reducing the bounded aggregate error of cost estimation and 2) strategically constraining the exploration policy. Both algorithms are theoretically grounded with tractable sample complexity. We empirically demonstrate the performance of our algorithms under various environments.
Authors: Marco Palena, Tania Cerquitelli, Carla Fabiana Chiasserini
Abstract: Motivated by the proliferation of Internet-of-Thing (IoT) devices and the rapid advances in the field of deep learning, there is a growing interest in pushing deep learning computations, conventionally handled by the cloud, to the edge of the network to deliver faster responses to end users, reduce bandwidth consumption to the cloud, and address privacy concerns. However, to fully realize deep learning at the edge, two main challenges still need to be addressed: (i) how to meet the high resource requirements of deep learning on resource-constrained devices, and (ii) how to leverage the availability of multiple streams of spatially correlated data, to increase the effectiveness of deep learning and improve application-level performance. To address the above challenges, we explore collaborative inference at the edge, in which edge nodes and end devices share correlated data and the inference computational burden by leveraging different ways to split computation and fuse data. Besides traditional centralized and distributed schemes for edge-end device collaborative inference, we introduce selective schemes that decrease bandwidth resource consumption by effectively reducing data redundancy. As a reference scenario, we focus on multi-view classification in a networked system in which sensing nodes can capture overlapping fields of view. The proposed schemes are compared in terms of accuracy, computational expenditure at the nodes, communication overhead, inference latency, robustness, and noise sensitivity. Experimental results highlight that selective collaborative schemes can achieve different trade-offs between the above performance metrics, with some of them bringing substantial communication savings (from 18% to 74% of the transmitted data with respect to centralized inference) while still keeping the inference accuracy well above 90%.
Authors: Minjae Ok, Simon Kl\"uttermann, Emmanuel M\"uller
Abstract: Anomaly detection is a dynamic field, in which the evaluation of models plays a critical role in understanding their effectiveness. The selection and interpretation of the evaluation metrics are pivotal, particularly in scenarios with varying amounts of anomalies. This study focuses on examining the behaviors of three widely used anomaly detection metrics under different conditions: F1 score, Receiver Operating Characteristic Area Under Curve (ROC AUC), and Precision-Recall Curve Area Under Curve (AUCPR). Our study critically analyzes the extent to which these metrics provide reliable and distinct insights into model performance, especially considering varying levels of outlier fractions and contamination thresholds in datasets. Through a comprehensive experimental setup involving widely recognized algorithms for anomaly detection, we present findings that challenge the conventional understanding of these metrics and reveal nuanced behaviors under varying conditions. We demonstrated that while the F1 score and AUCPR are sensitive to outlier fractions, the ROC AUC maintains consistency and is unaffected by such variability. Additionally, under conditions of a fixed outlier fraction in the test set, we observe an alignment between ROC AUC and AUCPR, indicating that the choice between these two metrics may be less critical in such scenarios. The results of our study contribute to a more refined understanding of metric selection and interpretation in anomaly detection, offering valuable insights for both researchers and practitioners in the field.
Authors: Xiaoming Shi, Shiyu Wang, Yuqi Nie, Dianqi Li, Zhou Ye, Qingsong Wen, Ming Jin
Abstract: Deep learning for time series forecasting has seen significant advancements over the past decades. However, despite the success of large-scale pre-training in language and vision domains, pre-trained time series models remain limited in scale and operate at a high cost, hindering the development of larger capable forecasting models in real-world applications. In response, we introduce Time-MoE, a scalable and unified architecture designed to pre-train larger, more capable forecasting foundation models while reducing inference costs. By leveraging a sparse mixture-of-experts (MoE) design, Time-MoE enhances computational efficiency by activating only a subset of networks for each prediction, reducing computational load while maintaining high model capacity. This allows Time-MoE to scale effectively without a corresponding increase in inference costs. Time-MoE comprises a family of decoder-only transformer models that operate in an auto-regressive manner and support flexible forecasting horizons with varying input context lengths. We pre-trained these models on our newly introduced large-scale data Time-300B, which spans over 9 domains and encompassing over 300 billion time points. For the first time, we scaled a time series foundation model up to 2.4 billion parameters, achieving significantly improved forecasting precision. Our results validate the applicability of scaling laws for training tokens and model size in the context of time series forecasting. Compared to dense models with the same number of activated parameters or equivalent computation budgets, our models consistently outperform them by large margin. These advancements position Time-MoE as a state-of-the-art solution for tackling real-world time series forecasting challenges with superior capability, efficiency, and flexibility.
Authors: Sjoerd de Vries, Dirk Thierens
Abstract: In supervised machine learning, models are typically trained using data with hard labels, i.e., definite assignments of class membership. This traditional approach, however, does not take the inherent uncertainty in these labels into account. We investigate whether incorporating label uncertainty, represented as discrete probability distributions over the class labels -- known as soft labels -- improves the predictive performance of classification models. We first demonstrate the potential value of soft label learning (SLL) for estimating model parameters in a simulation experiment, particularly for limited sample sizes and imbalanced data. Subsequently, we compare the performance of various wrapper methods for learning from both hard and soft labels using identical base classifiers. On real-world-inspired synthetic data with clean labels, the SLL methods consistently outperform hard label methods. Since real-world data is often noisy and precise soft labels are challenging to obtain, we study the effect that noisy probability estimates have on model performance. Alongside conventional noise models, our study examines four types of miscalibration that are known to affect human annotators. The results show that SLL methods outperform the hard label methods in the majority of settings. Finally, we evaluate the methods on a real-world dataset with confidence scores, where the SLL methods are shown to match the traditional methods for predicting the (noisy) hard labels while providing more accurate confidence estimates.
Authors: Huixin Guan
Abstract: This paper presents an experimental study focused on understanding the simplification properties of neural networks under different hyperparameter configurations, specifically investigating the effects on Lempel Ziv complexity and sensitivity. By adjusting key hyperparameters such as activation functions, hidden layers, and learning rate, this study evaluates how these parameters impact the complexity of network outputs and their robustness to input perturbations. The experiments conducted using the MNIST dataset aim to provide insights into the relationships between hyperparameters, complexity, and sensitivity, contributing to a deeper theoretical understanding of these concepts in neural networks.
Authors: \'Africa Peri\'a\~nez, Ana Fern\'andez del R\'io, Ivan Nazarov, Enric Jan\'e, Moiz Hassan, Aditya Rastogi, Dexian Tang
Abstract: Mobile health has the potential to revolutionize health care delivery and patient engagement. In this work, we discuss how integrating Artificial Intelligence into digital health applications-focused on supply chain, patient management, and capacity building, among other use cases-can improve the health system and public health performance. We present an Artificial Intelligence and Reinforcement Learning platform that allows the delivery of adaptive interventions whose impact can be optimized through experimentation and real-time monitoring. The system can integrate multiple data sources and digital health applications. The flexibility of this platform to connect to various mobile health applications and digital devices and send personalized recommendations based on past data and predictions can significantly improve the impact of digital tools on health system outcomes. The potential for resource-poor settings, where the impact of this approach on health outcomes could be more decisive, is discussed specifically. This framework is, however, similarly applicable to improving efficiency in health systems where scarcity is not an issue.
Authors: Francesco D'Amico, Matteo Negri
Abstract: Transformers are one of the most successful architectures of modern neural networks. At their core there is the so-called attention mechanism, which recently interested the physics community as it can be written as the derivative of an energy function in certain cases: while it is possible to write the cross-attention layer as a modern Hopfield network, the same is not possible for the self-attention, which is used in the GPT architectures and other autoregressive models. In this work we show that it is possible to obtain the self-attention layer as the derivative of local energy terms, which resemble a pseudo-likelihood. We leverage the analogy with pseudo-likelihood to design a recurrent model that can be trained without backpropagation: the dynamics shows transient states that are strongly correlated with both train and test examples. Overall we present a novel framework to interpret self-attention as an attractor network, potentially paving the way for new theoretical approaches inspired from physics to understand transformers.
Authors: Andrei Margeloiu, Xiangjian Jiang, Nikola Simidjievski, Mateja Jamnik
Abstract: Data collection is often difficult in critical fields such as medicine, physics, and chemistry. As a result, classification methods usually perform poorly with these small datasets, leading to weak predictive performance. Increasing the training set with additional synthetic data, similar to data augmentation in images, is commonly believed to improve downstream classification performance. However, current tabular generative methods that learn either the joint distribution $ p(\mathbf{x}, y) $ or the class-conditional distribution $ p(\mathbf{x} \mid y) $ often overfit on small datasets, resulting in poor-quality synthetic data, usually worsening classification performance compared to using real data alone. To solve these challenges, we introduce TabEBM, a novel class-conditional generative method using Energy-Based Models (EBMs). Unlike existing methods that use a shared model to approximate all class-conditional densities, our key innovation is to create distinct EBM generative models for each class, each modelling its class-specific data distribution individually. This approach creates robust energy landscapes, even in ambiguous class distributions. Our experiments show that TabEBM generates synthetic data with higher quality and better statistical fidelity than existing methods. When used for data augmentation, our synthetic data consistently improves the classification performance across diverse datasets of various sizes, especially small ones.
Authors: Ziyu Zhao, Tao Shen, Didi Zhu, Zexi Li, Jing Su, Xuwu Wang, Kun Kuang, Fei Wu
Abstract: Low-Rank Adaptation (LoRA) has emerged as a popular technique for fine-tuning large language models (LLMs) to various domains due to its modular design and widespread availability on platforms like Huggingface. This modularity has sparked interest in combining multiple LoRAs to enhance LLM capabilities. However, existing methods for LoRA composition primarily focus on task-specific adaptations that require additional training, and current model merging techniques often fail to fully leverage LoRA's modular nature, leading to parameter interference and performance degradation. In this paper, we investigate the feasibility of disassembling and reassembling multiple LoRAs at a finer granularity, analogous to assembling LEGO blocks. We introduce the concept of Minimal Semantic Units (MSUs), where the parameters corresponding to each rank in LoRA function as independent units. These MSUs demonstrate permutation invariance and concatenation-summation equivalence properties, enabling flexible combinations to create new LoRAs. Building on these insights, we propose the LoRA-LEGO framework. This framework conducts rank-wise parameter clustering by grouping MSUs from different LoRAs into $k$ clusters. The centroid of each cluster serves as a representative MSU, enabling the assembly of a merged LoRA with an adjusted rank of $k$. Additionally, we apply a dual reweighting strategy to optimize the scale of the merged LoRA. Experiments across various benchmarks demonstrate that our method outperforms existing approaches in LoRA merging.
Authors: Aldo Pacchiano
Abstract: Many works have developed algorithms no-regret algorithms for contextual bandits with function approximation, where the mean rewards over context-action pairs belongs to a function class. Although there are many approaches to this problem, one that has gained in importance is the use of algorithms based on the optimism principle such as optimistic least squares. It can be shown the regret of this algorithm scales as square root of the product of the eluder dimension (a statistical measure of the complexity of the function class), the logarithm of the function class size and the time horizon. Unfortunately, even if the variance of the measurement noise of the rewards at each time is changing and is very small, the regret of the optimistic least squares algorithm scales with square root of the time horizon. In this work we are the first to develop algorithms that satisfy regret bounds of scaling not with the square root of the time horizon, but the square root of the sum of the measurement variances in the setting of contextual bandits with function approximation when the variances are unknown. These bounds generalize existing techniques for deriving second order bounds in contextual linear problems.
Authors: Matheus Camilo da Silva, Gabriel Marques Tavares, Eric Medvet, Sylvio Barbon Junior
Abstract: The Problem-oriented AutoML in Clustering (PoAC) framework introduces a novel, flexible approach to automating clustering tasks by addressing the shortcomings of traditional AutoML solutions. Conventional methods often rely on predefined internal Clustering Validity Indexes (CVIs) and static meta-features, limiting their adaptability and effectiveness across diverse clustering tasks. In contrast, PoAC establishes a dynamic connection between the clustering problem, CVIs, and meta-features, allowing users to customize these components based on the specific context and goals of their task. At its core, PoAC employs a surrogate model trained on a large meta-knowledge base of previous clustering datasets and solutions, enabling it to infer the quality of new clustering pipelines and synthesize optimal solutions for unseen datasets. Unlike many AutoML frameworks that are constrained by fixed evaluation metrics and algorithm sets, PoAC is algorithm-agnostic, adapting seamlessly to different clustering problems without requiring additional data or retraining. Experimental results demonstrate that PoAC not only outperforms state-of-the-art frameworks on a variety of datasets but also excels in specific tasks such as data visualization, and highlight its ability to dynamically adjust pipeline configurations based on dataset complexity.
Authors: Zheda Mai, Arpita Chowdhury, Ping Zhang, Cheng-Hao Tu, Hong-You Chen, Vardaan Pahuja, Tanya Berger-Wolf, Song Gao, Charles Stewart, Yu Su, Wei-Lun Chao
Abstract: Fine-tuning is arguably the most straightforward way to tailor a pre-trained model (e.g., a foundation model) to downstream applications, but it also comes with the risk of losing valuable knowledge the model had learned in pre-training. For example, fine-tuning a pre-trained classifier capable of recognizing a large number of classes to master a subset of classes at hand is shown to drastically degrade the model's accuracy in the other classes it had previously learned. As such, it is hard to further use the fine-tuned model when it encounters classes beyond the fine-tuning data. In this paper, we systematically dissect the issue, aiming to answer the fundamental question, ''What has been damaged in the fine-tuned model?'' To our surprise, we find that the fine-tuned model neither forgets the relationship among the other classes nor degrades the features to recognize these classes. Instead, the fine-tuned model often produces more discriminative features for these other classes, even if they were missing during fine-tuning! {What really hurts the accuracy is the discrepant logit scales between the fine-tuning classes and the other classes}, implying that a simple post-processing calibration would bring back the pre-trained model's capability and at the same time unveil the feature improvement over all classes. We conduct an extensive empirical study to demonstrate the robustness of our findings and provide preliminary explanations underlying them, suggesting new directions for future theoretical analysis. Our code is available at https://github.com/OSU-MLB/Fine-Tuning-Is-Fine-If-Calibrated.
URLs: https://github.com/OSU-MLB/Fine-Tuning-Is-Fine-If-Calibrated.
Authors: Henry Musto, Daniel Stamate, Doina Logofatu, Daniel Stahl
Abstract: The paper proposes a novel approach of survival transformers and extreme gradient boosting models in predicting cognitive deterioration in individuals with mild cognitive impairment (MCI) using metabolomics data in the ADNI cohort. By leveraging advanced machine learning and transformer-based techniques applied in survival analysis, the proposed approach highlights the potential of these techniques for more accurate early detection and intervention in Alzheimer's dementia disease. This research also underscores the importance of non-invasive biomarkers and innovative modelling tools in enhancing the accuracy of dementia risk assessments, offering new avenues for clinical practice and patient care. A comprehensive Monte Carlo simulation procedure consisting of 100 repetitions of a nested cross-validation in which models were trained and evaluated, indicates that the survival machine learning models based on Transformer and XGBoost achieved the highest mean C-index performances, namely 0.85 and 0.8, respectively, and that they are superior to the conventional survival analysis Cox Proportional Hazards model which achieved a mean C-Index of 0.77. Moreover, based on the standard deviations of the C-Index performances obtained in the Monte Carlo simulation, we established that both survival machine learning models above are more stable than the conventional statistical model.
Authors: Yu Wu, Anand Sarwate
Abstract: Machine learning models implemented in hardware on physical devices may be deployed for a long time. The computational abilities of the device may be limited and become outdated with respect to newer improvements. Because of the size of ML models, offloading some computation (e.g. to an edge cloud) can help such legacy devices. We cast this problem in the framework of learning with abstention (LWA) in which the expert (edge) must be trained to assist the client (device). Prior work on LWA trains the client assuming the edge is either an oracle or a human expert. In this work, we formalize the reverse problem of training the expert for a fixed (legacy) client. As in LWA, the client uses a rejection rule to decide when to offload inference to the expert (at a cost). We find the Bayes-optimal rule, prove a generalization bound, and find a consistent surrogate loss function. Empirical results show that our framework outperforms confidence-based rejection rules.
Authors: Victor Sechaud (Phys-ENS), Laurent Jacques (ICTEAM), Patrice Abry (Phys-ENS), Juli\'an Tachella (Phys-ENS)
Abstract:
In numerous inverse problems, state-of-the-art solving strategies involve training neural networks from ground truth and associated measurement datasets that, however, may be expensive or impossible to collect. Recently, self-supervised learning techniques have emerged, with the major advantage of no longer requiring ground truth data. Most theoretical and experimental results on self-supervised learning focus on linear inverse problems. The present work aims to study self-supervised learning for the non-linear inverse problem of recovering audio signals from clipped measurements. An equivariance-based selfsupervised loss is proposed and studied. Performance is assessed on simulated clipped measurements with controlled and varied levels of clipping, and further reported on standard real music signals. We show that the performance of the proposed equivariance-based self-supervised declipping strategy compares favorably to fully supervised learning while only requiring clipped measurements alone for training.
Authors: Kaiwen Tang, Zhanglu Yan, Weng-Fai Wong
Abstract: For reasons such as privacy, there are use cases for language models at the edge. This has given rise to small language models (SLMs) targeted for deployment in resource-constrained devices where energy efficiency is a significant concern. Spiking neural networks (SNNs) offer a promising solution due to their energy efficiency, and there are already works on realizing transformer-based models on SNNs. However, key operations like softmax and layer normalization (LN) are difficult to implement on neuromorphic hardware, and many of these early works sidestepped them. To address these challenges, we introduce Sorbet, a transformer-based spiking language model that is more neuromorphic hardware-compatible. Sorbet incorporates a novel shifting-based softmax called PTsoftmax and a power normalization method using bit-shifting (BSPN), both designed to replace the respective energy-intensive operations. By leveraging knowledge distillation and model quantization, Sorbet achieved a highly compressed binary weight model that maintains competitive performance while significantly reducing energy consumption. We validate Sorbet's effectiveness through extensive testing on the GLUE benchmark and a series of ablation studies, demonstrating its potential as an energy-efficient solution for language model inference.
Authors: Ahmad Hafez
Abstract: Recently, there has been a substantial amount of interest in GNN-based anomaly detection. Existing efforts have focused on simultaneously mastering the node representations and the classifier necessary for identifying abnormalities with relatively shallow models to create an embedding. Therefore, the existing state-of-the-art models are incapable of capturing nonlinear network information and producing suboptimal outcomes. In this thesis, we deploy decoupled GNNs to overcome this issue. Specifically, we decouple the essential node representations and classifier for detecting anomalies. In addition, for node representation learning, we develop a GNN architecture with two modules for aggregating node feature information to produce the final node embedding. Finally, we conduct empirical experiments to verify the effectiveness of our proposed approach. The findings demonstrate that decoupled training along with the global context enhanced representation of the nodes is superior to the state-of-the-art models in terms of AUC and introduces a novel way of capturing the node information.
Authors: Conor O'Sullivan, Ambrish Kashyap, Seamus Coveney, Xavier Monteys, Soumyabrata Dev
Abstract: Ireland's coastline, a critical and dynamic resource, is facing challenges such as erosion, sedimentation, and human activities. Monitoring these changes is a complex task we approach using a combination of satellite imagery and deep learning methods. However, limited research exists in this area, particularly for Ireland. This paper presents the Landsat Irish Coastal Segmentation (LICS) dataset, which aims to facilitate the development of deep learning methods for coastal water body segmentation while addressing modelling challenges specific to Irish meteorology and coastal types. The dataset is used to evaluate various automated approaches for segmentation, with U-NET achieving the highest accuracy of 95.0% among deep learning methods. Nevertheless, the Normalised Difference Water Index (NDWI) benchmark outperformed U-NET with an average accuracy of 97.2%. The study suggests that deep learning approaches can be further improved with more accurate training data and by considering alternative measurements of erosion. The LICS dataset and code are freely available to support reproducible research and further advancements in coastal monitoring efforts.
Authors: Brandon J. McMahan, Zhenghao Peng, Bolei Zhou, Jonathan C. Kao
Abstract: The rapid development of artificial intelligence (AI) has unearthed the potential to assist humans in controlling advanced technologies. Shared autonomy (SA) facilitates control by combining inputs from a human pilot and an AI copilot. In prior SA studies, the copilot is constantly active in determining the action played at each time step. This limits human autonomy and may have deleterious effects on performance. In general, the amount of helpful copilot assistance can vary greatly depending on the task dynamics. We therefore hypothesize that human autonomy and SA performance improve through dynamic and selective copilot intervention. To address this, we develop a goal-agnostic intervention assistance (IA) that dynamically shares control by having the copilot intervene only when the expected value of the copilot's action exceeds that of the human's action across all possible goals. We implement IA with a diffusion copilot (termed IDA) trained on expert demonstrations with goal masking. We prove a lower bound on the performance of IA that depends on pilot and copilot performance. Experiments with simulated human pilots show that IDA achieves higher performance than pilot-only and traditional SA control in variants of the Reacher environment and Lunar Lander. We then demonstrate that IDA achieves better control in Lunar Lander with human-in-the-loop experiments. Human participants report greater autonomy with IDA and prefer IDA over pilot-only and traditional SA control. We attribute the success of IDA to preserving human autonomy while simultaneously offering assistance to prevent the human pilot from entering universally bad states.
Authors: Iqra Yousaf
Abstract: This research investigates the use of artificial intelligence and machine learning techniques to predict the toxicity of nanoparticles, a pressing concern due to their pervasive use in various industries and the inherent challenges in assessing their biological interactions. Employing models such as Decision Trees, Random Forests, and XGBoost, the study focuses on analyzing physicochemical properties like size, shape, surface charge, and chemical composition to determine their influence on toxicity. Our findings highlight the significant role of oxygen atoms, particle size, surface area, dosage, and exposure duration in affecting toxicity levels. The use of machine learning allows for a nuanced understanding of the intricate patterns these properties form in biological contexts, surpassing traditional analysis methods in efficiency and predictive power. These advancements aid in developing safer nanomaterials through computational chemistry, reducing reliance on costly and time-consuming experimental methods. This approach not only enhances our understanding of nanoparticle behavior in biological systems but also streamlines the safety assessment process, marking a significant stride towards integrating computational techniques in nanotoxicology.
Authors: Grant Rosario, David Noever
Abstract: The utility of Synthetic Aperture Radar (SAR) imagery in remote sensing and satellite image analysis is well established, offering robustness under various weather and lighting conditions. However, SAR images, characterized by their unique structural and texture characteristics, often pose interpretability challenges for analysts accustomed to electrooptical (EO) imagery. This application compares state-of-the-art Generative Adversarial Networks (GANs) including Pix2Pix, CycleGan, S-CycleGan, and a novel dual?generator GAN utilizing partial convolutions and a novel dual-generator architecture utilizing transformers. These models are designed to progressively refine the realism in the translated optical images, thereby enhancing the visual interpretability of SAR data. We demonstrate the efficacy of our approach through qualitative and quantitative evaluations, comparing the synthesized EO images with actual EO images in terms of visual fidelity and feature preservation. The results show significant improvements in interpretability, making SAR data more accessible for analysts familiar with EO imagery. Furthermore, we explore the potential of this technology in various applications, including environmental monitoring, urban planning, and military reconnaissance, where rapid, accurate interpretation of SAR data is crucial. Our research contributes to the field of remote sensing by bridging the gap between SAR and EO imagery, offering a novel tool for enhanced data interpretation and broader application of SAR technology in various domains.
Authors: Dongqi Cai, Shangguang Wang, Chen Peng, Zeling Zhang, Mengwei Xu
Abstract: Human memory is inherently prone to forgetting. To address this, multimodal embedding models have been introduced, which transform diverse real-world data into a unified embedding space. These embeddings can be retrieved efficiently, aiding mobile users in recalling past information. However, as model complexity grows, so do its resource demands, leading to reduced throughput and heavy computational requirements that limit mobile device implementation. In this paper, we introduce RECALL, a novel on-device multimodal embedding system optimized for resource-limited mobile environments. RECALL achieves high-throughput, accurate retrieval by generating coarse-grained embeddings and leveraging query-based filtering for refined retrieval. Experimental results demonstrate that RECALL delivers high-quality embeddings with superior throughput, all while operating unobtrusively with minimal memory and energy consumption.
Authors: Franciszek Szewczyk, Gilles Louppe, Matthia Sabatelli
Abstract: Lifelike visualizations in design, cinematography, and gaming rely on precise physics simulations, typically requiring extensive computational resources and detailed physical input. This paper presents a method that can infer a system's physical properties from a short video, eliminating the need for explicit parameter input, provided it is close to the training condition. The learned representation is then used within a Graph Network-based Simulator to emulate the trajectories of physical systems. We demonstrate that the video-derived encodings effectively capture the physical properties of the system and showcase a linear dependence between some of the encodings and the system's motion.
Authors: Fabio Greg\'orio, Rafaela Castro, Kele Belloze, Rui Pedro Lopes, Eduardo Bezerra
Abstract: The Brazilian Constitution, known as the Citizen's Charter, provides mechanisms for citizens to petition the Judiciary, including the so-called special appeal. This specific type of appeal aims to standardize the legal interpretation of Brazilian legislation in cases where the decision contradicts federal laws. The handling of special appeals is a daily task in the Judiciary, regularly presenting significant demands in its courts. We propose a new method called GLARE, based on unsupervised machine learning, to help the legal analyst classify a special appeal on a topic from a list made available by the National Court of Brazil (STJ). As part of this method, we propose a modification of the graph-based LexRank algorithm, which we call Guided LexRank. This algorithm generates the summary of a special appeal. The degree of similarity between the generated summary and different topics is evaluated using the BM25 algorithm. As a result, the method presents a ranking of themes most appropriate to the analyzed special appeal. The proposed method does not require prior labeling of the text to be evaluated and eliminates the need for large volumes of data to train a model. We evaluate the effectiveness of the method by applying it to a special appeal corpus previously classified by human experts.
Authors: Luis Gustavo Giacon Villani, Samuel da Silva, Americo Cunha Jr
Abstract: The damage detection problem in mechanical systems, using vibration measurements, is commonly called Structural Health Monitoring (SHM). Many tools are able to detect damages by changes in the vibration pattern, mainly, when damages induce nonlinear behavior. However, a more difficult problem is to detect structural variation associated with damage, when the mechanical system has nonlinear behavior even in the reference condition. In these cases, more sophisticated methods are required to detect if the changes in the response are based on some structural variation or changes in the vibration regime, because both can generate nonlinearities. Among the many ways to solve this problem, the use of the Volterra series has several favorable points, because they are a generalization of the linear convolution, allowing the separation of linear and nonlinear contributions by input filtering through the Volterra kernels. On the other hand, the presence of uncertainties in mechanical systems, due to noise, geometric imperfections, manufacturing irregularities, environmental conditions, and others, can also change the responses, becoming more difficult the damage detection procedure. An approach based on a stochastic version of Volterra series is proposed to be used in the detection of a breathing crack in a beam vibrating in a nonlinear regime of motion, even in reference condition (without crack). The system uncertainties are simulated by the variation imposed in the linear stiffness and damping coefficient. The results show, that the nonlinear analysis done, considering the high order Volterra kernels, allows the approach to detect the crack with a small propagation and probability confidence, even in the presence of uncertainties.
Authors: Zhihong Lei, Xingyu Na, Mingbin Xu, Ernest Pusateri, Christophe Van Gysel, Yuanyuan Zhang, Shiyi Han, Zhen Huang
Abstract: Large language models (LLMs) have shown superb capability of modeling multimodal signals including audio and text, allowing the model to generate spoken or textual response given a speech input. However, it remains a challenge for the model to recognize personal named entities, such as contacts in a phone book, when the input modality is speech. In this work, we start with a speech recognition task and propose a retrieval-based solution to contextualize the LLM: we first let the LLM detect named entities in speech without any context, then use this named entity as a query to retrieve phonetically similar named entities from a personal database and feed them to the LLM, and finally run context-aware LLM decoding. In a voice assistant task, our solution achieved up to 30.2% relative word error rate reduction and 73.6% relative named entity error rate reduction compared to a baseline system without contextualization. Notably, our solution by design avoids prompting the LLM with the full named entity database, making it highly efficient and applicable to large named entity databases.
Authors: Nikhil Raghav, Subhajit Saha, Md Sahidullah, Swagatam Das
Abstract: In this report, we describe the speaker diarization (SD) and language diarization (LD) systems developed by our team for the Second DISPLACE Challenge, 2024. Our contributions were dedicated to Track 1 for SD and Track 2 for LD in multilingual and multi-speaker scenarios. We investigated different speech enhancement techniques, voice activity detection (VAD) techniques, unsupervised domain categorization, and neural embedding extraction architectures. We also exploited the fusion of various embedding extraction models. We implemented our system with the open-source SpeechBrain toolkit. Our final submissions use spectral clustering for both the speaker and language diarization. We achieve about $7\%$ relative improvement over the challenge baseline in Track 1. We did not obtain improvement over the challenge baseline in Track 2.
Authors: Zheng Nan, Ting Dang, Vidhyasaharan Sethu, Beena Ahmed
Abstract: Relational thinking refers to the inherent ability of humans to form mental impressions about relations between sensory signals and prior knowledge, and subsequently incorporate them into their model of their world. Despite the crucial role relational thinking plays in human understanding of speech, it has yet to be leveraged in any artificial speech recognition systems. Recently, there have been some attempts to correct this oversight, but these have been limited to coarse utterance-level models that operate exclusively in the time domain. In an attempt to narrow the gap between artificial systems and human abilities, this paper presents a novel spectro-temporal relational thinking based acoustic modeling framework. Specifically, it first generates numerous probabilistic graphs to model the relationships among speech segments across both time and frequency domains. The relational information rooted in every pair of nodes within these graphs is then aggregated and embedded into latent representations that can be utilized by downstream tasks. Models built upon this framework outperform state-of-the-art systems with a 7.82\% improvement in phoneme recognition tasks over the TIMIT dataset. In-depth analyses further reveal that our proposed relational thinking modeling mainly improves the model's ability to recognize vowels, which are the most likely to be confused by phoneme recognizers.
Authors: Cassandra A. Cohen, William W. Cohen
Abstract: We propose a variant of chain of thought (CoT) prompting called Program Trace Prompting that makes explanations more observable while preserving the power, generality and flexibility of CoT. In our approach, few-shot CoT demonstrations are wrapped in a formal syntax based on Python, and each prompt: identifies and names steps; defines the input/output behavior of steps; and replaces CoT explanations of in-context examples with chains of these formalized steps on the same examples. Program Trace Prompting is applicable to many tasks, achieving strong results on the 23 diverse tasks in the BIG-Bench Hard benchmark. More importantly, by instrumenting explanations in this way, we enable new types of analysis. In particular, we identify "non-local errors" (which correspond to incorrectly learning the reasoning method illustrated in the demonstrations) as an unaddressed issue in CoT learning, and we present methods for verifying the modularity of steps in a CoT explanation.
Authors: Essa Jan, Nouar AlDahoul, Moiz Ali, Faizan Ahmad, Fareed Zaffar, Yasir Zaki
Abstract: Recent breakthroughs in Large Language Models (LLMs) have led to their adoption across a wide range of tasks, ranging from code generation to machine translation and sentiment analysis, etc. Red teaming/Safety alignment efforts show that fine-tuning models on benign (non-harmful) data could compromise safety. However, it remains unclear to what extent this phenomenon is influenced by different variables, including fine-tuning task, model calibrations, etc. This paper explores the task-wise safety degradation due to fine-tuning on downstream tasks such as summarization, code generation, translation, and classification across various calibration. Our results reveal that: 1) Fine-tuning LLMs for code generation and translation leads to the highest degradation in safety guardrails. 2) LLMs generally have weaker guardrails for translation and classification, with 73-92% of harmful prompts answered, across baseline and other calibrations, falling into one of two concern categories. 3) Current solutions, including guards and safety tuning datasets, lack cross-task robustness. To address these issues, we developed a new multitask safety dataset effectively reducing attack success rates across a range of tasks without compromising the model's overall helpfulness. Our work underscores the need for generalized alignment measures to ensure safer and more robust models.
Authors: Krishanu Das Baksi, Elijah Soba, John J. Higgins, Ravi Saini, Jaden Wood, Jane Cook, Jack Scott, Nirmala Pudota, Tim Weninger, Edward Bowen, Sanmitra Bhattacharya
Abstract: Medical coding is essential for standardizing clinical data and communication but is often time-consuming and prone to errors. Traditional Natural Language Processing (NLP) methods struggle with automating coding due to the large label space, lengthy text inputs, and the absence of supporting evidence annotations that justify code selection. Recent advancements in Generative Artificial Intelligence (AI) offer promising solutions to these challenges. In this work, we introduce MedCodER, a Generative AI framework for automatic medical coding that leverages extraction, retrieval, and re-ranking techniques as core components. MedCodER achieves a micro-F1 score of 0.60 on International Classification of Diseases (ICD) code prediction, significantly outperforming state-of-the-art methods. Additionally, we present a new dataset containing medical records annotated with disease diagnoses, ICD codes, and supporting evidence texts (https://doi.org/10.5281/zenodo.13308316). Ablation tests confirm that MedCodER's performance depends on the integration of each of its aforementioned components, as performance declines when these components are evaluated in isolation.
Authors: Shashi Shekhar Kumar, Anurag Harsh, Ritesh Chandra, Sonali Agarwal
Abstract: Cardiovascular disease (CVDs) is a rapidly rising global concern due to unhealthy diets, lack of physical activity, and other factors. According to the World Health Organization (WHO), primary risk factors include elevated blood pressure, glucose, blood lipids, and obesity. Recent research has focused on accurate and timely disease prediction to reduce risk and fatalities, often relying on predictive models trained on large datasets, which require intensive training. An intelligent system for CVDs patients could greatly assist in making informed decisions by effectively analyzing health parameters. Complex Event Processing (CEP) has emerged as a valuable method for solving real-time challenges by aggregating patterns of interest and their causes and effects on end users. In this work, we propose a fuzzy rule-based system for monitoring clinical data to provide real-time decision support. We designed fuzzy rules based on clinical and WHO standards to ensure accurate predictions. Our integrated approach uses Apache Kafka and Spark for data streaming, and the Siddhi CEP engine for event processing. Additionally, we pass numerous cardiovascular disease-related parameters through CEP engines to ensure fast and reliable prediction decisions. To validate the effectiveness of our approach, we simulated real-time, unseen data to predict cardiovascular disease. Using synthetic data (1000 samples), we categorized it into "Very Low Risk, Low Risk, Medium Risk, High Risk, and Very High Risk." Validation results showed that 20% of samples were categorized as very low risk, 15-45% as low risk, 35-65% as medium risk, 55-85% as high risk, and 75% as very high risk.
Authors: Suryansh Vidya, Kush Gupta, Amir Aly, Andy Wills, Emmanuel Ifeachor, Rohit Shankar
Abstract: Early diagnosis and intervention for Autism Spectrum Disorder (ASD) has been shown to significantly improve the quality of life of autistic individuals. However, diagnostics methods for ASD rely on assessments based on clinical presentation that are prone to bias and can be challenging to arrive at an early diagnosis. There is a need for objective biomarkers of ASD which can help improve diagnostic accuracy. Deep learning (DL) has achieved outstanding performance in diagnosing diseases and conditions from medical imaging data. Extensive research has been conducted on creating models that classify ASD using resting-state functional Magnetic Resonance Imaging (fMRI) data. However, existing models lack interpretability. This research aims to improve the accuracy and interpretability of ASD diagnosis by creating a DL model that can not only accurately classify ASD but also provide explainable insights into its working. The dataset used is a preprocessed version of the Autism Brain Imaging Data Exchange (ABIDE) with 884 samples. Our findings show a model that can accurately classify ASD and highlight critical brain regions differing between ASD and typical controls, with potential implications for early diagnosis and understanding of the neural basis of ASD. These findings are validated by studies in the literature that use different datasets and modalities, confirming that the model actually learned characteristics of ASD and not just the dataset. This study advances the field of explainable AI in medical imaging by providing a robust and interpretable model, thereby contributing to a future with objective and reliable ASD diagnostics.
Authors: Boxun Xu, Hejia Geng, Yuxuan Yin, Peng Li
Abstract: Vision Transformers (ViT) are current high-performance models of choice for various vision applications. Recent developments have given rise to biologically inspired spiking transformers that thrive in ultra-low power operations on neuromorphic hardware, however, without fully unlocking the potential of spiking neural networks. We introduce DS2TA, a Denoising Spiking transformer with attenuated SpatioTemporal Attention, designed specifically for vision applications. DS2TA introduces a new spiking attenuated spatiotemporal attention mechanism that considers input firing correlations occurring in both time and space, thereby fully harnessing the computational power of spiking neurons at the core of the transformer architecture. Importantly, DS2TA facilitates parameter-efficient spatiotemporal attention computation without introducing extra weights. DS2TA employs efficient hashmap-based nonlinear spiking attention denoisers to enhance the robustness and expressive power of spiking attention maps. DS2TA demonstrates state-of-the-art performances on several widely adopted static image and dynamic neuromorphic datasets. Operated over 4 time steps, DS2TA achieves 94.92% top-1 accuracy on CIFAR10 and 77.47% top-1 accuracy on CIFAR100, as well as 79.1% and 94.44% on CIFAR10-DVS and DVS-Gesture using 10 time steps.
Authors: G M Shahariar, Jia Chen, Jiachen Li, Yue Dong
Abstract: Recent studies show that text-to-image (T2I) models are vulnerable to adversarial attacks, especially with noun perturbations in text prompts. In this study, we investigate the impact of adversarial attacks on different POS tags within text prompts on the images generated by T2I models. We create a high-quality dataset for realistic POS tag token swapping and perform gradient-based attacks to find adversarial suffixes that mislead T2I models into generating images with altered tokens. Our empirical results show that the attack success rate (ASR) varies significantly among different POS tag categories, with nouns, proper nouns, and adjectives being the easiest to attack. We explore the mechanism behind the steering effect of adversarial suffixes, finding that the number of critical tokens and content fusion vary among POS tags, while features like suffix transferability are consistent across categories. We have made our implementation publicly available at - https://github.com/shahariar-shibli/Adversarial-Attack-on-POS-Tags.
URLs: https://github.com/shahariar-shibli/Adversarial-Attack-on-POS-Tags.
Authors: Burooj Ghani, Vincent J. Kalkman, Bob Planqu\'e, Willem-Pier Vellinga, Lisa Gill, Dan Stowell
Abstract: Animal sounds can be recognised automatically by machine learning, and this has an important role to play in biodiversity monitoring. Yet despite increasingly impressive capabilities, bioacoustic species classifiers still exhibit imbalanced performance across species and habitats, especially in complex soundscapes. In this study, we explore the effectiveness of transfer learning in large-scale bird sound classification across various conditions, including single- and multi-label scenarios, and across different model architectures such as CNNs and Transformers. Our experiments demonstrate that both fine-tuning and knowledge distillation yield strong performance, with cross-distillation proving particularly effective in improving in-domain performance on Xeno-canto data. However, when generalizing to soundscapes, shallow fine-tuning exhibits superior performance compared to knowledge distillation, highlighting its robustness and constrained nature. Our study further investigates how to use multi-species labels, in cases where these are present but incomplete. We advocate for more comprehensive labeling practices within the animal sound community, including annotating background species and providing temporal details, to enhance the training of robust bird sound classifiers. These findings provide insights into the optimal reuse of pretrained models for advancing automatic bioacoustic recognition.
Authors: EungGu Kang, Byeonghun Lee, Sunghoon Im, Kyong Hwan Jin
Abstract: Multi frame super-resolution(MFSR) achieves higher performance than single image super-resolution (SISR), because MFSR leverages abundant information from multiple frames. Recent MFSR approaches adapt the deformable convolution network (DCN) to align the frames. However, the existing MFSR suffers from misalignments between the reference and source frames due to the limitations of DCN, such as small receptive fields and the predefined number of kernels. From these problems, existing MFSR approaches struggle to represent high-frequency information. To this end, we propose Deep Burst Multi-scale SR using Fourier Space with Optical Flow (BurstM). The proposed method estimates the optical flow offset for accurate alignment and predicts the continuous Fourier coefficient of each frame for representing high-frequency textures. In addition, we have enhanced the network flexibility by supporting various super-resolution (SR) scale factors with the unimodel. We demonstrate that our method has the highest performance and flexibility than the existing MFSR methods. Our source code is available at https://github.com/Egkang-Luis/burstm
Authors: Nikola Ljube\v{s}i\'c, Peter Rupnik, Danijel Kor\v{z}inek
Abstract: Recent significant improvements in speech and language technologies come both from self-supervised approaches over raw language data as well as various types of explicit supervision. To ensure high-quality processing of spoken data, the most useful type of explicit supervision is still the alignment between the speech signal and its corresponding text transcript, which is a data type that is not available for many languages. In this paper, we present our approach to building large and open speech-and-text-aligned datasets of less-resourced languages based on transcripts of parliamentary proceedings and their recordings. Our starting point are the ParlaMint comparable corpora of transcripts of parliamentary proceedings of 26 national European parliaments. In the pilot run on expanding the ParlaMint corpora with aligned publicly available recordings, we focus on three Slavic languages, namely Croatian, Polish, and Serbian. The main challenge of our approach is the lack of any global alignment between the ParlaMint texts and the available recordings, as well as the sometimes varying data order in each of the modalities, which requires a novel approach in aligning long sequences of text and audio in a large search space. The results of this pilot run are three high-quality datasets that span more than 5,000 hours of speech and accompanying text transcripts. Although these datasets already make a huge difference in the availability of spoken and textual data for the three languages, we want to emphasize the potential of the presented approach in building similar datasets for many more languages.
Authors: Ambrish Rawat, Stefan Schoepf, Giulio Zizzo, Giandomenico Cornacchia, Muhammad Zaid Hameed, Kieran Fraser, Erik Miehling, Beat Buesser, Elizabeth M. Daly, Mark Purcell, Prasanna Sattigeri, Pin-Yu Chen, Kush R. Varshney
Abstract: As generative AI, particularly large language models (LLMs), become increasingly integrated into production applications, new attack surfaces and vulnerabilities emerge and put a focus on adversarial threats in natural language and multi-modal systems. Red-teaming has gained importance in proactively identifying weaknesses in these systems, while blue-teaming works to protect against such adversarial attacks. Despite growing academic interest in adversarial risks for generative AI, there is limited guidance tailored for practitioners to assess and mitigate these challenges in real-world environments. To address this, our contributions include: (1) a practical examination of red- and blue-teaming strategies for securing generative AI, (2) identification of key challenges and open questions in defense development and evaluation, and (3) the Attack Atlas, an intuitive framework that brings a practical approach to analyzing single-turn input attacks, placing it at the forefront for practitioners. This work aims to bridge the gap between academic insights and practical security measures for the protection of generative AI systems.
Authors: Maximilian Weiherer, Bernhard Egger
Abstract: We propose to use the family of Mat\'ern kernels for tunable implicit surface reconstruction, building upon the recent success of kernel methods for 3D reconstruction of oriented point clouds. As we show, both, from a theoretical and practical perspective, Mat\'ern kernels have some appealing properties which make them particularly well suited for surface reconstruction -- outperforming state-of-the-art methods based on the arc-cosine kernel while being significantly easier to implement, faster to compute, and scaleable. Being stationary, we demonstrate that the Mat\'ern kernels' spectrum can be tuned in the same fashion as Fourier feature mappings help coordinate-based MLPs to overcome spectral bias. Moreover, we theoretically analyze Mat\'ern kernel's connection to SIREN networks as well as its relation to previously employed arc-cosine kernels. Finally, based on recently introduced Neural Kernel Fields, we present data-dependent Mat\'ern kernels and conclude that especially the Laplace kernel (being part of the Mat\'ern family) is extremely competitive, performing almost on par with state-of-the-art methods in the noise-free case while having a more than five times shorter training time.
Authors: Abdul-Lateef Haji-Ali, Marcelo Pereyra, Luke Shaw, Konstantinos Zygalakis
Abstract: Generative diffusion models have recently emerged as a powerful strategy to perform stochastic sampling in Bayesian inverse problems, delivering remarkably accurate solutions for a wide range of challenging applications. However, diffusion models often require a large number of neural function evaluations per sample in order to deliver accurate posterior samples. As a result, using diffusion models as stochastic samplers for Monte Carlo integration in Bayesian computation can be highly computationally expensive. This cost is especially high in large-scale inverse problems such as computational imaging, which rely on large neural networks that are expensive to evaluate. With Bayesian imaging problems in mind, this paper presents a Multilevel Monte Carlo strategy that significantly reduces the cost of Bayesian computation with diffusion models. This is achieved by exploiting cost-accuracy trade-offs inherent to diffusion models to carefully couple models of different levels of accuracy in a manner that significantly reduces the overall cost of the calculation, without reducing the final accuracy. The effectiveness of the proposed Multilevel Monte Carlo approach is demonstrated with three canonical computational imaging problems, where we observe a $4\times$-to-$8\times$ reduction in computational cost compared to conventional Monte Carlo averaging.
Authors: Kin Man Lee, Sean Ye, Qingyu Xiao, Zixuan Wu, Zulfiqar Zaidi, David B. D'Ambrosio, Pannag R. Sanketi, Matthew Gombolay
Abstract: Advances in robot learning have enabled robots to generate skills for a variety of tasks. Yet, robot learning is typically sample inefficient, struggles to learn from data sources exhibiting varied behaviors, and does not naturally incorporate constraints. These properties are critical for fast, agile tasks such as playing table tennis. Modern techniques for learning from demonstration improve sample efficiency and scale to diverse data, but are rarely evaluated on agile tasks. In the case of reinforcement learning, achieving good performance requires training on high-fidelity simulators. To overcome these limitations, we develop a novel diffusion modeling approach that is offline, constraint-guided, and expressive of diverse agile behaviors. The key to our approach is a kinematic constraint gradient guidance (KCGG) technique that computes gradients through both the forward kinematics of the robot arm and the diffusion model to direct the sampling process. KCGG minimizes the cost of violating constraints while simultaneously keeping the sampled trajectory in-distribution of the training data. We demonstrate the effectiveness of our approach for time-critical robotic tasks by evaluating KCGG in two challenging domains: simulated air hockey and real table tennis. In simulated air hockey, we achieved a 25.4% increase in block rate, while in table tennis, we saw a 17.3% increase in success rate compared to imitation learning baselines.
Authors: Johan Hallberg Szabadv\'ary
Abstract: Conformal prediction is a widely-used framework for distribution-free uncertainty quantification, which generates valid prediction sets at a user-defined significance level. However, this framework relies on the assumption that the data-generating distribution is exchangeable, a condition that is frequently violated in time-series and other structured data. In such cases, the validity guarantees of conformal prediction break down. Adaptive conformal inference (ACI) has been proposed as a solution for non-exchangeable data by dynamically adjusting the significance level to retain at least finite sample guarantees on the marginal coverage error rate. This paper demonstrates that, despite its name, ACI does not strictly require the use of conformal predictors. Instead, it can operate effectively with the more general concept of a confidence predictor, which is often computationally simpler. The key requirement is that larger significance levels correspond to smaller prediction sets, a property known as nested prediction sets. Through experiments on synthetic and real-world data, we investigate whether ACI with conformal predictors offers advantages over confidence predictors. Our results indicate that confidence predictors can perform just as well, and sometimes better than conformal predictors in some cases, although further empirical studies are needed to determine when one approach may be preferable.
Authors: R. Stuart Geiger, Flynn O'Sullivan, Elsie Wang, Jonathan Lo
Abstract: We conducted controlled experimental bias audits for four versions of ChatGPT, which we asked to recommend an opening offer in salary negotiations for a new hire. We submitted 98,800 prompts to each version, systematically varying the employee's gender, university, and major, and tested prompts in voice of each side of the negotiation: the employee versus employer. We find ChatGPT as a multi-model platform is not robust and consistent enough to be trusted for such a task. We observed statistically significant salary offers when varying gender for all four models, although with smaller gaps than for other attributes tested. The largest gaps were different model versions and between the employee- vs employer-voiced prompts. We also observed substantial gaps when varying university and major, but many of the biases were not consistent across model versions. We tested for fictional and fraudulent universities and found wildly inconsistent results across cases and model versions. We make broader contributions to the AI/ML fairness literature. Our scenario and our experimental design differ from mainstream AI/ML auditing efforts in key ways. Bias audits typically test discrimination for protected classes like gender, which we contrast with testing non-protected classes of university and major. Asking for negotiation advice includes how aggressive one ought to be in a negotiation relative to known empirical salary distributions and scales, which is a deeply contextual and personalized task that has no objective ground truth to validate. These results raise concerns for the specific model versions we tested and ChatGPT as a multi-model platform in continuous development. Our epistemology does not permit us to definitively certify these models as either generally biased or unbiased on the attributes we test, but our study raises matters of concern for stakeholders to further investigate.
Authors: Abdulaziz Samra, Evgeney Frolov, Alexey Vasilev, Alexander Grigorievskiy, Anton Vakhrushev
Abstract: Data sparsity has been one of the long-standing problems for recommender systems. One of the solutions to mitigate this issue is to exploit knowledge available in other source domains. However, many cross-domain recommender systems introduce a complex architecture that makes them less scalable in practice. On the other hand, matrix factorization methods are still considered to be strong baselines for single-domain recommendations. In this paper, we introduce the CDIMF, a model that extends the standard implicit matrix factorization with ALS to cross-domain scenarios. We apply the Alternating Direction Method of Multipliers to learn shared latent factors for overlapped users while factorizing the interaction matrix. In a dual-domain setting, experiments on industrial datasets demonstrate a competing performance of CDIMF for both cold-start and warm-start. The proposed model can outperform most other recent cross-domain and single-domain models. We also provide the code to reproduce experiments on GitHub.
Authors: Alex Nguyen, David J. Schwab, Vudtiwat Ngampruetikorn
Abstract: Machine learning models are often brittle under distribution shift, i.e., when data distributions at test time differ from those during training. Understanding this failure mode is central to identifying and mitigating safety risks of mass adoption of machine learning. Here we analyze ridge regression under concept shift -- a form of distribution shift in which the input-label relationship changes at test time. We derive an exact expression for prediction risk in the high-dimensional limit. Our results reveal nontrivial effects of concept shift on generalization performance, depending on the properties of robust and nonrobust features of the input. We show that test performance can exhibit a nonmonotonic data dependence, even when double descent is absent. Finally, our experiments on MNIST and FashionMNIST suggest that this intriguing behavior is present also in classification problems.
Authors: Bandhav Veluri, Benjamin N Peloquin, Bokai Yu, Hongyu Gong, Shyamnath Gollakota
Abstract: Despite broad interest in modeling spoken dialogue agents, most approaches are inherently "half-duplex" -- restricted to turn-based interaction with responses requiring explicit prompting by the user or implicit tracking of interruption or silence events. Human dialogue, by contrast, is "full-duplex" allowing for rich synchronicity in the form of quick and dynamic turn-taking, overlapping speech, and backchanneling. Technically, the challenge of achieving full-duplex dialogue with LLMs lies in modeling synchrony as pre-trained LLMs do not have a sense of "time". To bridge this gap, we propose Synchronous LLMs for full-duplex spoken dialogue modeling. We design a novel mechanism to integrate time information into Llama3-8b so that they run synchronously with the real-world clock. We also introduce a training recipe that uses 212k hours of synthetic spoken dialogue data generated from text dialogue data to create a model that generates meaningful and natural spoken dialogue, with just 2k hours of real-world spoken dialogue data. Synchronous LLMs outperform state-of-the-art in dialogue meaningfulness while maintaining naturalness. Finally, we demonstrate the model's ability to participate in full-duplex dialogue by simulating interaction between two agents trained on different datasets, while considering Internet-scale latencies of up to 240 ms. Webpage: https://syncllm.cs.washington.edu/.
Authors: Yun-Jie Ho, Zih-Yun Chiu, Yuheng Zhi, Michael C. Yip
Abstract: Surgical automation holds immense potential to improve the outcome and accessibility of surgery. Recent studies use reinforcement learning to learn policies that automate different surgical tasks. However, these policies are developed independently and are limited in their reusability when the task changes, making it more time-consuming when robots learn to solve multiple tasks. Inspired by how human surgeons build their expertise, we train surgical automation policies through Surgical Incremental Reinforcement Learning (SurgIRL). SurgIRL aims to (1) acquire new skills by referring to external policies (knowledge) and (2) accumulate and reuse these skills to solve multiple unseen tasks incrementally (incremental learning). Our SurgIRL framework includes three major components. We first define an expandable knowledge set containing heterogeneous policies that can be helpful for surgical tasks. Then, we propose Knowledge Inclusive Attention Network with mAximum Coverage Exploration (KIAN-ACE), which improves learning efficiency by maximizing the coverage of the knowledge set during the exploration process. Finally, we develop incremental learning pipelines based on KIAN-ACE to accumulate and reuse learned knowledge and solve multiple surgical tasks sequentially. Our simulation experiments show that KIAN-ACE efficiently learns to automate ten surgical tasks separately or incrementally. We also evaluate our learned policies on the da Vinci Research Kit (dVRK) and demonstrate successful sim-to-real transfers.
Authors: Tonmoy Roy, Md Robiul Islam, Asif Ahmed Miazi, Anika Antara, Al Amin, Sunjim Hossain
Abstract: Over the years, the number of users of social media has increased drastically. People frequently share their thoughts through social platforms, and this leads to an increase in hate content. In this virtual community, individuals share their views, express their feelings, and post photos, videos, blogs, and more. Social networking sites like Facebook and Twitter provide platforms to share vast amounts of content with a single click. However, these platforms do not impose restrictions on the uploaded content, which may include abusive language and explicit images unsuitable for social media. To resolve this issue, a new idea must be implemented to divide the inappropriate content. Numerous studies have been done to automate the process. In this paper, we propose a new Bi-GRU-CNN model to classify whether the text is offensive or not. The combination of the Bi-GRU and CNN models outperforms the existing model
Authors: Taowen Wang, Yiyang Liu, James Chenhao Liang, junhan zhao, Yiming Cui, Yuning Mao, Shaoliang Nie, Jiahao Liu, Fuli Feng, Zenglin Xu, Cheng Han, Lifu Huang, Qifan Wang, Dongfang Liu
Abstract: Multimodal Large Language Models (MLLMs) demonstrate remarkable performance across a wide range of domains, with increasing emphasis on enhancing their zero-shot generalization capabilities for unseen tasks across various modalities. Instruction tuning has emerged as an effective strategy for achieving zero-shot generalization by finetuning pretrained models on diverse multimodal tasks. As the scale of MLLMs continues to grow, parameter-efficient finetuning becomes increasingly critical. However, most existing parameter-efficient approaches focus only on single modalities and often overlook the multimodal characteristics during finetuning. In this work, we introduce a novel Multimodal Prompt Tuning (MMPT) approach for efficient instruction tuning of MLLMs. MMPT effectively integrates visual and textual prompts into the vision encoder and language processor respectively during finetuning, facilitating the extraction and alignment of features across modalities. Empirical results on various multimodal evaluation datasets demonstrate the superior performance of our approach compared to several state-of-the-art baselines. A comprehensive set of ablation studies validates the effectiveness of our prompt design and the efficiency of our approach.
Authors: Suman Itani, Yibo Zhang, Jiadong Zang
Abstract: The discovery of novel magnetic materials with greater operating temperature ranges and optimized performance is essential for advanced applications. Current data-driven approaches are challenging and limited due to the lack of accurate, comprehensive, and feature-rich databases. This study aims to address this challenge by introducing a new approach that uses Large Language Models (LLMs) to create a comprehensive, experiment-based, magnetic materials database named the Northeast Materials Database (NEMAD), which consists of 26,706 magnetic materials (www.nemad.org). The database incorporates chemical composition, magnetic phase transition temperatures, structural details, and magnetic properties. Enabled by NEMAD, machine learning models were developed to classify materials and predict transition temperatures. Our classification model achieved an accuracy of 90% in categorizing materials as ferromagnetic (FM), antiferromagnetic (AFM), and non-magnetic (NM). The regression models predict Curie (N\'eel) temperature with a coefficient of determination (R2) of 0.86 (0.85) and a mean absolute error (MAE) of 62K (32K). These models identified 62 (19) FM (AFM) candidates with a predicted Curie (N\'eel) temperature above 500K (100K) from the Materials Project. This work shows the feasibility of combining LLMs for automated data extraction and machine learning models in accelerating the discovery of magnetic materials.
Authors: Yuchen Fang, Sen Na, Michael W. Mahoney, Mladen Kolar
Abstract: In this work, we consider solving optimization problems with a stochastic objective and deterministic equality constraints. We propose a Trust-Region Sequential Quadratic Programming method to find both first- and second-order stationary points. Our method utilizes a random model to represent the objective function, which is constructed from stochastic observations of the objective and is designed to satisfy proper adaptive accuracy conditions with a high but fixed probability. To converge to first-order stationary points, our method computes a gradient step in each iteration defined by minimizing a quadratic approximation of the objective subject to a (relaxed) linear approximation of the problem constraints and a trust-region constraint. To converge to second-order stationary points, our method additionally computes an eigen step to explore the negative curvature of the reduced Hessian matrix, as well as a second-order correction step to address the potential Maratos effect, which arises due to the nonlinearity of the problem constraints. Such an effect may impede the method from moving away from saddle points. Both gradient and eigen step computations leverage a novel parameter-free decomposition of the step and the trust-region radius, accounting for the proportions among the feasibility residual, optimality residual, and negative curvature. We establish global almost sure first- and second-order convergence guarantees for our method, and present computational results on CUTEst problems, regression problems, and saddle-point problems to demonstrate its superiority over existing line-search-based stochastic methods.
Authors: Sung Yun Lee, Do Hyung Cho, Chulho Jung, Daeho Sung, Daewoong Nam, Sangsoo Kim, Changyong Song
Abstract: Machine learning is attracting surging interest across nearly all scientific areas by enabling the analysis of large datasets and the extraction of scientific information from incomplete data. Data-driven science is rapidly growing, especially in X-ray methodologies, where advanced light sources and detection technologies accumulate vast amounts of data that exceed meticulous human inspection capabilities. Despite the increasing demands, the full application of machine learning has been hindered by the need for data-specific optimizations. In this study, we introduce a new deep-learning-based phase retrieval method for imperfect diffraction data. This method provides robust phase retrieval for simulated data and performs well on weak-signal single-pulse diffraction data from X-ray free-electron lasers. Moreover, the method significantly reduces data processing time, facilitating real-time image reconstructions that are crucial for high-repetition-rate data acquisition. Thus, this approach offers a reliable solution to the phase problem and is expected to be widely adopted across various research areas.
Authors: Zhenyan Lu, Xiang Li, Dongqi Cai, Rongjie Yi, Fangming Liu, Xiwen Zhang, Nicholas D. Lane, Mengwei Xu
Abstract: Small language models (SLMs), despite their widespread adoption in modern smart devices, have received significantly less academic attention compared to their large language model (LLM) counterparts, which are predominantly deployed in data centers and cloud environments. While researchers continue to improve the capabilities of LLMs in the pursuit of artificial general intelligence, SLM research aims to make machine intelligence more accessible, affordable, and efficient for everyday tasks. Focusing on transformer-based, decoder-only language models with 100M-5B parameters, we survey 59 state-of-the-art open-source SLMs, analyzing their technical innovations across three axes: architectures, training datasets, and training algorithms. In addition, we evaluate their capabilities in various domains, including commonsense reasoning, in-context learning, mathematics, and coding. To gain further insight into their on-device runtime costs, we benchmark their inference latency and memory footprints. Through in-depth analysis of our benchmarking data, we offer valuable insights to advance research in this field.
Authors: Razin Farhan Hussain, Mohsen Amini Salehi
Abstract: Deep neural network (DNN) models are effective solutions for industry 4.0 applications (\eg oil spill detection, fire detection, anomaly detection). However, training a DNN network model needs a considerable amount of data collected from various sources and transferred to the central cloud server that can be expensive and sensitive to privacy. For instance, in the remote offshore oil field where network connectivity is vulnerable, a federated fog environment can be a potential computing platform. Hence it is feasible to perform computation within the federation. On the contrary, performing a DNN model training using fog systems poses a security issue that the federated learning (FL) technique can resolve. In this case, the new challenge is the class imbalance problem that can be inherited in local data sets and can degrade the performance of the global model. Therefore, FL training needs to be performed considering the class imbalance problem locally. In addition, an efficient technique to select the relevant worker model needs to be adopted at the global level to increase the robustness of the global model. Accordingly, we utilize one of the suitable loss functions addressing the class imbalance in workers at the local level. In addition, we employ a dynamic threshold mechanism with user-defined worker's weight to efficiently select workers for aggregation that improve the global model's robustness. Finally, we perform an extensive empirical evaluation to explore the benefits of our solution and find up to 3-5% performance improvement than baseline federated learning methods.
Authors: Min Hun Lee, Renee Bao Xuan Ng, Silvana Xinyi Choo, Shamala Thilarajah
Abstract: A growing research explores the usage of AI explanations on user's decision phases for human-AI collaborative decision-making. However, previous studies found the issues of overreliance on `wrong' AI outputs. In this paper, we propose interactive example-based explanations to improve health professionals' onboarding with AI for their better reliance on AI during AI-assisted decision-making. We implemented an AI-based decision support system that utilizes a neural network to assess the quality of post-stroke survivors' exercises and interactive example-based explanations that systematically surface the nearest neighborhoods of a test/task sample from the training set of the AI model to assist users' onboarding with the AI model. To investigate the effect of interactive example-based explanations, we conducted a study with domain experts, health professionals to evaluate their performance and reliance on AI. Our interactive example-based explanations during onboarding assisted health professionals in having a better reliance on AI and making a higher ratio of making `right' decisions and a lower ratio of `wrong' decisions than providing only feature-based explanations during the decision-support phase. Our study discusses new challenges of assisting user's onboarding with AI for human-AI collaborative decision-making.
Authors: Matteo Zecchin, Osvaldo Simeone
Abstract: We introduce adaptive learn-then-test (aLTT), an efficient hyperparameter selection procedure that provides finite-sample statistical guarantees on the population risk of AI models. Unlike the existing learn-then-test (LTT) technique, which relies on conventional p-value-based multiple hypothesis testing (MHT), aLTT implements sequential data-dependent MHT with early termination by leveraging e-processes. As a result, aLTT can reduce the number of testing rounds, making it particularly well-suited for scenarios in which testing is costly or presents safety risks. Apart from maintaining statistical validity, in applications such as online policy selection for offline reinforcement learning and hyperparameter tuning for engineering systems, aLTT is shown to achieve the same performance as LTT while requiring only a fraction of the testing rounds.
Authors: Jiayu Chen, Chao Yu, Guosheng Li, Wenhao Tang, Xinyi Yang, Botian Xu, Huazhong Yang, Yu Wang
Abstract: Multi-UAV pursuit-evasion, where pursuers aim to capture evaders, poses a key challenge for UAV swarm intelligence. Multi-agent reinforcement learning (MARL) has demonstrated potential in modeling cooperative behaviors, but most RL-based approaches remain constrained to simplified simulations with limited dynamics or fixed scenarios. Previous attempts to deploy RL policy to real-world pursuit-evasion are largely restricted to two-dimensional scenarios, such as ground vehicles or UAVs at fixed altitudes. In this paper, we address multi-UAV pursuit-evasion by considering UAV dynamics and physical constraints. We introduce an evader prediction-enhanced network to tackle partial observability in cooperative strategy learning. Additionally, we propose an adaptive environment generator within MARL training, enabling higher exploration efficiency and better policy generalization across diverse scenarios. Simulations show our method significantly outperforms all baselines in challenging scenarios, generalizing to unseen scenarios with a 100\% capture rate. Finally, we derive a feasible policy via a two-stage reward refinement and deploy the policy on real quadrotors in a zero-shot manner. To our knowledge, this is the first work to derive and deploy an RL-based policy using collective thrust and body rates control commands for multi-UAV pursuit-evasion in unknown environments. The open-source code and videos are available at https://sites.google.com/view/pursuit-evasion-rl.
Authors: Wei Huang, Yinggui Wang, Cen Chen
Abstract: By inducing privacy attacks on NLP models, attackers can obtain sensitive information such as training data and model parameters, etc. Although researchers have studied, in-depth, several kinds of attacks in NLP models, they are non-systematic analyses. It lacks a comprehensive understanding of the impact caused by the attacks. For example, we must consider which scenarios can apply to which attacks, what the common factors are that affect the performance of different attacks, the nature of the relationships between different attacks, and the influence of various datasets and models on the effectiveness of the attacks, etc. Therefore, we need a benchmark to holistically assess the privacy risks faced by NLP models. In this paper, we present a privacy attack and defense evaluation benchmark in the field of NLP, which includes the conventional/small models and large language models (LLMs). This benchmark supports a variety of models, datasets, and protocols, along with standardized modules for comprehensive evaluation of attacks and defense strategies. Based on the above framework, we present a study on the association between auxiliary data from different domains and the strength of privacy attacks. And we provide an improved attack method in this scenario with the help of Knowledge Distillation (KD). Furthermore, we propose a chained framework for privacy attacks. Allowing a practitioner to chain multiple attacks to achieve a higher-level attack objective. Based on this, we provide some defense and enhanced attack strategies. The code for reproducing the results can be found at https://github.com/user2311717757/nlp_doctor.
Authors: Yael Segal-Feldman, Aviv Shamsian, Aviv Navon, Gill Hetz, Joseph Keshet
Abstract: Large transformer-based models have significant potential for speech transcription and translation. Their self-attention mechanisms and parallel processing enable them to capture complex patterns and dependencies in audio sequences. However, this potential comes with challenges, as these large and computationally intensive models lead to slow inference speeds. Various optimization strategies have been proposed to improve performance, including efficient hardware utilization and algorithmic enhancements. In this paper, we introduce Whisper-Medusa, a novel approach designed to enhance processing speed with minimal impact on Word Error Rate (WER). The proposed model extends the OpenAI's Whisper architecture by predicting multiple tokens per iteration, resulting in a 50% reduction in latency. We showcase the effectiveness of Whisper-Medusa across different learning setups and datasets.
Authors: Alexis Plaquet (IRIT-SAMoVA), Herv\'e Bredin (IRIT-SAMoVA, CNRS)
Abstract: End-to-end neural diarization models have usually relied on a multilabel-classification formulation of the speaker diarization problem. Recently, we proposed a powerset multiclass formulation that has beaten the state-of-the-art on multiple datasets. In this paper, we propose to study the calibration of a powerset speaker diarization model, and explore some of its uses. We study the calibration in-domain, as well as out-of-domain, and explore the data in low-confidence regions. The reliability of model confidence is then tested in practice: we use the confidence of the pretrained model to selectively create training and validation subsets out of unannotated data, and compare this to random selection. We find that top-label confidence can be used to reliably predict high-error regions. Moreover, training on low-confidence regions provides a better calibrated model, and validating on low-confidence regions can be more annotation-efficient than random regions.
Authors: Angelo Didonna, Dayron Ramos Lopez, Giuseppe Iaselli, Nicola Amoroso, Nicola Ferrara, Gabriella Maria Incoronata Pugliese
Abstract: Boron Neutron Capture Therapy (BNCT) is an innovative binary form of radiation therapy with high selectivity towards cancer tissue based on the neutron capture reaction 10B(n,$\alpha$)7Li, consisting in the exposition of patients to neutron beams after administration of a boron compound with preferential accumulation in cancer cells. The high linear energy transfer products of the ensuing reaction deposit their energy at cell level, sparing normal tissue. Although progress in accelerator-based BNCT has led to renewed interest in this cancer treatment modality, in vivo dose monitoring during treatment still remains not feasible and several approaches are under investigation. While Compton imaging presents various advantages over other imaging methods, it typically requires long reconstruction times, comparable with BNCT treatment duration. This study aims to develop deep neural network models to estimate the dose distribution by using a simulated dataset of BNCT Compton camera images. The models pursue the avoidance of the iteration time associated with the maximum-likelihood expectation-maximization algorithm (MLEM), enabling a prompt dose reconstruction during the treatment. The U-Net architecture and two variants based on the deep convolutional framelets framework have been used for noise and artifacts reduction in few-iterations reconstructed images, leading to promising results in terms of reconstruction accuracy and processing time.
Authors: Samuel Arcadinho, David Aparicio, Mariana Almeida
Abstract: Tool-augmented LLMs are a promising approach to create AI agents that can have realistic conversations, follow procedures, and call appropriate functions. However, evaluating them is challenging due to the diversity of possible conversations, and existing datasets focus only on single interactions and function-calling. We present a test generation pipeline to evaluate LLMs as conversational AI agents. Our framework uses LLMs to generate diverse tests grounded on user-defined procedures. For that, we use intermediate graphs to limit the LLM test generator's tendency to hallucinate content that is not grounded on input procedures, and enforces high coverage of the possible conversations. Additionally, we put forward ALMITA, a manually curated dataset for evaluating AI agents in customer support, and use it to evaluate existing LLMs. Our results show that while tool-augmented LLMs perform well in single interactions, they often struggle to handle complete conversations. While our focus is on customer support, our method is general and capable of AI agents for different domains.
Authors: Michele Caselle, Elia Cellini, Alessandro Nada
Abstract: Flow-based architectures have recently proved to be an efficient tool for numerical simulations of Effective String Theories regularized on the lattice that otherwise cannot be efficiently sampled by standard Monte Carlo methods. In this work we use Stochastic Normalizing Flows, a state-of-the-art deep-learning architecture based on non-equilibrium Monte Carlo simulations, to study different effective string models. After testing the reliability of this approach through a comparison with exact results for the Nambu-Got\={o} model, we discuss results on observables that are challenging to study analytically, such as the width of the string and the shape of the flux density. Furthermore, we perform a novel numerical study of Effective String Theories with terms beyond the Nambu-Got\={o} action, including a broader discussion on their significance for lattice gauge theories. These results establish the reliability and feasibility of flow-based samplers for Effective String Theories and pave the way for future applications on more complex models.
Authors: Fang Wang (Florence Wong), Marko Gacesa
Abstract: This study extends the examination of the Efficient-Market Hypothesis in Bitcoin market during a five year fluctuation period, from September 1 2017 to September 1 2022, by analyzing 28,739,514 qualified tweets containing the targeted topic "Bitcoin". Unlike previous studies, we extracted fundamental keywords as an informative proxy for carrying out the study of the EMH in the Bitcoin market rather than focusing on sentiment analysis, information volume, or price data. We tested market efficiency in hourly, 4-hourly, and daily time periods to understand the speed and accuracy of market reactions towards the information within different thresholds. A sequence of machine learning methods and textual analyses were used, including measurements of distances of semantic vector spaces of information, keywords extraction and encoding model, and Light Gradient Boosting Machine (LGBM) classifiers. Our results suggest that 78.06% (83.08%), 84.63% (87.77%), and 94.03% (94.60%) of hourly, 4-hourly, and daily bullish (bearish) market movements can be attributed to public information within organic tweets.
Authors: Juan Ossa, Eren Do\u{g}an, Alex Birch, F. Johnson
Abstract: In this technical report, we document the changes we made to SDXL in the process of training NovelAI Diffusion V3, our state of the art anime image generation model.
Authors: Santiago Sanchez-Escalonilla, Samuele Zoboli, Bayu Jayawardhana
Abstract: In this paper, we restructure the Neural Interconnection and Damping Assignment - Passivity Based Control (Neural IDA-PBC) design methodology, and we formally analyze its closed-loop properties. Neural IDA-PBC redefines the IDA-PBC design approach as an optimization problem by building on the framework of Physics Informed Neural Networks (PINNs). However, the closed-loop stability and robustness properties under Neural IDA-PBC remain unexplored. To address the issue, we study the behavior of classical IDA-PBC under approximations. Our theoretical analysis allows deriving conditions for practical and asymptotic stability of the desired equilibrium point. Moreover, it extends the Neural IDA-PBC applicability to port-Hamiltonian systems where the matching conditions cannot be solved exactly. Our renewed optimization-based design introduces three significant aspects: i) it involves a novel optimization objective including stability and robustness constraints issued from our theoretical analysis; ii) it employs separate Neural Networks (NNs), which can be structured to reduce the search space to relevant functions; iii) it does not require knowledge about the port-Hamiltonian formulation of the system's model. Our methodology is validated with simulations on three standard benchmarks: a double pendulum, a nonlinear mass-spring-damper and a cartpole. Notably, classical IDA-PBC designs cannot be analytically derived for the latter.
Authors: Tifanny Portela, Andrei Cramariuc, Mayank Mittal, Marco Hutter
Abstract: Combining manipulation with the mobility of legged robots is essential for a wide range of robotic applications. However, integrating an arm with a mobile base significantly increases the system's complexity, making precise end-effector control challenging. Existing model-based approaches are often constrained by their modeling assumptions, leading to limited robustness. Meanwhile, recent Reinforcement Learning (RL) implementations restrict the arm's workspace to be in front of the robot or track only the position to obtain decent tracking accuracy. In this work, we address these limitations by introducing a whole-body RL formulation for end-effector pose tracking in a large workspace on rough, unstructured terrains. Our proposed method involves a terrain-aware sampling strategy for the robot's initial configuration and end-effector pose commands, as well as a game-based curriculum to extend the robot's operating range. We validate our approach on the ANYmal quadrupedal robot with a six DoF robotic arm. Through our experiments, we show that the learned controller achieves precise command tracking over a large workspace and adapts across varying terrains such as stairs and slopes. On deployment, it achieves a pose-tracking error of 2.64 cm and 3.64 degrees, outperforming existing competitive baselines.
Authors: Nilotpal Kakati, Etienne Dreyer, Eilam Gross
Abstract: Accurately reconstructing particles from detector data is a critical challenge in experimental particle physics, where the spatial resolution of calorimeters has a crucial impact. This study explores the integration of super-resolution techniques into an LHC-like reconstruction pipeline to effectively enhance the granularity of calorimeter data and suppress noise. We find that this software preprocessing step can significantly improve reconstruction quality without physical changes to detectors. To demonstrate the impact of our approach, we propose a novel particle flow model that offers enhanced particle reconstruction quality and interpretability. These advancements underline the potential of super-resolution to impact both current and future particle physics experiments.
Authors: Getachew K Befekadu
Abstract: In this technical note, we consider a collaborative learning framework with principal-agent setting, in which the principal at each time-step determines a set of appropriate aggregation coefficients based on how the current parameter estimates from a group of $K$ agents effectively performed in connection with a separate test dataset, which is not part of the agents' training model datasets. Whereas, the agents, who act together as a team, then update their parameter estimates using a discrete-time version of Langevin dynamics with mean-field-like interaction term, but guided by their respective different training model datasets. Here, we propose a decision-theoretic framework that explicitly describes how the principal progressively determines a set of nonnegative and sum to one aggregation coefficients used by the agents in their mean-field-like interaction term, that eventually leading them to reach a consensus optimal parameter estimate. Interestingly, due to the inherent feedbacks and cooperative behavior among the agents, the proposed framework offers some advantages in terms of stability and generalization, despite that both the principal and the agents do not necessarily need to have any knowledge of the sample distributions or the quality of each others' datasets.
Authors: Lorenzo Borella, Alberto Coppi, Jacopo Pazzini, Andrea Stanco, Marco Trenti, Andrea Triossi, Marco Zanetti
Abstract: Tensor Networks (TNs) are a computational paradigm used for representing quantum many-body systems. Recent works have shown how TNs can also be applied to perform Machine Learning (ML) tasks, yielding comparable results to standard supervised learning techniques.In this work, we study the use of Tree Tensor Networks (TTNs) in high-frequency real-time applications by exploiting the low-latency hardware of the Field-Programmable Gate Array (FPGA) technology. We present different implementations of TTN classifiers, capable of performing inference on classical ML datasets as well as on complex physics data. A preparatory analysis of bond dimensions and weight quantization is realized in the training phase, together with entanglement entropy and correlation measurements, that help setting the choice of the TTN architecture. The generated TTNs are then deployed on a hardware accelerator; using an FPGA integrated into a server, the inference of the TTN is completely offloaded. Eventually, a classifier for High Energy Physics (HEP) applications is implemented and executed fully pipelined with sub-microsecond latency.
Authors: Ivan DeAndres-Tame, Muhammad Faisal, Ruben Tolosana, Rouqaiah Al-Refai, Ruben Vera-Rodriguez, Philipp Terh\"orst
Abstract: Face Recognition (FR) has advanced significantly with the development of deep learning, achieving high accuracy in several applications. However, the lack of interpretability of these systems raises concerns about their accountability, fairness, and reliability. In the present study, we propose an interactive framework to enhance the explainability of FR models by combining model-agnostic Explainable Artificial Intelligence (XAI) and Natural Language Processing (NLP) techniques. The proposed framework is able to accurately answer various questions of the user through an interactive chatbot. In particular, the explanations generated by our proposed method are in the form of natural language text and visual representations, which for example can describe how different facial regions contribute to the similarity measure between two faces. This is achieved through the automatic analysis of the output's saliency heatmaps of the face images and a BERT question-answering model, providing users with an interface that facilitates a comprehensive understanding of the FR decisions. The proposed approach is interactive, allowing the users to ask questions to get more precise information based on the user's background knowledge. More importantly, in contrast to previous studies, our solution does not decrease the face recognition performance. We demonstrate the effectiveness of the method through different experiments, highlighting its potential to make FR systems more interpretable and user-friendly, especially in sensitive applications where decision-making transparency is crucial.
Authors: Aditya Ashvin, Rimita Lahiri, Aditya Kommineni, Somer Bishop, Catherine Lord, Sudarsana Reddy Kadiri, Shrikanth Narayanan
Abstract: The ability to reliably transcribe child-adult conversations in a clinical setting is valuable for diagnosis and understanding of numerous developmental disorders such as Autism Spectrum Disorder. Recent advances in deep learning architectures and availability of large scale transcribed data has led to development of speech foundation models that have shown dramatic improvements in ASR performance. However, the ability of these models to translate well to conversational child-adult interactions is under studied. In this work, we provide a comprehensive evaluation of ASR performance on a dataset containing child-adult interactions from autism diagnostic sessions, using Whisper, Wav2Vec2, HuBERT, and WavLM. We find that speech foundation models show a noticeable performance drop (15-20% absolute WER) for child speech compared to adult speech in the conversational setting. Then, we employ LoRA on the best performing zero shot model (whisper-large) to probe the effectiveness of fine-tuning in a low resource setting, resulting in ~8% absolute WER improvement for child speech and ~13% absolute WER improvement for adult speech.
Authors: Mark Hamilton, Simon Stent, Vasha DuTell, Anne Harrington, Jennifer Corbett, Ruth Rosenholtz, William T. Freeman
Abstract: The human visual system is well-tuned to detect faces of all shapes and sizes. While this brings obvious survival advantages, such as a better chance of spotting unknown predators in the bush, it also leads to spurious face detections. ``Face pareidolia'' describes the perception of face-like structure among otherwise random stimuli: seeing faces in coffee stains or clouds in the sky. In this paper, we study face pareidolia from a computer vision perspective. We present an image dataset of ``Faces in Things'', consisting of five thousand web images with human-annotated pareidolic faces. Using this dataset, we examine the extent to which a state-of-the-art human face detector exhibits pareidolia, and find a significant behavioral gap between humans and machines. We find that the evolutionary need for humans to detect animal faces, as well as human faces, may explain some of this gap. Finally, we propose a simple statistical model of pareidolia in images. Through studies on human subjects and our pareidolic face detectors we confirm a key prediction of our model regarding what image conditions are most likely to induce pareidolia. Dataset and Website: https://aka.ms/faces-in-things
Authors: Ioannis Kouroudis, Poonam, Neel Misciaci, Felix Mayr, Leon M\"uller, Zhaosu Gu, Alessio Gagliardi
Abstract: In this paper, we propose a novel flexible optimization pipeline for determining the optimal adsorption sites, named AUGUR (Aware of Uncertainty Graph Unit Regression). Our model combines graph neural networks and Gaussian processes to create a flexible, efficient, symmetry-aware, translation, and rotation- invariant predictor with inbuilt uncertainty quantification. This predictor is then used as a surrogate for a data-efficient Bayesian Optimization scheme to determine the optimal adsorption positions. This pipeline determines the optimal position of large and complicated clusters with far fewer iterations than current state-of-the-art approaches. Further, it does not rely on hand-crafted features and can be seamlessly employed on any molecule without any alterations. Additionally, the pooling properties of graphs allow for the processing of molecules of different sizes by the same model. This allows the energy prediction of computationally demanding systems by a model trained on comparatively smaller and less expensive ones
Authors: Mark Weber, Lijun Yu, Qihang Yu, Xueqing Deng, Xiaohui Shen, Daniel Cremers, Liang-Chieh Chen
Abstract: Masked transformer models for class-conditional image generation have become a compelling alternative to diffusion models. Typically comprising two stages - an initial VQGAN model for transitioning between latent space and image space, and a subsequent Transformer model for image generation within latent space - these frameworks offer promising avenues for image synthesis. In this study, we present two primary contributions: Firstly, an empirical and systematic examination of VQGANs, leading to a modernized VQGAN. Secondly, a novel embedding-free generation network operating directly on bit tokens - a binary quantized representation of tokens with rich semantics. The first contribution furnishes a transparent, reproducible, and high-performing VQGAN model, enhancing accessibility and matching the performance of current state-of-the-art methods while revealing previously undisclosed details. The second contribution demonstrates that embedding-free image generation using bit tokens achieves a new state-of-the-art FID of 1.52 on the ImageNet 256x256 benchmark, with a compact generator model of mere 305M parameters.
Authors: Harry Rogers, Tahmina Zebin, Grzegorz Cielniak, Beatriz De La Iglesia, Ben Magri
Abstract: Precision spraying evaluation requires automation primarily in post-spraying imagery. In this paper we propose an eXplainable Artificial Intelligence (XAI) computer vision pipeline to evaluate a precision spraying system post-spraying without the need for traditional agricultural methods. The developed system can semantically segment potential targets such as lettuce, chickweed, and meadowgrass and correctly identify if targets have been sprayed. Furthermore, this pipeline evaluates using a domain-specific Weakly Supervised Deposition Estimation task, allowing for class-specific quantification of spray deposit weights in {\mu}L. Estimation of coverage rates of spray deposition in a class-wise manner allows for further understanding of effectiveness of precision spraying systems. Our study evaluates different Class Activation Mapping techniques, namely AblationCAM and ScoreCAM, to determine which is more effective and interpretable for these tasks. In the pipeline, inference-only feature fusion is used to allow for further interpretability and to enable the automation of precision spraying evaluation post-spray. Our findings indicate that a Fully Convolutional Network with an EfficientNet-B0 backbone and inference-only feature fusion achieves an average absolute difference in deposition values of 156.8 {\mu}L across three classes in our test set. The dataset curated in this paper is publicly available at https://github.com/Harry-Rogers/PSIE
Authors: Hannah Kerner, Snehal Chaudhari, Aninda Ghosh, Caleb Robinson, Adeel Ahmad, Eddie Choi, Nathan Jacobs, Chris Holmes, Matthias Mohr, Rahul Dodhia, Juan M. Lavista Ferres, Jennifer Marcus
Abstract: Crop field boundaries are foundational datasets for agricultural monitoring and assessments but are expensive to collect manually. Machine learning (ML) methods for automatically extracting field boundaries from remotely sensed images could help realize the demand for these datasets at a global scale. However, current ML methods for field instance segmentation lack sufficient geographic coverage, accuracy, and generalization capabilities. Further, research on improving ML methods is restricted by the lack of labeled datasets representing the diversity of global agricultural fields. We present Fields of The World (FTW) -- a novel ML benchmark dataset for agricultural field instance segmentation spanning 24 countries on four continents (Europe, Africa, Asia, and South America). FTW is an order of magnitude larger than previous datasets with 70,462 samples, each containing instance and semantic segmentation masks paired with multi-date, multi-spectral Sentinel-2 satellite images. We provide results from baseline models for the new FTW benchmark, show that models trained on FTW have better zero-shot and fine-tuning performance in held-out countries than models that aren't pre-trained with diverse datasets, and show positive qualitative zero-shot results of FTW models in a real-world scenario -- running on Sentinel-2 scenes over Ethiopia.
Authors: Homanga Bharadhwaj, Debidatta Dwibedi, Abhinav Gupta, Shubham Tulsiani, Carl Doersch, Ted Xiao, Dhruv Shah, Fei Xia, Dorsa Sadigh, Sean Kirmani
Abstract: How can robot manipulation policies generalize to novel tasks involving unseen object types and new motions? In this paper, we provide a solution in terms of predicting motion information from web data through human video generation and conditioning a robot policy on the generated video. Instead of attempting to scale robot data collection which is expensive, we show how we can leverage video generation models trained on easily available web data, for enabling generalization. Our approach Gen2Act casts language-conditioned manipulation as zero-shot human video generation followed by execution with a single policy conditioned on the generated video. To train the policy, we use an order of magnitude less robot interaction data compared to what the video prediction model was trained on. Gen2Act doesn't require fine-tuning the video model at all and we directly use a pre-trained model for generating human videos. Our results on diverse real-world scenarios show how Gen2Act enables manipulating unseen object types and performing novel motions for tasks not present in the robot data. Videos are at https://homangab.github.io/gen2act/
Authors: Xi Wang, Tianxing Chen, Qiaojun Yu, Tianling Xu, Zanxin Chen, Yiting Fu, Cewu Lu, Yao Mu, Ping Luo
Abstract: Articulated object manipulation requires precise object interaction, where the object's axis must be carefully considered. Previous research employed interactive perception for manipulating articulated objects, but typically, open-loop approaches often suffer from overlooking the interaction dynamics. To address this limitation, we present a closed-loop pipeline integrating interactive perception with online axis estimation from segmented 3D point clouds. Our method leverages any interactive perception technique as a foundation for interactive perception, inducing slight object movement to generate point cloud frames of the evolving dynamic scene. These point clouds are then segmented using Segment Anything Model 2 (SAM2), after which the moving part of the object is masked for accurate motion online axis estimation, guiding subsequent robotic actions. Our approach significantly enhances the precision and efficiency of manipulation tasks involving articulated objects. Experiments in simulated environments demonstrate that our method outperforms baseline approaches, especially in tasks that demand precise axis-based control. Project Page: https://hytidel.github.io/video-tracking-for-axis-estimation/.
URLs: https://hytidel.github.io/video-tracking-for-axis-estimation/.
Authors: Nicholas D. Kullman, Nikita Dudorov, Jorge E. Mendoza, Martin Cousineau, Justin C. Goodson
Abstract: Do you remember your first video game console? We remember ours. Decades ago, they provided hours of entertainment. Now, we have repurposed them to solve dynamic and stochastic optimization problems. With deep reinforcement learning methods posting superhuman performance on a wide range of Atari games, we consider the task of representing a classic logistics problem as a game. Then, we train agents to play it. We consider several game designs for the vehicle routing problem with stochastic requests. We show how various design features impact agents' performance, including perspective, field of view, and minimaps. With the right game design, general purpose Atari agents outperform optimization-based benchmarks, especially as problem size grows. Our work points to the representation of dynamic and stochastic optimization problems via games as a promising research direction.
Authors: Anis Elgabli, Mohammed S. Elbamby, Cristina Perfecto, Mounssif Krouka, Mehdi Bennis, Vaneet Aggarwal
Abstract: Wirelessly streaming high quality 360 degree videos is still a challenging problem. When there are many users watching different 360 degree videos and competing for the computing and communication resources, the streaming algorithm at hand should maximize the average quality of experience (QoE) while guaranteeing a minimum rate for each user. In this paper, we propose a cross layer optimization approach that maximizes the available rate to each user and efficiently uses it to maximize users' QoE. Particularly, we consider a tile based 360 degree video streaming, and we optimize a QoE metric that balances the tradeoff between maximizing each user's QoE and ensuring fairness among users. We show that the problem can be decoupled into two interrelated subproblems: (i) a physical layer subproblem whose objective is to find the download rate for each user, and (ii) an application layer subproblem whose objective is to use that rate to find a quality decision per tile such that the user's QoE is maximized. We prove that the physical layer subproblem can be solved optimally with low complexity and an actor-critic deep reinforcement learning (DRL) is proposed to leverage the parallel training of multiple independent agents and solve the application layer subproblem. Extensive experiments reveal the robustness of our scheme and demonstrate its significant performance improvement compared to several baseline algorithms.
Authors: Weihuang Wen, Tianshu Yu
Abstract: The Boolean Satisfiability (SAT) problem stands out as an attractive NP-complete problem in theoretic computer science and plays a central role in a broad spectrum of computing-related applications. Exploiting and tuning SAT solvers under numerous scenarios require massive high-quality industry-level SAT instances, which unfortunately are quite limited in the real world. To address the data insufficiency issue, in this paper, we propose W2SAT, a framework to generate SAT formulas by learning intrinsic structures and properties from given real-world/industrial instances in an implicit fashion. To this end, we introduce a novel SAT representation called Weighted Literal Incidence Graph (WLIG), which exhibits strong representation ability and generalizability against existing counterparts, and can be efficiently generated via a specialized learning-based graph generative model. Decoding from WLIGs into SAT problems is then modeled as finding overlapping cliques with a novel hill-climbing optimization method termed Optimal Weight Coverage (OWC). Experiments demonstrate the superiority of our WLIG-induced approach in terms of graph metrics, efficiency, and scalability in comparison to previous methods. Additionally, we discuss the limitations of graph-based SAT generation for real-world applications, especially when utilizing generated instances for SAT solver parameter-tuning, and pose some potential directions.
Authors: Guy Blanc
Abstract: Ensuring that analyses performed on a dataset are representative of the entire population is one of the central problems in statistics. Most classical techniques assume that the dataset is independent of the analyst's query and break down in the common setting where a dataset is reused for multiple, adaptively chosen, queries. This problem of \emph{adaptive data analysis} was formalized in the seminal works of Dwork et al. (STOC, 2015) and Hardt and Ullman (FOCS, 2014). We identify a remarkably simple set of assumptions under which the queries will continue to be representative even when chosen adaptively: The only requirements are that each query takes as input a random subsample and outputs few bits. This result shows that the noise inherent in subsampling is sufficient to guarantee that query responses generalize. The simplicity of this subsampling-based framework allows it to model a variety of real-world scenarios not covered by prior work. In addition to its simplicity, we demonstrate the utility of this framework by designing mechanisms for two foundational tasks, statistical queries and median finding. In particular, our mechanism for answering the broadly applicable class of statistical queries is both extremely simple and state of the art in many parameter regimes.
Authors: Adam Gosztolai, Robert L. Peach, Alexis Arnaudon, Mauricio Barahona, Pierre Vandergheynst
Abstract: The dynamics of neuron populations commonly evolve on low-dimensional manifolds. Thus, we need methods that learn the dynamical processes over neural manifolds to infer interpretable and consistent latent representations. We introduce a representation learning method, MARBLE, that decomposes on-manifold dynamics into local flow fields and maps them into a common latent space using unsupervised geometric deep learning. In simulated non-linear dynamical systems, recurrent neural networks, and experimental single-neuron recordings from primates and rodents, we discover emergent low-dimensional latent representations that parametrise high-dimensional neural dynamics during gain modulation, decision-making, and changes in the internal state. These representations are consistent across neural networks and animals, enabling the robust comparison of cognitive computations. Extensive benchmarking demonstrates state-of-the-art within- and across-animal decoding accuracy of MARBLE compared with current representation learning approaches, with minimal user input. Our results suggest that manifold structure provides a powerful inductive bias to develop powerful decoding algorithms and assimilate data across experiments.
Authors: Utsav Singh, Vinay P. Namboodiri
Abstract: Hierarchical reinforcement learning (HRL) is a promising approach that uses temporal abstraction to solve complex long horizon problems. However, simultaneously learning a hierarchy of policies is unstable as it is challenging to train higher-level policy when the lower-level primitive is non-stationary. In this paper, we present CRISP, a novel HRL algorithm that effectively generates a curriculum of achievable subgoals for evolving lower-level primitives using reinforcement learning and imitation learning. CRISP uses the lower level primitive to periodically perform data relabeling on a handful of expert demonstrations, using a novel primitive informed parsing (PIP) approach, thereby mitigating non-stationarity. Since our approach only assumes access to a handful of expert demonstrations, it is suitable for most robotic control tasks. Experimental evaluations on complex robotic maze navigation and robotic manipulation tasks demonstrate that inducing hierarchical curriculum learning significantly improves sample efficiency, and results in efficient goal conditioned policies for solving temporally extended tasks. Additionally, we perform real world robotic experiments on complex manipulation tasks and demonstrate that CRISP demonstrates impressive generalization in real world scenarios.
Authors: Weiye Zhao, Yifan Sun, Feihan Li, Rui Chen, Ruixuan Liu, Tianhao Wei, Changliu Liu
Abstract: Due to the trial-and-error nature, it is typically challenging to apply RL algorithms to safety-critical real-world applications, such as autonomous driving, human-robot interaction, robot manipulation, etc, where such errors are not tolerable. Recently, safe RL (i.e. constrained RL) has emerged rapidly in the literature, in which the agents explore the environment while satisfying constraints. Due to the diversity of algorithms and tasks, it remains difficult to compare existing safe RL algorithms. To fill that gap, we introduce GUARD, a Generalized Unified SAfe Reinforcement Learning Development Benchmark. GUARD has several advantages compared to existing benchmarks. First, GUARD is a generalized benchmark with a wide variety of RL agents, tasks, and safety constraint specifications. Second, GUARD comprehensively covers state-of-the-art safe RL algorithms with self-contained implementations. Third, GUARD is highly customizable in tasks and algorithms. We present a comparison of state-of-the-art safe RL algorithms in various task settings using GUARD and establish baselines that future work can build on.
Authors: Christian Komusiewicz, Pascal Kunz, Frank Sommer, Manuel Sorge
Abstract: Random forests and, more generally, (decision\nobreakdash-)tree ensembles are widely used methods for classification and regression. Recent algorithmic advances allow to compute decision trees that are optimal for various measures such as their size or depth. We are not aware of such research for tree ensembles and aim to contribute to this area. Mainly, we provide two novel algorithms and corresponding lower bounds. First, we are able to carry over and substantially improve on tractability results for decision trees: We obtain an algorithm that, given a training-data set and an size bound $S \in \mathbb{R}$, computes a tree ensemble of size at most $S$ that classifies the data correctly. The algorithm runs in $(4\delta D S)^S \cdot poly$-time, where $D$ the largest domain size, $\delta$ is the largest number of features in which two examples differ, $n$ the number of input examples, and $poly$ a polynomial of the input size. For decision trees, that is, ensembles of size 1, we obtain a running time of $(\delta D s)^s \cdot poly$, where $s$ is the size of the tree. To obtain these algorithms, we introduce the witness-tree technique, which seems promising for practical implementations. Secondly, we show that dynamic programming, which has been applied successfully to computing decision trees, may also be viable for tree ensembles, providing an $\ell^n \cdot poly$-time algorithm, where $\ell$ is the number of trees. Finally, we compare the number of cuts necessary to classify training data sets for decision trees and tree ensembles, showing that ensembles may need exponentially fewer cuts for increasing number of trees.
Authors: Jingyang Zhang, Jingkang Yang, Pengyun Wang, Haoqi Wang, Yueqian Lin, Haoran Zhang, Yiyou Sun, Xuefeng Du, Yixuan Li, Ziwei Liu, Yiran Chen, Hai Li
Abstract: Out-of-Distribution (OOD) detection is critical for the reliable operation of open-world intelligent systems. Despite the emergence of an increasing number of OOD detection methods, the evaluation inconsistencies present challenges for tracking the progress in this field. OpenOOD v1 initiated the unification of the OOD detection evaluation but faced limitations in scalability and usability. In response, this paper presents OpenOOD v1.5, a significant improvement from its predecessor that ensures accurate, standardized, and user-friendly evaluation of OOD detection methodologies. Notably, OpenOOD v1.5 extends its evaluation capabilities to large-scale datasets such as ImageNet, investigates full-spectrum OOD detection which is important yet underexplored, and introduces new features including an online leaderboard and an easy-to-use evaluator. This work also contributes in-depth analysis and insights derived from comprehensive experimental results, thereby enriching the knowledge pool of OOD detection methodologies. With these enhancements, OpenOOD v1.5 aims to drive advancements and offer a more robust and comprehensive evaluation benchmark for OOD detection research.
Authors: Md Ferdous Alam, Yi Wang, Chin-Yi Cheng, Jieliang Luo
Abstract: Volumetric design, also called massing design, is the first and critical step in professional building design which is sequential in nature. As the volumetric design process requires careful design decisions and iterative adjustments, the underlying sequential design process encodes valuable information for designers. Many efforts have been made to automatically generate reasonable volumetric designs, but the quality of the generated design solutions varies, and evaluating a design solution requires either a prohibitively comprehensive set of metrics or expensive human expertise. While previous approaches focused on learning only the final design instead of sequential design tasks, we propose to encode the design knowledge from a collection of expert or high-performing design sequences and extract useful representations using transformer-based models. Later we propose to utilize the learned representations for crucial downstream applications such as design preference evaluation and procedural design generation. We develop the preference model by estimating the density of the learned representations whereas we train an autoregressive transformer model for sequential design generation. We demonstrate our ideas by leveraging a novel dataset of thousands of sequential volumetric designs. Our preference model can compare two arbitrarily given design sequences and is almost $90\%$ accurate in evaluation against random design sequences. Our autoregressive model is also capable of autocompleting a volumetric design sequence from a partial design sequence.
Authors: Arjun Roy, Christos Koutlis, Symeon Papadopoulos, Eirini Ntoutsi
Abstract: The generalisation capacity of Multi-Task Learning (MTL) suffers when unrelated tasks negatively impact each other by updating shared parameters with conflicting gradients. This is known as negative transfer and leads to a drop in MTL accuracy compared to single-task learning (STL). Lately, there has been a growing focus on the fairness of MTL models, requiring the optimization of both accuracy and fairness for individual tasks. Analogously to negative transfer for accuracy, task-specific fairness considerations might adversely affect the fairness of other tasks when there is a conflict of fairness loss gradients between the jointly learned tasks - we refer to this as Bias Transfer. To address both negative- and bias-transfer in MTL, we propose a novel method called FairBranch, which branches the MTL model by assessing the similarity of learned parameters, thereby grouping related tasks to alleviate negative transfer. Moreover, it incorporates fairness loss gradient conflict correction between adjoining task-group branches to address bias transfer within these task groups. Our experiments on tabular and visual MTL problems show that FairBranch outperforms state-of-the-art MTLs on both fairness and accuracy.
Authors: Johannes Hagemann, Samuel Weinbach, Konstantin Dobler, Maximilian Schall, Gerard de Melo
Abstract: Efficiently training large language models requires parallelizing across hundreds of hardware accelerators and invoking various compute and memory optimizations. When combined, many of these strategies have complex interactions regarding the final training efficiency. Prior work tackling this problem did not have access to the latest set of optimizations, such as FlashAttention or sequence parallelism. In this work, we conduct a comprehensive ablation study of possible training configurations for large language models. We distill this large study into several key recommendations for the most efficient training. For instance, we find that using a micro-batch size of 1 usually enables the most efficient training layouts. Larger micro-batch sizes necessitate activation checkpointing or higher degrees of model parallelism and also lead to larger pipeline bubbles. Our most efficient configurations enable us to achieve state-of-the-art training efficiency results over a range of model sizes, most notably a Model FLOPs utilization of 70.5% when training a Llama 13B model.
Authors: Ying Liu, Peng Cui, Wenbo Hu, Richang Hong
Abstract: Real-world time series data frequently have significant amounts of missing values, posing challenges for advanced analysis. A common approach to address this issue is imputation, where the primary challenge lies in determining the appropriate values to fill in. While previous deep learning methods have proven effective for time series imputation, they often produce overconfident imputations, which could brings a potentially overlooked risk to the reliability of the intelligent system. Diffusion methods are proficient in estimating probability distributions but face challenges with high missing rates and moreover, computationally expensive due to the nature of the generative model framework. In this paper, we propose Quantile Sub-Ensembles, a novel method to estimate uncertainty with ensemble of quantile-regression-based task networks and then incorporate Quantile Sub-Ensembles into a non-generative time series imputation method. Our method not only produces accurate imputations that is robust to high missing rates, but also is computationally efficient due to the fast training of its non-generative model. We examine the performance of the proposed method on two real-world datasets, the air quality and health-care datasets, and conduct extensive experiments to show that our method outperforms other most of the baseline methods in making deterministic and probabilistic imputations. Compared with the diffusion method, CSDI, our approach can obtain comparable forecasting results which is better when more data is missing, and moreover consumes a much smaller computation overhead, yielding much faster training and test.
Authors: Bernhard Jaeger, Andreas Geiger
Abstract: Training a deep neural network to maximize a target objective has become the standard recipe for successful machine learning over the last decade. These networks can be optimized with supervised learning, if the target objective is differentiable. For many interesting problems, this is however not the case. Common objectives like intersection over union (IoU), bilingual evaluation understudy (BLEU) score or rewards cannot be optimized with supervised learning. A common workaround is to define differentiable surrogate losses, leading to suboptimal solutions with respect to the actual objective. Reinforcement learning (RL) has emerged as a promising alternative for optimizing deep neural networks to maximize non-differentiable objectives in recent years. Examples include aligning large language models via human feedback, code generation, object detection or control problems. This makes RL techniques relevant to the larger machine learning audience. The subject is, however, time intensive to approach due to the large range of methods, as well as the often very theoretical presentation. In this introduction, we take an alternative approach, different from classic reinforcement learning textbooks. Rather than focusing on tabular problems, we introduce reinforcement learning as a generalization of supervised learning, which we first apply to non-differentiable objectives and later to temporal problems. Assuming only basic knowledge of supervised learning, the reader will be able to understand state-of-the-art deep RL algorithms like proximal policy optimization (PPO) after reading this tutorial.
Authors: Mohammad Izadi, Mehran Safayani, Abdolreza Mirzaei
Abstract: Efficient real-time traffic prediction is crucial for reducing transportation time. To predict traffic conditions, we employ a spatio-temporal graph neural network (ST-GNN) to model our real-time traffic data as temporal graphs. Despite its capabilities, it often encounters challenges in delivering efficient real-time predictions for real-world traffic data. Recognizing the significance of timely prediction due to the dynamic nature of real-time data, we employ knowledge distillation (KD) as a solution to enhance the execution time of ST-GNNs for traffic prediction. In this paper, We introduce a cost function designed to train a network with fewer parameters (the student) using distilled data from a complex network (the teacher) while maintaining its accuracy close to that of the teacher. We use knowledge distillation, incorporating spatial-temporal correlations from the teacher network to enable the student to learn the complex patterns perceived by the teacher. However, a challenge arises in determining the student network architecture rather than considering it inadvertently. To address this challenge, we propose an algorithm that utilizes the cost function to calculate pruning scores, addressing small network architecture search issues, and jointly fine-tunes the network resulting from each pruning stage using KD. Ultimately, we evaluate our proposed ideas on two real-world datasets, PeMSD7 and PeMSD8. The results indicate that our method can maintain the student's accuracy close to that of the teacher, even with the retention of only 3% of network parameters.
Authors: Cooper Lorsung, Amir Barati Farimani
Abstract: Neural operators have recently grown in popularity as Partial Differential Equation (PDE) surrogate models. Learning solution functionals, rather than functions, has proven to be a powerful approach to calculate fast, accurate solutions to complex PDEs. While much work has been done evaluating neural operator performance on a wide variety of surrogate modeling tasks, these works normally evaluate performance on a single equation at a time. In this work, we develop a novel contrastive pretraining framework utilizing Generalized Contrastive Loss that improves neural operator generalization across multiple governing equations simultaneously. Governing equation coefficients are used to measure ground-truth similarity between systems. A combination of physics-informed system evolution and latent-space model output are anchored to input data and used in our distance function. We find that physics-informed contrastive pretraining improves accuracy for the Fourier Neural Operator in fixed-future and autoregressive rollout tasks for the 1D and 2D Heat, Burgers', and linear advection equations.
Authors: Cagri Ozdemir, Mohammad Al Olaimat, Yashu Vashishath, Serdar Bozdag, Alzheimer's Disease Neuroimaging Initiative
Abstract: Developing computational tools for integrative analysis across multiple types of omics data has been of immense importance in cancer molecular biology and precision medicine research. While recent advancements have yielded integrative prediction solutions for multi-omics data, these methods lack a comprehensive and cohesive understanding of the rationale behind their specific predictions. To shed light on personalized medicine and unravel previously unknown characteristics within integrative analysis of multi-omics data, we introduce a novel integrative neural network approach for cancer molecular subtype and biomedical classification applications, named Integrative Graph Convolutional Networks (IGCN). IGCN can identify which types of omics receive more emphasis for each patient to predict a certain class. Additionally, IGCN has the capability to pinpoint significant biomarkers from a range of omics data types. To demonstrate the superiority of IGCN, we compare its performance with other state-of-the-art approaches across different cancer subtype and biomedical classification tasks.
Authors: Siddhartha Dalal, Vishal Misra
Abstract: This paper introduces a novel Bayesian learning model to explain the behavior of Large Language Models (LLMs), focusing on their core optimization metric of next token prediction. We develop a theoretical framework based on an ideal generative text model represented by a multinomial transition probability matrix with a prior, and examine how LLMs approximate this matrix. Key contributions include: (i) a continuity theorem relating embeddings to multinomial distributions, (ii) a demonstration that LLM text generation aligns with Bayesian learning principles, (iii) an explanation for the emergence of in-context learning in larger models, (iv) empirical validation using visualizations of next token probabilities from an instrumented Llama model Our findings provide new insights into LLM functioning, offering a statistical foundation for understanding their capabilities and limitations. This framework has implications for LLM design, training, and application, potentially guiding future developments in the field.
Authors: Lianghao Xia, Ben Kao, Chao Huang
Abstract: Graph learning has become indispensable for interpreting and harnessing relational data in diverse fields, ranging from recommendation systems to social network analysis. In this context, a variety of GNNs have emerged as promising methodologies for encoding the structural information of graphs. By effectively capturing the graph's underlying structure, these GNNs have shown great potential in enhancing performance in graph learning tasks, such as link prediction and node classification. However, despite their successes, a significant challenge persists: these advanced methods often face difficulties in generalizing to unseen graph data that significantly differs from the training instances. In this work, our aim is to advance the graph learning paradigm by developing a general graph foundation model. This model is designed to understand the complex topological patterns present in diverse graph data, enabling it to excel in zero-shot graph learning tasks across different downstream datasets. To achieve this goal, we address several key technical challenges in our OpenGraph model. Firstly, we propose a unified graph tokenizer to adapt our graph model to generalize well on unseen graph data, even when the underlying graph properties differ significantly from those encountered during training. Secondly, we develop a scalable graph transformer as the foundational encoder, which effectively captures node-wise dependencies within the global topological context. Thirdly, we introduce a data augmentation mechanism enhanced by a LLM to alleviate the limitations of data scarcity in real-world scenarios. Extensive experiments validate the effectiveness of our framework. By adapting our OpenGraph to new graph characteristics and comprehending the nuances of diverse graphs, our approach achieves remarkable zero-shot graph learning performance across various settings and domains.
Authors: Yunpeng Qing, Shunyu liu, Jingyuan Cong, Kaixuan Chen, Yihe Zhou, Mingli Song
Abstract: Offline reinforcement learning endeavors to leverage offline datasets to craft effective agent policy without online interaction, which imposes proper conservative constraints with the support of behavior policies to tackle the out-of-distribution problem. However, existing works often suffer from the constraint conflict issue when offline datasets are collected from multiple behavior policies, i.e., different behavior policies may exhibit inconsistent actions with distinct returns across the state space. To remedy this issue, recent advantage-weighted methods prioritize samples with high advantage values for agent training while inevitably ignoring the diversity of behavior policy. In this paper, we introduce a novel Advantage-Aware Policy Optimization (A2PO) method to explicitly construct advantage-aware policy constraints for offline learning under mixed-quality datasets. Specifically, A2PO employs a conditional variational auto-encoder to disentangle the action distributions of intertwined behavior policies by modeling the advantage values of all training data as conditional variables. Then the agent can follow such disentangled action distribution constraints to optimize the advantage-aware policy towards high advantage values. Extensive experiments conducted on both the single-quality and mixed-quality datasets of the D4RL benchmark demonstrate that A2PO yields results superior to the counterparts. Our code will be made publicly available.
Authors: Yushan Huang, Ranya Aloufi, Xavier Cadet, Yuchen Zhao, Payam Barnaghi, Hamed Haddadi
Abstract: Microcontroller Units (MCUs) are ideal platforms for edge applications due to their low cost and energy consumption, and are widely used in various applications, including personalized machine learning tasks, where customized models can enhance the task adaptation. However, existing approaches for local on-device personalization mostly support simple ML architectures or require complex local pre-training/training, leading to high energy consumption and negating the low-energy advantage of MCUs. In this paper, we introduce $MicroT$, an efficient and low-energy MCU personalization approach. $MicroT$ includes a robust, general, but tiny feature extractor, developed through self-supervised knowledge distillation, which trains a task-specific head to enable independent on-device personalization with minimal energy and computational requirements. MicroT implements an MCU-optimized early-exit inference mechanism called stage-decision to further reduce energy costs. This mechanism allows for user-configurable exit criteria (stage-decision ratio) to adaptively balance energy cost with model performance. We evaluated MicroT using two models, three datasets, and two MCU boards. $MicroT$ outperforms traditional transfer learning (TTL) and two SOTA approaches by 2.12 - 11.60% across two models and three datasets. Targeting widely used energy-aware edge devices, MicroT's on-device training requires no additional complex operations, halving the energy cost compared to SOTA approaches by up to 2.28$\times$ while keeping SRAM usage below 1MB. During local inference, MicroT reduces energy cost by 14.17% compared to TTL across two boards and two datasets, highlighting its suitability for long-term use on energy-aware resource-constrained MCUs.
Authors: Jingren Liu, Zhong Ji, Yanwei Pang, YunLong Yu
Abstract: The proliferation of Few-Shot Class Incremental Learning (FSCIL) methodologies has highlighted the critical challenge of maintaining robust anti-amnesia capabilities in FSCIL learners. In this paper, we present a novel conceptualization of anti-amnesia in terms of mathematical generalization, leveraging the Neural Tangent Kernel (NTK) perspective. Our method focuses on two key aspects: ensuring optimal NTK convergence and minimizing NTK-related generalization loss, which serve as the theoretical foundation for cross-task generalization. To achieve global NTK convergence, we introduce a principled meta-learning mechanism that guides optimization within an expanded network architecture. Concurrently, to reduce the NTK-related generalization loss, we systematically optimize its constituent factors. Specifically, we initiate self-supervised pre-training on the base session to enhance NTK-related generalization potential. These self-supervised weights are then carefully refined through curricular alignment, followed by the application of dual NTK regularization tailored specifically for both convolutional and linear layers. Through the combined effects of these measures, our network acquires robust NTK properties, ensuring optimal convergence and stability of the NTK matrix and minimizing the NTK-related generalization loss, significantly enhancing its theoretical generalization. On popular FSCIL benchmark datasets, our NTK-FSCIL surpasses contemporary state-of-the-art approaches, elevating end-session accuracy by 2.9\% to 9.3\%.
Authors: Tianxiang Zhan, Yuanpeng He, Yong Deng, Zhen Li, Wenjie Du, Qingsong Wen
Abstract: In practical scenarios, time series forecasting necessitates not only accuracy but also efficiency. Consequently, the exploration of model architectures remains a perennially trending topic in research. To address these challenges, we propose a novel backbone architecture named Time Evidence Fusion Network (TEFN) from the perspective of information fusion. Specifically, we introduce the Basic Probability Assignment (BPA) Module based on evidence theory to capture the uncertainty of multivariate time series data from both channel and time dimensions. Additionally, we develop a novel multi-source information fusion method to effectively integrate the two distinct dimensions from BPA output, leading to improved forecasting accuracy. Lastly, we conduct extensive experiments to demonstrate that TEFN achieves performance comparable to state-of-the-art methods while maintaining significantly lower complexity and reduced training time. Also, our experiments show that TEFN exhibits high robustness, with minimal error fluctuations during hyperparameter selection. Furthermore, due to the fact that BPA is derived from fuzzy theory, TEFN offers a high degree of interpretability. Therefore, the proposed TEFN balances accuracy, efficiency, stability, and interpretability, making it a desirable solution for time series forecasting.
Authors: Elika Bozorgi, Sakher Khalil Alqaiidi, Afsaneh Shams, Hamid Reza Arabnia, Krzysztof Kochut
Abstract: Machine learning, deep learning, and NLP methods on knowledge graphs are present in different fields and have important roles in various domains from self-driving cars to friend recommendations on social media platforms. However, to apply these methods to knowledge graphs, the data usually needs to be in an acceptable size and format. In fact, knowledge graphs normally have high dimensions and therefore we need to transform them to a low-dimensional vector space. An embedding is a low-dimensional space into which you can translate high dimensional vectors in a way that intrinsic features of the input data are preserved. In this review, we first explain knowledge graphs and their embedding and then review some of the random walk-based embedding methods that have been developed recently.
Authors: Tom Tseng, Euan McLean, Kellin Pelrine, Tony T. Wang, Adam Gleave
Abstract: Prior work found that superhuman Go AIs can be defeated by simple adversarial strategies, especially "cyclic" attacks. In this paper, we study whether adding natural countermeasures can achieve robustness in Go, a favorable domain for robustness since it benefits from incredible average-case capability and a narrow, innately adversarial setting. We test three defenses: adversarial training on hand-constructed positions, iterated adversarial training, and changing the network architecture. We find that though some of these defenses protect against previously discovered attacks, none withstand freshly trained adversaries. Furthermore, most of the reliably effective attacks these adversaries discover are different realizations of the same overall class of cyclic attacks. Our results suggest that building robust AI systems is challenging even with extremely superhuman systems in some of the most tractable settings, and highlight two key gaps: efficient generalization in defenses, and diversity in training. For interactive examples of attacks and a link to our codebase, see https://goattack.far.ai.
URLs: https://goattack.far.ai.
Authors: Beatrice Alessandra Motetti, Matteo Risso, Alessio Burrello, Enrico Macii, Massimo Poncino, Daniele Jahier Pagliari
Abstract: The resource requirements of deep neural networks (DNNs) pose significant challenges to their deployment on edge devices. Common approaches to address this issue are pruning and mixed-precision quantization, which lead to latency and memory occupation improvements. These optimization techniques are usually applied independently. We propose a novel methodology to apply them jointly via a lightweight gradient-based search, and in a hardware-aware manner, greatly reducing the time required to generate Pareto-optimal DNNs in terms of accuracy versus cost (i.e., latency or memory). We test our approach on three edge-relevant benchmarks, namely CIFAR-10, Google Speech Commands, and Tiny ImageNet. When targeting the optimization of the memory footprint, we are able to achieve a size reduction of 47.50% and 69.54% at iso-accuracy with the baseline networks with all weights quantized at 8 and 2-bit, respectively. Our method surpasses a previous state-of-the-art approach with up to 56.17% size reduction at iso-accuracy. With respect to the sequential application of state-of-the-art pruning and mixed-precision optimizations, we obtain comparable or superior results, but with a significantly lowered training time. In addition, we show how well-tailored cost models can improve the cost versus accuracy trade-offs when targeting specific hardware for deployment.
Authors: Gabriele Franch, Elena Tomasi, Rishabh Wanjari, Virginia Poli, Chiara Cardinali, Pier Paolo Alberoni, Marco Cristoforetti
Abstract: This work introduces GPTCast, a generative deep-learning method for ensemble nowcast of radar-based precipitation, inspired by advancements in large language models (LLMs). We employ a GPT model as a forecaster to learn spatiotemporal precipitation dynamics using tokenized radar images. The tokenizer is based on a Quantized Variational Autoencoder featuring a novel reconstruction loss tailored for the skewed distribution of precipitation that promotes faithful reconstruction of high rainfall rates. The approach produces realistic ensemble forecasts and provides probabilistic outputs with accurate uncertainty estimation. The model is trained without resorting to randomness, all variability is learned solely from the data and exposed by model at inference for ensemble generation. We train and test GPTCast using a 6-year radar dataset over the Emilia-Romagna region in Northern Italy, showing superior results compared to state-of-the-art ensemble extrapolation methods.
Authors: Yichun Ye, He Zhang, Ye Tian, Jian Sun, Karl Meinke
Abstract: Automated Vehicle (AV) validation based on simulated testing requires unbiased evaluation and high efficiency. One effective solution is to increase the exposure to risky rare events while reweighting the probability measure. However, characterizing the distribution of risky events is particularly challenging due to the paucity of samples and the temporality of continuous scenario variables. To solve it, we devise a method to represent, generate, and reweight the distribution of risky rare events. We decompose the temporal evolution of continuous variables into distribution components based on conditional probability. By introducing the Risk Indicator Function, the distribution of risky rare events is theoretically precipitated out of naturalistic driving distribution. This targeted distribution is practically generated via Normalizing Flow, which achieves exact and tractable probability evaluation of intricate distribution. The rare event distribution is then demonstrated as the advantageous Importance Sampling distribution. We also promote the technique of temporal Importance Sampling. The combined method, named as TrimFlow, is executed to estimate the collision rate of Car-following scenarios as a tentative practice. The results showed that sampling background vehicle maneuvers from rare event distribution could evolve testing scenarios to hazardous states. TrimFlow reduced 86.1% of tests compared to generating testing scenarios according to their exposure in the naturalistic driving environment. In addition, the TrimFlow method is not limited to one specific type of functional scenario.
Authors: Juan Miguel Lopez Alcaraz, Hjalmar Bouma, Nils Strodthoff
Abstract: Background: A clinically meaningful comparative assessment of medical decision support in emergency care is challenging due to a lack of appropriate datasets with multimodal input modalities and comprehensive prediction task. This hampers measurable progress in the field. Results: We introduce a dataset based on MIMIC-IV, a benchmarking protocol, and initial results for evaluating multimodal decision support in the emergency department (ED). We use diverse data modalities from the first 1.5 hours after patient arrival, including demographics, biometrics, vital signs, lab values, and electrocardiogram waveforms. We analyze 1443 clinical labels across two contexts: predicting diagnoses and patient deterioration. Our diagnostic model achieves an AUROC score over 0.8 in a statistically significant manner for 609 out of 1428 conditions, including cardiac conditions like myocardial infarction and non-cardiac conditions such as renal disease and diabetes. The deterioration model scores above 0.8 in a statistically significant manner for 14 out of 15 targets, including critical events like cardiac arrest, mechanical ventilation, intensive care unit admission, as well as short- and long-term mortality. Furthermore, we provide one of the first robust demonstrations of the significant impact of raw waveform input data on model performance. Conclusions: This study highlights the proposed dataset as a unique resource to foster progress towards measurable progress in the domain of algorithmic decision support in emergency care. The presented multimodal baseline models showcase the potential of diagnostic decision support in the field and provide strong incentives for including raw waveform data.
Authors: Qingqing Long, Yuchen Yan, Peiyan Zhang, Chen Fang, Wentao Cui, Zhiyuan Ning, Meng Xiao, Ning Cao, Xiao Luo, Lingjun Xu, Shiyue Jiang, Zheng Fang, Chong Chen, Xian-Sheng Hua, Yuanchun Zhou
Abstract: Large-scale "pre-train and prompt learning" paradigms have demonstrated remarkable adaptability, enabling broad applications across diverse domains such as question answering, image recognition, and multimodal retrieval. This approach fully leverages the potential of large-scale pre-trained models, reducing downstream data requirements and computational costs while enhancing model applicability across various tasks. Graphs, as versatile data structures that capture relationships between entities, play pivotal roles in fields such as social network analysis, recommender systems, and biological graphs. Despite the success of pre-train and prompt learning paradigms in Natural Language Processing (NLP) and Computer Vision (CV), their application in graph domains remains nascent. In graph-structured data, not only do the node and edge features often have disparate distributions, but the topological structures also differ significantly. This diversity in graph data can lead to incompatible patterns or gaps between pre-training and fine-tuning on downstream graphs. We aim to bridge this gap by summarizing methods for alleviating these disparities. This includes exploring prompt design methodologies, comparing related techniques, assessing application scenarios and datasets, and identifying unresolved problems and challenges. This survey categorizes over 100 relevant works in this field, summarizing general design principles and the latest applications, including text-attributed graphs, molecules, proteins, and recommendation systems. Through this extensive review, we provide a foundational understanding of graph prompt learning, aiming to impact not only the graph mining community but also the broader Artificial General Intelligence (AGI) community.
Authors: Muhammad Arbab Arshad, Pallavi Kandanur, Saurabh Sonawani, Laiba Batool, Muhammad Umar Habib
Abstract: This study analyzes the Ames Housing Dataset using CatBoost and LightGBM models to explore feature importance and causal relationships in housing price prediction. We examine the correlation between SHAP values and EconML predictions, achieving high accuracy in price forecasting. Our analysis reveals a moderate Spearman rank correlation of 0.48 between SHAP-based feature importance and causally significant features, highlighting the complexity of aligning predictive modeling with causal understanding in housing market analysis. Through extensive causal analysis, including heterogeneity exploration and policy tree interpretation, we provide insights into how specific features like porches impact housing prices across various scenarios. This work underscores the need for integrated approaches that combine predictive power with causal insights in real estate valuation, offering valuable guidance for stakeholders in the industry.
Authors: Lorenzo Bini, Marco Sorbi, Stephane Marchand-Maillet
Abstract: Graph Neural Networks (GNNs) have become increasingly popular for effectively modeling data with graph structures. Recently, attention mechanisms have been integrated into GNNs to improve their ability to capture complex patterns. This paper presents the first comprehensive study revealing a critical, unexplored consequence of this integration: the emergence of Massive Activations (MAs) within attention layers. We introduce a novel method for detecting and analyzing MAs, focusing on edge features in different graph transformer architectures. Our study assesses various GNN models using benchmark datasets, including ZINC, TOX21, and PROTEINS. Key contributions include (1) establishing the direct link between attention mechanisms and MAs generation in GNNs, (2) developing a robust definition and detection method for MAs based on activation ratio distributions, (3) introducing the Explicit Bias Term (EBT) as a potential countermeasure and exploring it as an adversarial framework to assess models robustness based on the presence or absence of MAs. Our findings highlight the prevalence and impact of attention-induced MAs across different architectures, such as GraphTransformer, GraphiT, and SAN. The study reveals the complex interplay between attention mechanisms, model architecture, dataset characteristics, and MAs emergence, providing crucial insights for developing more robust and reliable graph models.
Authors: Jahyun Koo, Dahoon Park, Sangwoo Jung, Jaeha Kung
Abstract: To overcome the burden on the memory size and bandwidth due to ever-increasing size of large language models (LLMs), aggressive weight quantization has been recently studied, while lacking research on quantizing activations. In this paper, we present a hardware-software co-design method that results in an energy-efficient LLM accelerator, named OPAL, for generation tasks. First of all, a novel activation quantization method that leverages the microscaling data format while preserving several outliers per sub-tensor block (e.g., four out of 128 elements) is proposed. Second, on top of preserving outliers, mixed precision is utilized that sets 5-bit for inputs to sensitive layers in the decoder block of an LLM, while keeping inputs to less sensitive layers to 3-bit. Finally, we present the OPAL hardware architecture that consists of FP units for handling outliers and vectorized INT multipliers for dominant non-outlier related operations. In addition, OPAL uses log2-based approximation on softmax operations that only requires shift and subtraction to maximize power efficiency. As a result, we are able to improve the energy efficiency by 1.6~2.2x, and reduce the area by 2.4~3.1x with negligible accuracy loss, i.e., <1 perplexity increase.
Authors: Woojin Chae, Dabeen Lee
Abstract: This paper proposes a computationally tractable algorithm for learning infinite-horizon average-reward linear Markov decision processes (MDPs) and linear mixture MDPs under the Bellman optimality condition. While guaranteeing computational efficiency, our algorithm for linear MDPs achieves the best-known regret upper bound of $\widetilde{\mathcal{O}}(d^{3/2}\mathrm{sp}(v^*)\sqrt{T})$ over $T$ time steps where $\mathrm{sp}(v^*)$ is the span of the optimal bias function $v^*$ and $d$ is the dimension of the feature mapping. For linear mixture MDPs, our algorithm attains a regret bound of $\widetilde{\mathcal{O}}(d\cdot\mathrm{sp}(v^*)\sqrt{T})$. The algorithm applies novel techniques to control the covering number of the value function class and the span of optimistic estimators of the value function, which is of independent interest.
Authors: Slimane Larabi
Abstract: In this paper, we introduce the gated perceptron, an enhancement of the conventional perceptron, which incorporates an additional input computed as the product of the existing inputs. This allows the perceptron to capture non-linear interactions between features, significantly improving its ability to classify and regress on complex datasets. We explore its application in both linear and non-linear regression tasks using the Iris dataset, as well as binary and multi-class classification problems, including the PIMA Indian dataset and Breast Cancer Wisconsin dataset. Our results demonstrate that the gated perceptron can generate more distinct decision regions compared to traditional perceptrons, enhancing its classification capabilities, particularly in handling non-linear data. Performance comparisons show that the gated perceptron competes with state-of-the-art classifiers while maintaining a simple architecture.
Authors: Naheed Anjum Arafat, Debabrota Basu, Yulia Gel, Yuzhou Chen
Abstract: Capitalizing on the intuitive premise that shape characteristics are more robust to perturbations, we bridge adversarial graph learning with the emerging tools from computational topology, namely, persistent homology representations of graphs. We introduce the concept of witness complex to adversarial analysis on graphs, which allows us to focus only on the salient shape characteristics of graphs, yielded by the subset of the most essential nodes (i.e., landmarks), with minimal loss of topological information on the whole graph. The remaining nodes are then used as witnesses, governing which higher-order graph substructures are incorporated into the learning process. Armed with the witness mechanism, we design Witness Graph Topological Layer (WGTL), which systematically integrates both local and global topological graph feature representations, the impact of which is, in turn, automatically controlled by the robust regularized topological loss. Given the attacker's budget, we derive the important stability guarantees of both local and global topology encodings and the associated robust topological loss. We illustrate the versatility and efficiency of WGTL by its integration with five GNNs and three existing non-topological defense mechanisms. Our extensive experiments across six datasets demonstrate that WGTL boosts the robustness of GNNs across a range of perturbations and against a range of adversarial attacks, leading to relative gains of up to 18%.
Authors: Rongting Zhang, Martin Bertran, Aaron Roth
Abstract: Large Language Models (LLMs) have the promise to revolutionize computing broadly, but their complexity and extensive training data also expose significant privacy vulnerabilities. One of the simplest privacy risks associated with LLMs is their susceptibility to membership inference attacks (MIAs), wherein an adversary aims to determine whether a specific data point was part of the model's training set. Although this is a known risk, state of the art methodologies for MIAs rely on training multiple computationally costly shadow models, making risk evaluation prohibitive for large models. Here we adapt a recent line of work which uses quantile regression to mount membership inference attacks; we extend this work by proposing a low-cost MIA that leverages an ensemble of small quantile regression models to determine if a document belongs to the model's training set or not. We demonstrate the effectiveness of this approach on fine-tuned LLMs of varying families (OPT, Pythia, Llama) and across multiple datasets. Across all scenarios we obtain comparable or improved accuracy compared to state of the art shadow model approaches, with as little as 6% of their computation budget. We demonstrate increased effectiveness across multi-epoch trained target models, and architecture miss-specification robustness, that is, we can mount an effective attack against a model using a different tokenizer and architecture, without requiring knowledge on the target model.
Authors: Mor Oren, Vered Paslev, Wasim Huleihel
Abstract: In this paper, we study the task of detecting the edge dependency between two weighted random graphs. We formulate this task as a simple hypothesis testing problem, where under the null hypothesis, the two observed graphs are statistically independent, whereas under the alternative, the edges of one graph are dependent on the edges of a uniformly and randomly vertex-permuted version of the other graph. For general edge-weight distributions, we establish thresholds at which optimal testing becomes information-theoretically possible or impossible, as a function of the total number of nodes in the observed graphs and the generative distributions of the weights. Finally, we identify a statistical-computational gap, and present evidence suggesting that this gap is inherent using the framework of low-degree polynomials.
Authors: Agniv Sharma, Jonas Geiping
Abstract: Transformers are widely used across various applications, many of which yield sparse or partially filled attention matrices. Examples include attention masks designed to reduce the quadratic complexity of attention, sequence packing techniques, and recent innovations like tree masking for fast validation in MEDUSA. Despite the inherent sparsity in these matrices, the state-of-the-art algorithm Flash Attention still processes them with quadratic complexity as though they were dense. In this paper, we introduce Binary Block Masking, a highly efficient modification that enhances Flash Attention by making it mask-aware. We further propose two optimizations: one tailored for masks with contiguous non-zero patterns and another for extremely sparse masks. Our experiments on attention masks derived from real-world scenarios demonstrate up to a 9x runtime improvement. The implementation will be publicly released to foster further research and application.
Authors: Jon Saad-Falcon, Adrian Gamarra Lafuente, Shlok Natarajan, Nahum Maru, Hristo Todorov, Etash Guha, E. Kelly Buchanan, Mayee Chen, Neel Guha, Christopher R\'e, Azalia Mirhoseini
Abstract: Inference-time techniques are emerging as highly effective tools to increase large language model (LLM) capabilities. However, there is still limited understanding of the best practices for developing systems that combine inference-time techniques with one or more LLMs, with challenges including: (1) effectively allocating inference compute budget, (2) understanding the interactions between different combinations of inference-time techniques and their impact on downstream performance, and 3) efficiently searching over the large space of model choices, inference-time techniques, and their compositions. To address these challenges, we introduce Archon, an automated framework for designing inference-time architectures. Archon defines an extensible design space, encompassing methods such as generation ensembling, multi-sampling, ranking, fusion, critiquing, verification, and unit testing. It then transforms the problem of selecting and combining LLMs and inference-time techniques into a hyperparameter optimization objective. To optimize this objective, we introduce automated Inference-Time Architecture Search (ITAS) algorithms. Given target benchmark(s), an inference compute budget, and available LLMs, ITAS outputs optimized architectures. We evaluate Archon architectures across a wide range of instruction-following and reasoning benchmarks, including MT-Bench, Arena-Hard-Auto, AlpacaEval 2.0, MixEval, MixEval Hard, MATH, and CodeContests. We show that automatically designed inference-time architectures by Archon outperform strong models such as GPT-4o and Claude 3.5 Sonnet on these benchmarks, achieving an average increase of 14.1 and 10.3 percentage points with all-source models and open-source models, respectively. We make our code and datasets available publicly on Github: https://github.com/ScalingIntelligence/Archon.
Authors: Damir Filipovic, Michael Multerer, Paul Schneider
Abstract: We develop a new framework for estimating joint probability distributions using tensor product reproducing kernel Hilbert spaces (RKHS). Our framework accommodates a low-dimensional, normalized and positive model of a Radon--Nikodym derivative, which we estimate from sample sizes of up to several millions, alleviating the inherent limitations of RKHS modeling. Well-defined normalized and positive conditional distributions are natural by-products to our approach. Our proposal is fast to compute and accommodates learning problems ranging from prediction to classification. Our theoretical findings are supplemented by favorable numerical results.
Authors: Arne Schneuing, Charles Harris, Yuanqi Du, Kieran Didi, Arian Jamasb, Ilia Igashov, Weitao Du, Carla Gomes, Tom Blundell, Pietro Lio, Max Welling, Michael Bronstein, Bruno Correia
Abstract: Structure-based drug design (SBDD) aims to design small-molecule ligands that bind with high affinity and specificity to pre-determined protein targets. Generative SBDD methods leverage structural data of drugs in complex with their protein targets to propose new drug candidates. These approaches typically place one atom at a time in an autoregressive fashion using the binding pocket as well as previously added ligand atoms as context in each step. Recently a surge of diffusion generative models has entered this domain which hold promise to capture the statistical properties of natural ligands more faithfully. However, most existing methods focus exclusively on bottom-up de novo design of compounds or tackle other drug development challenges with task-specific models. The latter requires curation of suitable datasets, careful engineering of the models and retraining from scratch for each task. Here we show how a single pre-trained diffusion model can be applied to a broader range of problems, such as off-the-shelf property optimization, explicit negative design, and partial molecular design with inpainting. We formulate SBDD as a 3D-conditional generation problem and present DiffSBDD, an SE(3)-equivariant diffusion model that generates novel ligands conditioned on protein pockets. Our in silico experiments demonstrate that DiffSBDD captures the statistics of the ground truth data effectively. Furthermore, we show how additional constraints can be used to improve the generated drug candidates according to a variety of computational metrics. These results support the assumption that diffusion models represent the complex distribution of structural data more accurately than previous methods, and are able to incorporate additional design objectives and constraints changing nothing but the sampling strategy.
Authors: Sloan Nietert, Rachel Cummings, Ziv Goldfeld
Abstract: We study the problem of robust distribution estimation under the Wasserstein distance, a popular discrepancy measure between probability distributions rooted in optimal transport (OT) theory. Given $n$ samples from an unknown distribution $\mu$, of which $\varepsilon n$ are adversarially corrupted, we seek an estimate for $\mu$ with minimal Wasserstein error. To address this task, we draw upon two frameworks from OT and robust statistics: partial OT (POT) and minimum distance estimation (MDE). We prove new structural properties for POT and use them to show that MDE under a partial Wasserstein distance achieves the minimax-optimal robust estimation risk in many settings. Along the way, we derive a novel dual form for POT that adds a sup-norm penalty to the classic Kantorovich dual for standard OT. Since the popular Wasserstein generative adversarial network (WGAN) framework implements Wasserstein MDE via Kantorovich duality, our penalized dual enables large-scale generative modeling with contaminated datasets via an elementary modification to WGAN. Numerical experiments demonstrating the efficacy of our approach in mitigating the impact of adversarial corruptions are provided.
Authors: Xiaoqian Liu, Xu Han, Eric C. Chi, Boaz Nadler
Abstract: In 1-bit matrix completion, the aim is to estimate an underlying low-rank matrix from a partial set of binary observations. We propose a novel method for 1-bit matrix completion called Majorization-Minimization Gauss-Newton (MMGN). Our method is based on the majorization-minimization principle, which converts the original optimization problem into a sequence of standard low-rank matrix completion problems. We solve each of these sub-problems by a factorization approach that explicitly enforces the assumed low-rank structure and then apply a Gauss-Newton method. Using simulations and a real data example, we illustrate that in comparison to existing 1-bit matrix completion methods, MMGN outputs comparable if not more accurate estimates. In addition, it is often significantly faster, and less sensitive to the spikiness of the underlying matrix. In comparison with three standard generic optimization approaches that directly minimize the original objective, MMGN also exhibits a clear computational advantage, especially when the fraction of observed entries is small.
Authors: Mark Sellke
Abstract: We advance the study of incentivized bandit exploration, in which arm choices are viewed as recommendations and are required to be Bayesian incentive compatible. Recent work has shown under certain independence assumptions that after collecting enough initial samples, the popular Thompson sampling algorithm becomes incentive compatible. We give an analog of this result for linear bandits, where the independence of the prior is replaced by a natural convexity condition. This opens up the possibility of efficient and regret-optimal incentivized exploration in high-dimensional action spaces. In the semibandit model, we also improve the sample complexity for the pre-Thompson sampling phase of initial data collection.
Authors: Luca Anzalone, Simranjit Singh Chhibra, Benedikt Maier, Nadezda Chernyavskaya, Maurizio Pierini
Abstract: We present a family of conditional dual auto-encoders (CoDAEs) for generic and model-independent new physics searches at colliders. New physics signals, which arise from new types of particles and interactions, are considered in our study as anomalies causing deviations in data with respect to expected background events. In this work, we perform a normal-only anomaly detection, which employs only background samples, to search for manifestations of a dark version of strong force applying (variational) auto-encoders on raw detector images, which are large and highly sparse, without leveraging any physics-based pre-processing or strong assumption on the signals. The proposed CoDAE has a dual-encoder design, which is general and can learn an auxiliary yet compact latent space through spatial conditioning, showing a neat improvement over competitive physics-based baselines and related approaches, therefore also reducing the gap with fully supervised models. It is the first time an unsupervised model is shown to exhibit excellent discrimination against multiple dark shower models, illustrating the suitability of this method as an accurate, fast, model-independent algorithm to deploy, e.g., in the real-time event triggering systems of Large Hadron Collider experiments such as ATLAS and CMS.
Authors: Marcel Hirt, Domenico Campolo, Victoria Leong, Juan-Pablo Ortega
Abstract: Devising deep latent variable models for multi-modal data has been a long-standing theme in machine learning research. Multi-modal Variational Autoencoders (VAEs) have been a popular generative model class that learns latent representations that jointly explain multiple modalities. Various objective functions for such models have been suggested, often motivated as lower bounds on the multi-modal data log-likelihood or from information-theoretic considerations. To encode latent variables from different modality subsets, Product-of-Experts (PoE) or Mixture-of-Experts (MoE) aggregation schemes have been routinely used and shown to yield different trade-offs, for instance, regarding their generative quality or consistency across multiple modalities. In this work, we consider a variational objective that can tightly approximate the data log-likelihood. We develop more flexible aggregation schemes that avoid the inductive biases in PoE or MoE approaches by combining encoded features from different modalities based on permutation-invariant neural networks. Our numerical experiments illustrate trade-offs for multi-modal variational objectives and various aggregation schemes. We show that our variational objective and more flexible aggregation models can become beneficial when one wants to approximate the true joint distribution over observed modalities and latent variables in identifiable models.
Authors: Pascal K\"undig, Fabio Sigrist
Abstract: Latent Gaussian process (GP) models are flexible probabilistic non-parametric function models. Vecchia approximations are accurate approximations for GPs to overcome computational bottlenecks for large data, and the Laplace approximation is a fast method with asymptotic convergence guarantees to approximate marginal likelihoods and posterior predictive distributions for non-Gaussian likelihoods. Unfortunately, the computational complexity of combined Vecchia-Laplace approximations grows faster than linearly in the sample size when used in combination with direct solver methods such as the Cholesky decomposition. Computations with Vecchia-Laplace approximations can thus become prohibitively slow precisely when the approximations are usually the most accurate, i.e., on large data sets. In this article, we present iterative methods to overcome this drawback. Among other things, we introduce and analyze several preconditioners, derive new convergence results, and propose novel methods for accurately approximating predictive variances. We analyze our proposed methods theoretically and in experiments with simulated and real-world data. In particular, we obtain a speed-up of an order of magnitude compared to Cholesky-based calculations and a threefold increase in prediction accuracy in terms of the continuous ranked probability score compared to a state-of-the-art method on a large satellite data set. All methods are implemented in a free C++ software library with high-level Python and R packages.
Authors: Francesco Paissan, Luca Della Libera, Zhepei Wang, Mirco Ravanelli, Paris Smaragdis, Cem Subakan
Abstract: In this paper, we explore audio-editing with non-rigid text edits. We show that the proposed editing pipeline is able to create audio edits that remain faithful to the input audio. We explore text prompts that perform addition, style transfer, and in-painting. We quantitatively and qualitatively show that the edits are able to obtain results which outperform Audio-LDM, a recently released text-prompted audio generation model. Qualitative inspection of the results points out that the edits given by our approach remain more faithful to the input audio in terms of keeping the original onsets and offsets of the audio events.
Authors: Szymon Antoniak, Micha{\l} Krutul, Maciej Pi\'oro, Jakub Krajewski, Jan Ludziejewski, Kamil Ciebiera, Krystian Kr\'ol, Tomasz Odrzyg\'o\'zd\'z, Marek Cygan, Sebastian Jaszczur
Abstract: Mixture of Experts (MoE) models based on Transformer architecture are pushing the boundaries of language and vision tasks. The allure of these models lies in their ability to substantially increase the parameter count without a corresponding increase in FLOPs. Most widely adopted MoE models are discontinuous with respect to their parameters - often referred to as sparse. At the same time, existing continuous MoE designs either lag behind their sparse counterparts or are incompatible with autoregressive decoding. Motivated by the observation that the adaptation of fully continuous methods has been an overarching trend in deep learning, we develop Mixture of Tokens (MoT), a simple, continuous architecture that is capable of scaling the number of parameters similarly to sparse MoE models. Unlike conventional methods, MoT assigns mixtures of tokens from different examples to each expert. This architecture is fully compatible with autoregressive training and generation. Our best models not only achieve a 3x increase in training speed over dense Transformer models in language pretraining but also match the performance of state-of-the-art MoE architectures. Additionally, a close connection between MoT and MoE is demonstrated through a novel technique we call transition tuning.
Authors: Francesco Paissan, Elisabetta Farella
Abstract: Contrastive Language-Audio Pretraining (CLAP) became of crucial importance in the field of audio and speech processing. Its employment ranges from sound event detection to text-to-audio generation. However, one of the main limitations is the considerable amount of data required in the training process and the overall computational complexity during inference. This paper investigates how we can reduce the complexity of contrastive language-audio pre-trained models, yielding an efficient model that we call tinyCLAP. We derive an unimodal distillation loss from first principles and explore how the dimensionality of the shared, multimodal latent space can be reduced via pruning. TinyCLAP uses only 6% of the original Microsoft CLAP parameters with a minimal reduction (less than 5%) in zero-shot classification performance across the three sound event detection datasets on which it was tested
Authors: Yinwei Dai, Rui Pan, Anand Iyer, Kai Li, Ravi Netravali
Abstract: Machine learning (ML) inference platforms are tasked with balancing two competing goals: ensuring high throughput given many requests, and delivering low-latency responses to support interactive applications. Unfortunately, existing platform knobs (e.g., batch sizes) fail to ease this fundamental tension, and instead only enable users to harshly trade off one property for the other. This paper explores an alternate strategy to taming throughput-latency tradeoffs by changing the granularity at which inference is performed. We present Apparate, a system that automatically applies and manages early exits (EEs) in ML models, whereby certain inputs can exit with results at intermediate layers. To cope with the time-varying overhead and accuracy challenges that EEs bring, Apparate repurposes exits to provide continual feedback that powers several novel runtime monitoring and adaptation strategies. Apparate lowers median response latencies by 40.5--91.5% and 10.0--24.2% for diverse CV and NLP classification workloads, and median time-per-token latencies by 22.6--77.9% for generative scenarios, without affecting throughputs or violating tight accuracy constraints.
Authors: Thibaut Loiseau, Tuan-Hung Vu, Mickael Chen, Patrick P\'erez, Matthieu Cord
Abstract: Assessing the robustness of perception models to covariate shifts and their ability to detect out-of-distribution (OOD) inputs is crucial for safety-critical applications such as autonomous vehicles. By nature of such applications, however, the relevant data is difficult to collect and annotate. In this paper, we show for the first time how synthetic data can be specifically generated to assess comprehensively the real-world reliability of semantic segmentation models. By fine-tuning Stable Diffusion with only in-domain data, we perform zero-shot generation of visual scenes in OOD domains or inpainted with OOD objects. This synthetic data is employed to evaluate the robustness of pretrained segmenters, thereby offering insights into their performance when confronted with real edge cases. Through extensive experiments, we demonstrate a high correlation between the performance of models when evaluated on our synthetic OOD data and when evaluated on real OOD inputs, showing the relevance of such virtual testing. Furthermore, we demonstrate how our approach can be utilized to enhance the calibration and OOD detection capabilities of segmenters. Code and data are made public.
Authors: Tavis Shore, Simon Hadfield, Oscar Mendez
Abstract: Cross-view image matching for geo-localisation is a challenging problem due to the significant visual difference between aerial and ground-level viewpoints. The method provides localisation capabilities from geo-referenced images, eliminating the need for external devices or costly equipment. This enhances the capacity of agents to autonomously determine their position, navigate, and operate effectively in GNSS-denied environments. Current research employs a variety of techniques to reduce the domain gap such as applying polar transforms to aerial images or synthesising between perspectives. However, these approaches generally rely on having a 360{\deg} field of view, limiting real-world feasibility. We propose BEV-CV, an approach introducing two key novelties with a focus on improving the real-world viability of cross-view geo-localisation. Firstly bringing ground-level images into a semantic Birds-Eye-View before matching embeddings, allowing for direct comparison with aerial image representations. Secondly, we adapt datasets into application realistic format - limited Field-of-View images aligned to vehicle direction. BEV-CV achieves state-of-the-art recall accuracies, improving Top-1 rates of 70{\deg} crops of CVUSA and CVACT by 23% and 24% respectively. Also decreasing computational requirements by reducing floating point operations to below previous works, and decreasing embedding dimensionality by 33% - together allowing for faster localisation capabilities.
Authors: Yaojia Lv, Haojie Pan, Zekun Wang, Jiafeng Liang, Yuanxing Liu, Ruiji Fu, Ming Liu, Zhongyuan Wang, Bing Qin
Abstract: Cognitive dynamics are pivotal to advance human understanding of the world. Recent advancements in large language models (LLMs) reveal their potential for cognitive simulation. However, these LLM-based cognitive studies primarily focus on static modeling, overlooking the dynamic nature of cognition. To bridge this gap, we propose the concept of the cognitive dynamics of LLMs and present a corresponding task with the inspiration of longitudinal studies. Towards the task, we develop CogBench, a novel benchmark to assess the cognitive dynamics of LLMs and validate it through participant surveys. We also design two evaluation metrics for CogBench, including Authenticity and Rationality. Recognizing the inherent static nature of LLMs, we introduce CogGPT for the task, which features an innovative iterative cognitive mechanism aimed at enhancing lifelong cognitive dynamics. Empirical results demonstrate the superiority of CogGPT over existing methods, particularly in its ability to facilitate role-specific cognitive dynamics under continuous information flows.
Authors: Baoxiong Jia, Yixin Chen, Huangyue Yu, Yan Wang, Xuesong Niu, Tengyu Liu, Qing Li, Siyuan Huang
Abstract: 3D vision-language grounding, which focuses on aligning language with the 3D physical environment, stands as a cornerstone in the development of embodied agents. In comparison to recent advancements in the 2D domain, grounding language in 3D scenes faces several significant challenges: (i) the inherent complexity of 3D scenes due to the diverse object configurations, their rich attributes, and intricate relationships; (ii) the scarcity of paired 3D vision-language data to support grounded learning; and (iii) the absence of a unified learning framework to distill knowledge from grounded 3D data. In this work, we aim to address these three major challenges in 3D vision-language by examining the potential of systematically upscaling 3D vision-language learning in indoor environments. We introduce the first million-scale 3D vision-language dataset, SceneVerse, encompassing about 68K 3D indoor scenes and comprising 2.5M vision-language pairs derived from both human annotations and our scalable scene-graph-based generation approach. We demonstrate that this scaling allows for a unified pre-training framework, Grounded Pre-training for Scenes (GPS), for 3D vision-language learning. Through extensive experiments, we showcase the effectiveness of GPS by achieving state-of-the-art performance on all existing 3D visual grounding benchmarks. The vast potential of SceneVerse and GPS is unveiled through zero-shot transfer experiments in the challenging 3D vision-language tasks. Project website: https://scene-verse.github.io.
Authors: Xinda Qi, Dong Chen, Zhaojian Li, Xiaobo Tan
Abstract: In this paper, we propose a novel technique, Back-stepping Experience Replay (BER), that is compatible with arbitrary off-policy reinforcement learning (RL) algorithms. BER aims to enhance learning efficiency in systems with approximate reversibility, reducing the need for complex reward shaping. The method constructs reversed trajectories using back-stepping transitions to reach random or fixed targets. Interpretable as a bi-directional approach, BER addresses inaccuracies in back-stepping transitions through a distillation of the replay experience during learning. Given the intricate nature of soft robots and their complex interactions with environments, we present an application of BER in a model-free RL approach for the locomotion and navigation of a soft snake robot, which is capable of serpentine motion enabled by anisotropic friction between the body and ground. In addition, a dynamic simulator is developed to assess the effectiveness and efficiency of the BER algorithm, in which the robot demonstrates successful learning (reaching a 100% success rate) and adeptly reaches random targets, achieving an average speed 48% faster than that of the best baseline approach.
Authors: Xinyue Chen, Pengyu Gao, Jiangjiang Song, Xiaoyang Tan
Abstract: Retrieval-augmented generation (RAG) has rapidly advanced the language model field, particularly in question-answering (QA) systems. By integrating external documents during the response generation phase, RAG significantly enhances the accuracy and reliability of language models. This method elevates the quality of responses and reduces the frequency of hallucinations, where the model generates incorrect or misleading information. However, these methods exhibit limited retrieval accuracy when faced with numerous indistinguishable documents, presenting notable challenges in their practical application. In response to these emerging challenges, we present HiQA, an advanced multi-document question-answering (MDQA) framework that integrates cascading metadata into content and a multi-route retrieval mechanism. We also release a benchmark called MasQA to evaluate and research in MDQA. Finally, HiQA demonstrates the state-of-the-art performance in multi-document environments.
Authors: Xinyi Wang, Qing Zhao, Lang Tong
Abstract: This paper introduces a generative AI approach to probabilistic forecasting of real-time electricity market signals, including locational marginal prices, interregional price spreads, and demand-supply imbalances. We present WIAE-GPF, a Weak Innovation AutoEncoder-based Generative Probabilistic Forecasting architecture that generates future samples of multivariate time series. Unlike traditional black-box models, WIAE-GPF offers interpretability through the Wiener-Kallianpur innovation representation for nonparametric time series, making it a nonparametric generalization of the Wiener/Kalman filter-based forecasting. A novel learning algorithm with structural convergence guarantees is proposed, ensuring that, under ideal training conditions, the generated forecast samples match the ground truth conditional probability distribution. Extensive tests using publicly available data from U.S. independent system operators under various point and probabilistic forecasting metrics demonstrate that WIAE-GPF consistently outperforms classical methods and cutting-edge machine learning techniques.
Authors: Yan Wang, Lihao Wang, Yuning Shen, Yiqun Wang, Huizhuo Yuan, Yue Wu, Quanquan Gu
Abstract: The conformational landscape of proteins is crucial to understanding their functionality in complex biological processes. Traditional physics-based computational methods, such as molecular dynamics (MD) simulations, suffer from rare event sampling and long equilibration time problems, hindering their applications in general protein systems. Recently, deep generative modeling techniques, especially diffusion models, have been employed to generate novel protein conformations. However, existing score-based diffusion methods cannot properly incorporate important physical prior knowledge to guide the generation process, causing large deviations in the sampled protein conformations from the equilibrium distribution. In this paper, to overcome these limitations, we propose a force-guided SE(3) diffusion model, ConfDiff, for protein conformation generation. By incorporating a force-guided network with a mixture of data-based score models, ConfDiff can generate protein conformations with rich diversity while preserving high fidelity. Experiments on a variety of protein conformation prediction tasks, including 12 fast-folding proteins and the Bovine Pancreatic Trypsin Inhibitor (BPTI), demonstrate that our method surpasses the state-of-the-art method.
Authors: Matteo Cederle, Luca Vittorio Piron, Marina Ceccon, Federico Chiariotti, Alessandro Fabris, Marco Fabris, Gian Antonio Susto
Abstract: As Machine Learning grows in popularity across various fields, equity has become a key focus for the AI community. However fairness-oriented approaches are still underexplored in smart mobility. Addressing this gap, our study investigates the balance between performance optimization and algorithmic fairness in shared micromobility services providing a novel framework based on Reinforcement Learning. Exploiting Q-Learning, the proposed methodology achieves equitable outcomes in terms of the Gini index across different areas characterized by their distance from central hubs. Through vehicle rebalancing, the provided scheme maximizes operator performance while ensuring fairness principles for users, reducing iniquity by up to 80% while only increasing costs by 30% (w.r.t. applying no equity adjustment). A case study with synthetic data validates our insights and highlights the importance of fairness in urban micromobility.
Authors: Kyla Levin, Nicolas van Kempen, Emery D. Berger, Stephen N. Freund
Abstract: Debugging is a critical but challenging task for programmers. This paper proposes ChatDBG, an AI-powered debugging assistant. ChatDBG integrates large language models (LLMs) to significantly enhance the capabilities and user-friendliness of conventional debuggers. ChatDBG lets programmers engage in a collaborative dialogue with the debugger, allowing them to pose complex questions about program state, perform root cause analysis for crashes or assertion failures, and explore open-ended queries like `why is x null?'. To handle these queries, ChatDBG grants the LLM autonomy to "take the wheel": it can act as an independent agent capable of querying and controlling the debugger to navigate through stacks and inspect program state. It then reports its findings and yields back control to the programmer. Our ChatDBG prototype integrates with standard debuggers including LLDB and GDB for native code and Pdb for Python. Our evaluation across a diverse set of code, including C/C++ code with known bugs and a suite of Python code including standalone scripts and Jupyter notebooks, demonstrates that ChatDBG can successfully analyze root causes, explain bugs, and generate accurate fixes for a wide range of real-world errors. For the Python programs, a single query led to an actionable bug fix 67% of the time; one additional follow-up query increased the success rate to 85%. ChatDBG has seen rapid uptake; it has already been downloaded roughly 50,000 times.
Authors: Matina Mahdizadeh Sani, Ali Royat, Mahdieh Soleymani Baghshah
Abstract: Deep neural networks have reached remarkable achievements in medical image processing tasks, specifically in classifying and detecting various diseases. However, when confronted with limited data, these networks face a critical vulnerability, often succumbing to overfitting by excessively memorizing the limited information available. This work addresses the challenge mentioned above by improving the supervised contrastive learning method leveraging both image-level labels and domain-specific augmentations to enhance model robustness. This approach integrates self-supervised pre-training with a two-stage supervised contrastive learning strategy. In the first stage, we employ a modified supervised contrastive loss that not only focuses on reducing false negatives but also introduces an elimination effect to address false positives. In the second stage, a relaxing mechanism is introduced that refines positive and negative pairs based on similarity, ensuring that only relevant image representations are aligned. We evaluate our method on the BreakHis dataset, which consists of breast cancer histopathology images, and demonstrate an increase in classification accuracy by 1.45% in the image level, compared to the state-of-the-art method. This improvement corresponds to 93.63% absolute accuracy, highlighting the effectiveness of our approach in leveraging properties of data to learn more appropriate representation space.
Authors: Takaya Tanaka, Yutaka Yamaguti
Abstract: Successive image generation using cyclic transformations is demonstrated by extending the CycleGAN model to transform images among three different categories. Repeated application of the trained generators produces sequences of images that transition among the different categories. The generated image sequences occupy a more limited region of the image space compared with the original training dataset. Quantitative evaluation using precision and recall metrics indicates that the generated images have high quality but reduced diversity relative to the training dataset. Such successive generation processes are characterized as chaotic dynamics in terms of dynamical system theory. Positive Lyapunov exponents estimated from the generated trajectories confirm the presence of chaotic dynamics, with the Lyapunov dimension of the attractor found to be comparable to the intrinsic dimension of the training data manifold. The results suggest that chaotic dynamics in the image space defined by the deep generative model contribute to the diversity of the generated images, constituting a novel approach for multi-class image generation. This model can be interpreted as an extension of classical associative memory to perform hetero-association among image categories.
Authors: Fazel Arasteh, Mohammed Elmahgiubi, Behzad Khamidehi, Hamidreza Mirkhani, Weize Zhang, Cao Tongtong, Kasra Rezaee
Abstract: The planning problem constitutes a fundamental aspect of the autonomous driving framework. Recent strides in representation learning have empowered vehicles to comprehend their surrounding environments, thereby facilitating the integration of learning-based planning strategies. Among these approaches, Imitation Learning stands out due to its notable training efficiency. However, traditional Imitation Learning methodologies encounter challenges associated with the co-variate shift phenomenon. We propose Validity Learning on Failures, VL(on failure), as a remedy to address this issue. The essence of our method lies in deploying a pre-trained planner across diverse scenarios. Instances where the planner deviates from its immediate objectives, such as maintaining a safe distance from obstacles or adhering to traffic rules, are flagged as failures. The states corresponding to these failures are compiled into a new dataset, termed the failure dataset. Notably, the absence of expert annotations for this data precludes the applicability of standard imitation learning approaches. To facilitate learning from the closed-loop mistakes, we introduce the VL objective which aims to discern valid trajectories within the current environmental context. Experimental evaluations conducted on both reactive CARLA simulation and non-reactive log-replay simulations reveal substantial enhancements in closed-loop metrics such as \textit{Score, Progress}, and Success Rate, underscoring the effectiveness of the proposed methodology. Further evaluations against the Bench2Drive benchmark demonstrate that VL(on failure) outperforms the state-of-the-art methods by a large margin.
Authors: Tao Ge, Xin Chan, Xiaoyang Wang, Dian Yu, Haitao Mi, Dong Yu
Abstract: We propose a novel persona-driven data synthesis methodology that leverages various perspectives within a large language model (LLM) to create diverse synthetic data. To fully exploit this methodology at scale, we introduce Persona Hub -- a collection of 1 billion diverse personas automatically curated from web data. These 1 billion personas (~13% of the world's total population), acting as distributed carriers of world knowledge, can tap into almost every perspective encapsulated within the LLM, thereby facilitating the creation of diverse synthetic data at scale for various scenarios. By showcasing Persona Hub's use cases in synthesizing high-quality mathematical and logical reasoning problems, instructions (i.e., user prompts), knowledge-rich texts, game NPCs and tools (functions) at scale, we demonstrate persona-driven data synthesis is versatile, scalable, flexible, and easy to use, potentially driving a paradigm shift in synthetic data creation and applications in practice, which may have a profound impact on LLM research and development.
Authors: Jiawei Wang, Liping Yuan, Yuchen Zhang, Haomiao Sun
Abstract: Generating fine-grained video descriptions is a fundamental challenge in video understanding. In this work, we introduce Tarsier, a family of large-scale video-language models designed to generate high-quality video descriptions. Tarsier employs CLIP-ViT to encode frames separately and then uses an LLM to model temporal relationships. Despite its simple architecture, we demonstrate that with a meticulously designed two-stage training procedure, the Tarsier models exhibit substantially stronger video description capabilities than any existing open-source model, showing a $+51.4\%$ advantage in human side-by-side evaluation over the strongest model. Additionally, they are comparable to state-of-the-art proprietary models, with a $+12.3\%$ advantage against GPT-4V and a $-6.7\%$ disadvantage against Gemini 1.5 Pro. When upgraded to Tarsier2 by building upon SigLIP and Qwen2-7B, it further improves significantly with a $+4.8\%$ advantage against GPT-4o. Besides video description, Tarsier proves to be a versatile generalist model, achieving new state-of-the-art results across nine public benchmarks, including multi-choice VQA, open-ended VQA, and zero-shot video captioning. Our second contribution is the introduction of a new benchmark -- DREAM-1K (https://tarsier-vlm.github.io/) for evaluating video description models, consisting of a new challenging dataset featuring videos from diverse sources and varying complexity, along with an automatic method specifically designed to assess the quality of fine-grained video descriptions. We make our models and evaluation benchmark publicly available at https://github.com/bytedance/tarsier.
URLs: https://tarsier-vlm.github.io/), https://github.com/bytedance/tarsier.
Authors: Mengjie Qian, Siyuan Tang, Rao Ma, Kate M. Knill, Mark J. F. Gales
Abstract: Foundation ASR models often support many languages, e.g. 100 languages in Whisper. However, there has been limited work on integrating an additional, typically low-resource, language, while maintaining performance on the original language set. Fine-tuning, while simple, may degrade the accuracy of the original set. We compare three approaches that exploit adaptation parameters: soft language code tuning, train only the language code; soft prompt tuning, train prepended tokens; and LoRA where a small set of additional parameters are optimised. Elastic Weight Consolidation (EWC) offers an alternative compromise with the potential to maintain performance in specific target languages. Results show that direct fine-tuning yields the best performance for the new language but degrades existing language capabilities. EWC can address this issue for specific languages. If only adaptation parameters are used, the language capabilities are maintained but at the cost of performance in the new language.
Authors: Lisanne van Gelderen, Cristian Tejedor-Garc\'ia
Abstract: Parkinson's disease (PD), the second most prevalent neurodegenerative disorder worldwide, frequently presents with early-stage speech impairments. Recent advancements in Artificial Intelligence (AI), particularly deep learning (DL), have significantly enhanced PD diagnosis through the analysis of speech data. Nevertheless, the progress of research is restricted by the limited availability of publicly accessible speech-based PD datasets, primarily due to privacy concerns. The goal of this systematic review is to explore the current landscape of speech-based DL approaches for PD classification, based on 33 scientific works published between January 2020 and March 2024. We discuss their available resources, capabilities, and potential limitations, and issues related to bias, explainability, and privacy. Furthermore, this review provides an overview of publicly accessible speech-based datasets and open-source material for PD. The DL approaches identified are categorized into end-to-end (E2E) learning, transfer learning (TL), and deep acoustic feature extraction (DAFE). Among E2E approaches, Convolutional Neural Networks (CNNs) are prevalent, though Transformers are increasingly popular. E2E approaches face challenges such as limited data and computational resources, especially with Transformers. TL addresses these issues by providing more robust PD diagnosis and better generalizability across languages. DAFE aims to improve the explainability and interpretability of results by examining the specific effects of deep features on both other DL approaches and more traditional machine learning (ML) methods. However, it often underperforms compared to E2E and TL approaches.
Authors: Yiqi Liu, Yuqi Xue, Yu Cheng, Lingxiao Ma, Ziming Miao, Jilong Xue, Jian Huang
Abstract: As AI chips incorporate numerous parallelized cores to scale deep learning (DL) computing, inter-core communication is enabled recently by employing high-bandwidth and low-latency interconnect links on the chip (e.g., Graphcore IPU). It allows each core to directly access the fast scratchpad memory in other cores, which enables new parallel computing paradigms. However, without proper support for the scalable inter-core connections in current DL compilers, it is hard for developers to exploit the benefits of this new architecture. We present T10, the first DL compiler to exploit the inter-core communication bandwidth and distributed on-chip memory on AI chips. To formulate the computation and communication patterns of tensor operators in this new architecture, T10 introduces a distributed tensor abstraction rTensor. T10 maps a DNN model to execution plans with a generalized compute-shift pattern, by partitioning DNN computation into sub-operators and mapping them to cores, so that the cores can exchange data following predictable patterns. T10 makes globally optimized trade-offs between on-chip memory consumption and inter-core communication overhead, selects the best execution plan from a vast optimization space, and alleviates unnecessary inter-core communications. Our evaluation with a real inter-core connected AI chip, the Graphcore IPU, shows up to 3.3$\times$ performance improvement, and scalability support for larger models, compared to state-of-the-art DL compilers and vendor libraries.
Authors: Longbiao Cheng, Ashutosh Pandey, Buye Xu, Tobi Delbruck, Shih-Chii Liu
Abstract: This paper introduces a new Dynamic Gated Recurrent Neural Network (DG-RNN) for compute-efficient speech enhancement models running on resource-constrained hardware platforms. It leverages the slow evolution characteristic of RNN hidden states over steps, and updates only a selected set of neurons at each step by adding a newly proposed select gate to the RNN model. This select gate allows the computation cost of the conventional RNN to be reduced during network inference. As a realization of the DG-RNN, we further propose the Dynamic Gated Recurrent Unit (D-GRU) which does not require additional parameters. Test results obtained from several state-of-the-art compute-efficient RNN-based speech enhancement architectures using the DNS challenge dataset, show that the D-GRU based model variants maintain similar speech intelligibility and quality metrics comparable to the baseline GRU based models even with an average 50% reduction in GRU computes.
Authors: Takanori Fujiwara, Kostiantyn Kucher, Junpeng Wang, Rafael M. Martins, Andreas Kerren, Anders Ynnerman
Abstract: Research in ML4VIS investigates how to use machine learning (ML) techniques to generate visualizations, and the field is rapidly growing with high societal impact. However, as with any computational pipeline that employs ML processes, ML4VIS approaches are susceptible to a range of ML-specific adversarial attacks. These attacks can manipulate visualization generations, causing analysts to be tricked and their judgments to be impaired. Due to a lack of synthesis from both visualization and ML perspectives, this security aspect is largely overlooked by the current ML4VIS literature. To bridge this gap, we investigate the potential vulnerabilities of ML-aided visualizations from adversarial attacks using a holistic lens of both visualization and ML perspectives. We first identify the attack surface (i.e., attack entry points) that is unique in ML-aided visualizations. We then exemplify five different adversarial attacks. These examples highlight the range of possible attacks when considering the attack surface and multiple different adversary capabilities. Our results show that adversaries can induce various attacks, such as creating arbitrary and deceptive visualizations, by systematically identifying input attributes that are influential in ML inferences. Based on our observations of the attack surface characteristics and the attack examples, we underline the importance of comprehensive studies of security issues and defense mechanisms as a call of urgency for the ML4VIS community.
Authors: Zhihao Dou, Xin Hu, Haibo Yang, Zhuqing Liu, Minghong Fang
Abstract: Multi-modal models have gained significant attention due to their powerful capabilities. These models effectively align embeddings across diverse data modalities, showcasing superior performance in downstream tasks compared to their unimodal counterparts. Recent study showed that the attacker can manipulate an image or audio file by altering it in such a way that its embedding matches that of an attacker-chosen targeted input, thereby deceiving downstream models. However, this method often underperforms due to inherent disparities in data from different modalities. In this paper, we introduce CrossFire, an innovative approach to attack multi-modal models. CrossFire begins by transforming the targeted input chosen by the attacker into a format that matches the modality of the original image or audio file. We then formulate our attack as an optimization problem, aiming to minimize the angular deviation between the embeddings of the transformed input and the modified image or audio file. Solving this problem determines the perturbations to be added to the original media. Our extensive experiments on six real-world benchmark datasets reveal that CrossFire can significantly manipulate downstream tasks, surpassing existing attacks. Additionally, we evaluate six defensive strategies against CrossFire, finding that current defenses are insufficient to counteract our CrossFire.
Authors: Thomas Ball, Shuo Chen, Cormac Herley
Abstract: In this paper we explore evaluation of LLM capabilities. We present measurements of GPT-4 performance on several deterministic tasks; each task involves a basic calculation and takes as input parameter some element drawn from a large well-defined population (e.g., count elements in a list, multiply two k-digit numbers, etc). We examine several conditions per-task and perform enough trials so that statistically significant differences can be detected. This allows us to investigate the sensitivity of task-accuracy both to query phrasing and input parameter population. We find that seemingly trivial modifications in the task-prompt or input population can yield differences far larger than can be explained by sampling effects. For example, performance on a simple list-counting task varies with query-phrasing and list-length, but also with list composition (i.e., the thing-to-be-counted) and object frequency (e.g., success when an element accounts for $\approx$ 50\% of a list is different from when it accounts for $\approx$ 70\% etc). We conclude that efforts to quantify LLM capabilities easily succumb to the language-as-fixed-effect fallacy, where experimental observations are improperly generalized beyond what the data supports. A consequence appears to be that intuitions that have been formed based on interactions with humans form a very unreliable guide as to which input modifications should ``make no difference'' to LLM performance.
Authors: Rania Hossam, Ahmed Heakl, Walid Gomaa
Abstract: Traditional fish farming practices often lead to inefficient feeding, resulting in environmental issues and reduced productivity. We developed an innovative system combining computer vision and IoT technologies for precise Tilapia feeding. Our solution uses real-time IoT sensors to monitor water quality parameters and computer vision algorithms to analyze fish size and count, determining optimal feed amounts. A mobile app enables remote monitoring and control. We utilized YOLOv8 for keypoint detection to measure Tilapia weight from length, achieving \textbf{94\%} precision on 3,500 annotated images. Pixel-based measurements were converted to centimeters using depth estimation for accurate feeding calculations. Our method, with data collection mirroring inference conditions, significantly improved results. Preliminary estimates suggest this approach could increase production up to 58 times compared to traditional farms. Our models, code, and dataset are open-source~\footnote{The code, dataset, and models are available upon reasonable request.
Authors: Rasoul Jafari Gohari, Laya Aliahmadipour, Ezat Valipour
Abstract: The world of Machine Learning (ML) has witnessed rapid changes in terms of new models and ways to process users data. The majority of work that has been done is focused on Deep Learning (DL) based approaches. However, with the emergence of new algorithms such as the Tsetlin Machine (TM) algorithm, there is growing interest in exploring alternative approaches that may offer unique advantages in certain domains or applications. One of these domains is Federated Learning (FL), in which users privacy is of utmost importance. Due to its novelty, FL has seen a surge in the incorporation of personalization techniques to enhance model accuracy while maintaining user privacy under personalized conditions. In this work, we propose a novel approach called TPFL: Tsetlin-Personalized Federated Learning, in which models are grouped into clusters based on their confidence towards a specific class. In this way, clustering can benefit from two key advantages. Firstly, clients share only what they are confident about, resulting in the elimination of wrongful weight aggregation among clients whose data for a specific class may have not been enough during the training. This phenomenon is prevalent when the data are non-Independent and Identically Distributed (non-IID). Secondly, by sharing only weights towards a specific class, communication cost is substantially reduced, making TPLF efficient in terms of both accuracy and communication cost. The TPFL results were compared with 6 other baseline methods; namely FedAvg, FedProx, FLIS DC, FLIS HC, IFCA and FedTM. The results demonstrated that TPFL performance better than baseline methods with 98.94% accuracy on MNIST, 98.52% accuracy on FashionMNIST and 91.16% accuracy on FEMNIST dataset.
Authors: Yifan Wang, David Stevens, Pranay Shah, Wenwen Jiang, Miao Liu, Xu Chen, Robert Kuo, Na Li, Boying Gong, Daniel Lee, Jiabo Hu, Ning Zhang, Bob Kamma
Abstract: The growing demand for AI training data has transformed data annotation into a global industry, but traditional approaches relying on human annotators are often time-consuming, labor-intensive, and prone to inconsistent quality. We propose the Model-in-the-Loop (MILO) framework, which integrates AI/ML models into the annotation process. Our research introduces a collaborative paradigm that leverages the strengths of both professional human annotators and large language models (LLMs). By employing LLMs as pre-annotation and real-time assistants, and judges on annotator responses, MILO enables effective interaction patterns between human annotators and LLMs. Three empirical studies on multimodal data annotation demonstrate MILO's efficacy in reducing handling time, improving data quality, and enhancing annotator experiences. We also introduce quality rubrics for flexible evaluation and fine-grained feedback on open-ended annotations. The MILO framework has implications for accelerating AI/ML development, reducing reliance on human annotation alone, and promoting better alignment between human and machine values.
Authors: Hongyu Zhu, Wentao Hu, Sichu Liang, Fangqi Li, Wenwen Wang, Shilin Wang
Abstract: Model extraction aims to create a functionally similar copy from a machine learning as a service (MLaaS) API with minimal overhead, typically for illicit profit or as a precursor to further attacks, posing a significant threat to the MLaaS ecosystem. However, recent studies have shown that model extraction is highly inefficient, particularly when the target task distribution is unavailable. In such cases, even substantially increasing the attack budget fails to produce a sufficiently similar replica, reducing the adversary's motivation to pursue extraction attacks. In this paper, we revisit the elementary design choices throughout the extraction lifecycle. We propose an embarrassingly simple yet dramatically effective algorithm, Efficient and Effective Model Extraction (E3), focusing on both query preparation and training routine. E3 achieves superior generalization compared to state-of-the-art methods while minimizing computational costs. For instance, with only 0.005 times the query budget and less than 0.2 times the runtime, E3 outperforms classical generative model based data-free model extraction by an absolute accuracy improvement of over 50% on CIFAR-10. Our findings underscore the persistent threat posed by model extraction and suggest that it could serve as a valuable benchmarking algorithm for future security evaluations.
Authors: Yuxuan Zhu, Shiyi Wang, Wenqing Zhong, Nianchen Shen, Yunqi Li, Siqi Wang, Zhiheng Li, Cathy Wu, Zhengbing He, Li Li
Abstract: Artificial intelligence (AI) plays a crucial role in autonomous driving (AD) research, propelling its development towards intelligence and efficiency. Currently, the development of AD technology follows two main technical paths: modularization and end-to-end. Modularization decompose the driving task into modules such as perception, prediction, planning, and control, and train them separately. Due to the inconsistency of training objectives between modules, the integrated effect suffers from bias. End-to-end attempts to address this issue by utilizing a single model that directly maps from sensor data to control signals. This path has limited learning capabilities in a comprehensive set of features and struggles to handle unpredictable long-tail events and complex urban traffic scenarios. In the face of challenges encountered in both paths, many researchers believe that large language models (LLMs) with powerful reasoning capabilities and extensive knowledge understanding may be the solution, expecting LLMs to provide AD systems with deeper levels of understanding and decision-making capabilities. In light of the challenges faced by both paths, many researchers believe that LLMs, with their powerful reasoning abilities and extensive knowledge, could offer a solution. To understand if LLMs could enhance AD, this paper conducts a thorough analysis of the potential applications of LLMs in AD systems, including exploring their optimization strategies in both modular and end-to-end approaches, with a particular focus on how LLMs can tackle the problems and challenges present in current solutions. Furthermore, we discuss an important question: Can LLM-based artificial general intelligence (AGI) be a key to achieve high-level AD? We further analyze the potential limitations and challenges that LLMs may encounter in promoting the development of AD technology.
Authors: Bokang Bi, Leibo Liu, Sanja Lujic, Louisa Jorm, Oscar Perez-Concha
Abstract: The increasing volume and complexity of clinical documentation in Electronic Medical Records systems pose significant challenges for clinical coders, who must mentally process and summarise vast amounts of clinical text to extract essential information needed for coding tasks. While large language models have been successfully applied to shorter summarisation tasks in recent years, the challenge of summarising a hospital course remains an open area for further research and development. In this study, we adapted three pre trained LLMs, Llama 3, BioMistral, Mistral Instruct v0.1 for the hospital course summarisation task, using Quantized Low Rank Adaptation fine tuning. We created a free text clinical dataset from MIMIC III data by concatenating various clinical notes as the input clinical text, paired with ground truth Brief Hospital Course sections extracted from the discharge summaries for model training. The fine tuned models were evaluated using BERTScore and ROUGE metrics to assess the effectiveness of clinical domain fine tuning. Additionally, we validated their practical utility using a novel hospital course summary assessment metric specifically tailored for clinical coding. Our findings indicate that fine tuning pre trained LLMs for the clinical domain can significantly enhance their performance in hospital course summarisation and suggest their potential as assistive tools for clinical coding. Future work should focus on refining data curation methods to create higher quality clinical datasets tailored for hospital course summary tasks and adapting more advanced open source LLMs comparable to proprietary models to further advance this research.
Authors: Mohammad Atif, Pulkit Dubey, Pratik P. Aghor, Vanessa Lopez-Marrero, Tao Zhang, Abdullah Sharfuddin, Kwangmin Yu, Fan Yang, Foluso Ladeinde, Yangang Liu, Meifeng Lin, Lingda Li
Abstract: High-fidelity direct numerical simulation of turbulent flows for most real-world applications remains an outstanding computational challenge. Several machine learning approaches have recently been proposed to alleviate the computational cost even though they become unstable or unphysical for long time predictions. We identify that the Fourier neural operator (FNO) based models combined with a partial differential equation (PDE) solver can accelerate fluid dynamic simulations and thus address computational expense of large-scale turbulence simulations. We treat the FNO model on the same footing as a PDE solver and answer important questions about the volume and temporal resolution of data required to build pre-trained models for turbulence. We also discuss the pitfalls of purely data-driven approaches that need to be avoided by the machine learning models to become viable and competitive tools for long time simulations of turbulence.
Authors: Chenxu Yang, Ruipeng Jia, Naibin Gu, Zheng Lin, Siyuan Chen, Chao Pang, Weichong Yin, Yu Sun, Hua Wu, Weiping Wang
Abstract: DPO is an effective preference optimization algorithm. However, the DPO-tuned models tend to overfit on the dispreferred samples, manifested as overly long generations lacking diversity. While recent regularization approaches have endeavored to alleviate this issue by modifying the objective function, they achieved that at the cost of alignment performance degradation. In this paper, we innovatively incorporate regularization from the perspective of weight updating to curb alignment overfitting. Through the pilot experiment, we discovered that there exists a positive correlation between overfitting and the hyperspherical energy fluctuation. Hence, we introduce orthogonal finetuning for DPO via a weight-Rotated Preference Optimization (RoPO) method, which merely conducts rotational and magnitude-stretching updates on the weight parameters to maintain the hyperspherical energy invariant, thereby preserving the knowledge encoded in the angle between neurons. Extensive experiments demonstrate that our model aligns perfectly with human preferences while retaining the original expressive capacity using only 0.0086% of the trainable parameters, suggesting an effective regularization against overfitting. Specifically, RoPO outperforms DPO by up to 10 points on MT-Bench and by up to 2.8 points on AlpacaEval 2, while enhancing the generation diversity by an average of 6 points.
Authors: Louis Mozart Kamdem Teyou, Caglar Demir, Axel-Cyrille Ngonga Ngomo
Abstract: We introduce a novel embedding method diverging from conventional approaches by operating within function spaces of finite dimension rather than finite vector space, thus departing significantly from standard knowledge graph embedding techniques. Initially employing polynomial functions to compute embeddings, we progress to more intricate representations using neural networks with varying layer complexities. We argue that employing functions for embedding computation enhances expressiveness and allows for more degrees of freedom, enabling operations such as composition, derivatives and primitive of entities representation. Additionally, we meticulously outline the step-by-step construction of our approach and provide code for reproducibility, thereby facilitating further exploration and application in the field.
Authors: Ahjol Senbi, Tianyu Huang, Fei Lyu, Qing Li, Yuhui Tao, Wei Shao, Qiang Chen, Chengyan Wang, Shuo Wang, Tao Zhou, Yizhe Zhang
Abstract: We explore the feasibility and potential of building a ground-truth-free evaluation model to assess the quality of segmentations generated by the Segment Anything Model (SAM) and its variants in medical imaging. This evaluation model estimates segmentation quality scores by analyzing the coherence and consistency between the input images and their corresponding segmentation predictions. Based on prior research, we frame the task of training this model as a regression problem within a supervised learning framework, using Dice scores (and optionally other metrics) along with mean squared error to compute the training loss. The model is trained utilizing a large collection of public datasets of medical images with segmentation predictions from SAM and its variants. We name this model EvanySeg (Evaluation of Any Segmentation in Medical Images). Our exploration of convolution-based models (e.g., ResNet) and transformer-based models (e.g., ViT) suggested that ViT yields better performance for this task. EvanySeg can be employed for various tasks, including: (1) identifying poorly segmented samples by detecting low-percentile segmentation quality scores; (2) benchmarking segmentation models without ground truth by averaging quality scores across test samples; (3) alerting human experts to poor-quality segmentation predictions during human-AI collaboration by applying a threshold within the score space; and (4) selecting the best segmentation prediction for each test sample at test time when multiple segmentation models are available, by choosing the prediction with the highest quality score. Models and code will be made available at https://github.com/ahjolsenbics/EvanySeg.
Authors: Yixi Wu (Peter), Pengfei He (Peter), Zehao Wang (Peter), Shaowei Wang (Peter), Yuan Tian (Peter), Tse-Hsun (Peter), Chen
Abstract: Large language models (LLMs) like GitHub Copilot and ChatGPT have emerged as powerful tools for code generation, significantly enhancing productivity and accelerating software development. However, existing benchmarks primarily focus on general code generation without considering API-oriented code generation, i.e., generating code that invokes APIs from specific libraries. Given the growing demand for API-oriented code generation, there is a pressing need for a systematic and automated approach to evaluate LLM on API-oriented code generation. To address this gap, we propose AutoAPIEval, a lightweight and automated framework designed to evaluate the capabilities of LLMs in API-oriented code generation. Our framework works with any library that provides API documentation and focuses on two unit tasks: API recommendation and code example generation, along with four metrics to evaluate the generated APIs and code examples, such as the proportion of incorrect API recommendations for Task 1, and the proportion of code examples where no specific API is invoked and uncompilable/unexecutable code examples for Task 2. In addition, we conducted a case study on three LLMs (ChatGPT, MagiCoder, and DeepSeek Coder) and Java Runtime Environment 8 to demonstrate the framework's effectiveness. Our findings reveal substantial variability in LLM performance across tasks, with ChatGPT adhering better to instructions, while sharing similar effectiveness in code example generation with its counterparts (i.e., MagiCoder and DeekSeek Coder). We also identify key factors associated with code quality, such as API popularity and model confidence, and build classifiers that achieve high accuracy in detecting incorrect API recommendations and erroneous code examples. Retrieval-augmented generation enhances the quality of code generated by LLMs, though its effectiveness varies across different LLMs.