Authors: Qiqi Li, Mike Ludkovski
Abstract: We design a Gaussian Process (GP) spatiotemporal model to capture features of day-ahead wind power forecasts. We work with hourly-scale day-ahead forecasts across hundreds of wind farm locations, with the main aim of constructing a fully probabilistic joint model across space and hours of the day. To this end, we design a separable space-time kernel, implementing both temporal and spatial input warping to capture the non-stationarity in the covariance of wind power. We conduct synthetic experiments to validate our choice of the spatial kernel and to demonstrate the effectiveness of warping in addressing nonstationarity. The second half of the paper is devoted to a detailed case study using a realistic, fully calibrated dataset representing wind farms in the ERCOT region of Texas.
Authors: Julie Keisler (CRIStAL, EDF R\&D OSIRIS, EDF R\&D), Margaux Bregere (EDF R\&D, EDF R\&D OSIRIS, LPSM)
Abstract: Electricity is difficult to store, except at prohibitive cost, and therefore the balance between generation and load must be maintained at all times. Electricity is traditionally managed by anticipating demand and intermittent production (wind, solar) and matching flexible production (hydro, nuclear, coal and gas). Accurate forecasting of electricity load and renewable production is therefore essential to ensure grid performance and stability. Both are highly dependent on meteorological variables (temperature, wind, sunshine). These dependencies are complex and difficult to model. On the one hand, spatial variations do not have a uniform impact because population, industry, and wind and solar farms are not evenly distributed across the territory. On the other hand, temporal variations can have delayed effects on load (due to the thermal inertia of buildings). With access to observations from different weather stations and simulated data from meteorological models, we believe that both phenomena can be modeled together. In today's state-of-the-art load forecasting models, the spatio-temporal modeling of the weather is fixed. In this work, we aim to take advantage of the automated representation and spatio-temporal feature extraction capabilities of deep neural networks to improve spatio-temporal weather modeling for load forecasting. We compare our deep learning-based methodology with the state-of-the-art on French national load. This methodology could also be fully adapted to forecasting renewable energy production.
Authors: Shadi Iskander, Nachshon Cohen, Zohar Karnin, Ori Shapira, Sofia Tolmach
Abstract: Training large language models (LLMs) for external tool usage is a rapidly expanding field, with recent research focusing on generating synthetic data to address the shortage of available data. However, the absence of systematic data quality checks poses complications for properly training and testing models. To that end, we propose two approaches for assessing the reliability of data for training LLMs to use external tools. The first approach uses intuitive, human-defined correctness criteria. The second approach uses a model-driven assessment with in-context evaluation. We conduct a thorough evaluation of data quality on two popular benchmarks, followed by an extrinsic evaluation that showcases the impact of data quality on model performance. Our results demonstrate that models trained on high-quality data outperform those trained on unvalidated data, even when trained with a smaller quantity of data. These findings empirically support the significance of assessing and ensuring the reliability of training data for tool-using LLMs.
Authors: Cameron Taylor, Vassilis Vassiliades, Constantine Dovrolis
Abstract: We focus on a relatively unexplored learning paradigm known as {\em Online Unsupervised Continual Learning} (O-UCL), where an agent receives a non-stationary, unlabeled data stream and progressively learns to identify an increasing number of classes. This paradigm is designed to model real-world applications where encountering novelty is the norm, such as exploring a terrain with several unknown and time-varying entities. Unlike prior work in unsupervised, continual, or online learning, O-UCL combines all three areas into a single challenging and realistic learning paradigm. In this setting, agents are frequently evaluated and must aim to maintain the best possible representation at any point of the data stream, rather than at the end of pre-specified offline tasks. The proposed approach, called \textbf{P}atch-based \textbf{C}ontrastive learning and \textbf{M}emory \textbf{C}onsolidation (PCMC), builds a compositional understanding of data by identifying and clustering patch-level features. Embeddings for these patch-level features are extracted with an encoder trained via patch-based contrastive learning. PCMC incorporates new data into its distribution while avoiding catastrophic forgetting, and it consolidates memory examples during ``sleep" periods. We evaluate PCMC's performance on streams created from the ImageNet and Places365 datasets. Additionally, we explore various versions of the PCMC algorithm and compare its performance against several existing methods and simple baselines.
Authors: Satyananda Kashyap, Niharika S. D'Souza, Luyao Shi, Ken C. L. Wong, Hongzhi Wang, Tanveer Syeda-Mahmood
Abstract: Content-addressable memories such as Modern Hopfield Networks (MHN) have been studied as mathematical models of auto-association and storage/retrieval in the human declarative memory, yet their practical use for large-scale content storage faces challenges. Chief among them is the occurrence of meta-stable states, particularly when handling large amounts of high dimensional content. This paper introduces Hopfield Encoding Networks (HEN), a framework that integrates encoded neural representations into MHNs to improve pattern separability and reduce meta-stable states. We show that HEN can also be used for retrieval in the context of hetero association of images with natural language queries, thus removing the limitation of requiring access to partial content in the same domain. Experimental results demonstrate substantial reduction in meta-stable states and increased storage capacity while still enabling perfect recall of a significantly larger number of inputs advancing the practical utility of associative memory networks for real-world tasks.
Authors: Mohammad Hossein Moslemi, Harini Balamurugan, Mostafa Milani
Abstract: Entity Matching (EM) is crucial for identifying equivalent data entities across different sources, a task that becomes increasingly challenging with the growth and heterogeneity of data. Blocking techniques, which reduce the computational complexity of EM, play a vital role in making this process scalable. Despite advancements in blocking methods, the issue of fairness; where blocking may inadvertently favor certain demographic groups; has been largely overlooked. This study extends traditional blocking metrics to incorporate fairness, providing a framework for assessing bias in blocking techniques. Through experimental analysis, we evaluate the effectiveness and fairness of various blocking methods, offering insights into their potential biases. Our findings highlight the importance of considering fairness in EM, particularly in the blocking phase, to ensure equitable outcomes in data integration tasks.
Authors: Lucas Shoji, Kenta Suzuki, Leo Kozachkov
Abstract: This paper shows that a wide class of effective learning rules -- those that improve a scalar performance measure over a given time window -- can be rewritten as natural gradient descent with respect to a suitably defined loss function and metric. Specifically, we show that parameter updates within this class of learning rules can be expressed as the product of a symmetric positive definite matrix (i.e., a metric) and the negative gradient of a loss function. We also demonstrate that these metrics have a canonical form and identify several optimal ones, including the metric that achieves the minimum possible condition number. The proofs of the main results are straightforward, relying only on elementary linear algebra and calculus, and are applicable to continuous-time, discrete-time, stochastic, and higher-order learning rules, as well as loss functions that explicitly depend on time.
Authors: Zheda Mai, Ping Zhang, Cheng-Hao Tu, Hong-You Chen, Li Zhang, Wei-Lun Chao
Abstract: Parameter-efficient transfer learning (PETL) has attracted significant attention lately, due to the increasing size of pre-trained models and the need to fine-tune (FT) them for superior downstream performance. This community-wide enthusiasm has sparked a plethora of new methods. Nevertheless, a systematic study to understand their performance and suitable application scenarios is lacking, leaving questions like when to apply PETL and which method to use largely unanswered. In this paper, we conduct a unifying empirical study of representative PETL methods in the context of Vision Transformers. We systematically tune their hyper-parameters to fairly compare their accuracy on downstream tasks. Our study not only offers a valuable user guide but also unveils several new insights. First, if tuned carefully, different PETL methods can obtain quite similar accuracy in the low-shot benchmark VTAB-1K. This includes simple methods like FT the bias terms that were reported inferior. Second, though with similar accuracy, we find that PETL methods make different mistakes and high-confidence predictions, likely due to their different inductive biases. Such an inconsistency (or complementariness) opens up the opportunity for ensemble methods, and we make preliminary attempts at this. Third, going beyond the commonly used low-shot tasks, we find that PETL is also useful in many-shot regimes -- it achieves comparable and sometimes better accuracy than full FT, using much fewer learnable parameters. Last but not least, we investigate PETL's ability to preserve a pre-trained model's robustness to distribution shifts (e.g., a CLIP backbone). Perhaps not surprisingly, PETL methods outperform full FT alone. However, with weight-space ensembles, the fully FT model can achieve a better balance between downstream and out-of-distribution performance, suggesting a future research direction for PETL.
Authors: Elissa Mhanna, Mohamad Assaad
Abstract: Federated learning (FL) is a popular machine learning technique that enables multiple users to collaboratively train a model while maintaining the user data privacy. A significant challenge in FL is the communication bottleneck in the upload direction, and thus the corresponding energy consumption of the devices, attributed to the increasing size of the model/gradient. In this paper, we address this issue by proposing a zero-order (ZO) optimization method that requires the upload of a quantized single scalar per iteration by each device instead of the whole gradient vector. We prove its theoretical convergence and find an upper bound on its convergence rate in the non-convex setting, and we discuss its implementation in practical scenarios. Our FL method and the corresponding convergence analysis take into account the impact of quantization and packet dropping due to wireless errors. We show also the superiority of our method, in terms of communication overhead and energy consumption, as compared to standard gradient-based FL methods.
Authors: Yash Gandhi, Kexin Zheng, Birendra Jha, Ken-ichi Nomura, Aiichiro Nakano, Priya Vashishta, Rajiv K. Kalia
Abstract: Forecasting oil production from oilfields with multiple wells is an important problem in petroleum and geothermal energy extraction, as well as energy storage technologies. The accuracy of oil forecasts is a critical determinant of economic projections, hydrocarbon reserves estimation, construction of fluid processing facilities, and energy price fluctuations. Leveraging generative AI techniques, we model time series forecasting of oil and water productions across four multi-well sites spanning four decades. Our goal is to effectively model uncertainties and make precise forecasts to inform decision-making processes at the field scale. We utilize an autoregressive model known as TimeGrad and a variant of a transformer architecture named Informer, tailored specifically for forecasting long sequence time series data. Predictions from both TimeGrad and Informer closely align with the ground truth data. The overall performance of the Informer stands out, demonstrating greater efficiency compared to TimeGrad in forecasting oil production rates across all sites.
Authors: Nathaniel Hudson, Valerie Hayot-Sasson, Yadu Babuji, Matt Baughman, J. Gregory Pauloski, Ryan Chard, Ian Foster, Kyle Chard
Abstract: Federated Learning (FL) is a decentralized machine learning paradigm where models are trained on distributed devices and are aggregated at a central server. Existing FL frameworks assume simple two-tier network topologies where end devices are directly connected to the aggregation server. While this is a practical mental model, it does not exploit the inherent topology of real-world distributed systems like the Internet-of-Things. We present Flight, a novel FL framework that supports complex hierarchical multi-tier topologies, asynchronous aggregation, and decouples the control plane from the data plane. We compare the performance of Flight against Flower, a state-of-the-art FL framework. Our results show that Flight scales beyond Flower, supporting up to 2048 simultaneous devices, and reduces FL makespan across several models. Finally, we show that Flight's hierarchical FL model can reduce communication overheads by more than 60%.
Authors: Yahya Sattar, Yassir Jedra, Sarah Dean
Abstract: We consider the problem of learning a realization of a partially observed dynamical system with linear state transitions and bilinear observations. Under very mild assumptions on the process and measurement noises, we provide a finite time analysis for learning the unknown dynamics matrices (up to a similarity transform). Our analysis involves a regression problem with heavy-tailed and dependent data. Moreover, each row of our design matrix contains a Kronecker product of current input with a history of inputs, making it difficult to guarantee persistence of excitation. We overcome these challenges, first providing a data-dependent high probability error bound for arbitrary but fixed inputs. Then, we derive a data-independent error bound for inputs chosen according to a simple random design. Our main results provide an upper bound on the statistical error rates and sample complexity of learning the unknown dynamics matrices from a single finite trajectory of bilinear observations.
Authors: Xin Yuan, Ning Li, Quan Chen, Wenchao Xu, Zhaoxin Zhang, Song Guo
Abstract: Even the AI has been widely used and significantly changed our life, deploying the large AI models on resource limited edge devices directly is not appropriate. Thus, the model split inference is proposed to improve the performance of edge intelligence, in which the AI model is divided into different sub models and the resource-intensive sub model is offloaded to edge server wirelessly for reducing resource requirements and inference latency. However, the previous works mainly concentrate on improving and optimizing the system QoS, ignore the effect of QoE which is another critical item for the users except for QoS. Even the QoE has been widely learned in EC, considering the differences between task offloading in EC and split inference in EI, and the specific issues in QoE which are still not addressed in EC and EI, these algorithms cannot work effectively in edge split inference scenarios. Thus, an effective resource allocation algorithm is proposed in this paper, for accelerating split inference in EI and achieving the tradeoff between inference delay, QoE, and resource consumption, abbreviated as ERA. Specifically, the ERA takes the resource consumption, QoE, and inference latency into account to find the optimal model split strategy and resource allocation strategy. Since the minimum inference delay and resource consumption, and maximum QoE cannot be satisfied simultaneously, the gradient descent based algorithm is adopted to find the optimal tradeoff between them. Moreover, the loop iteration GD approach is developed to reduce the complexity of the GD algorithm caused by parameter discretization. Additionally, the properties of the proposed algorithms are investigated, including convergence, complexity, and approximation error. The experimental results demonstrate that the performance of ERA is much better than that of the previous studies.
Authors: Forest Kobayashi, Jonathan Hayase, Young-Heon Kim
Abstract: We consider the problem of finding the ``best'' approximation of an $n$-dimensional probability measure $\rho$ using a measure $\nu$ whose support is parametrized by $f : \mathbb{R}^m \to \mathbb{R}^n$ where $m < n$. We quantify the performance of the approximation with the Monge-Kantorovich $p$-cost (also called the Wasserstein $p$-cost) $\mathbb{W}_p^p(\rho, \nu)$, and constrain the complexity of the approximation by bounding the $W^{k,q}$ Sobolev norm of $f$, which acts as a ``budget.'' We may then reformulate the problem as minimizing a functional $\mathscr{J}_p(f)$ under a constraint on the Sobolev budget. We treat general $k \geq 1$ for the Sobolev differentiability order (though $q, m$ are chosen to restrict $W^{k,q}$ to the supercritical regime $k q > m$ to guarantee existence of optimizers). The problem is closely related to (but distinct from) principal curves with length constraints when $m=1, k = 1$ and smoothing splines when $k > 1$. New aspects and challenges arise from the higher order differentiability condition. We study the gradient of $\mathscr{J}_p$, which is given by a vector field along $f$ we call the barycenter field. We use it to construct improvements to a given $f$, which gives a nontrivial (almost) strict monotonicty relation between the functional $\mathscr{J}_p$ and the Sobolev budget. We also provide a natural discretization scheme and establish its consistency. We use this scheme to model a generative learning task; in particular, we demonstrate that adding a constraint like ours as a soft penalty yields substantial improvement in training a GAN to produce images of handwritten digits, with performance competitive with weight-decay.
Authors: Yifan Tan, Haoze Wang, Chao Yan, Yangdong Deng
Abstract: Model quantization has become a crucial technique to address the issues of large memory consumption and long inference times associated with LLMs. Mixed-precision quantization, which distinguishes between important and unimportant parameters, stands out among numerous quantization schemes as it achieves a balance between precision and compression rate. However, existing approaches can only identify important parameters through qualitative analysis and manual experiments without quantitatively analyzing how their importance is determined. We propose a new criterion, so-called 'precision alignment', to build a quantitative framework to holistically evaluate the importance of parameters in mixed-precision quantization. Our observations on floating point addition under various real-world scenarios suggest that two addends should have identical precision, otherwise the information in the higher-precision number will be wasted. Such an observation offers an essential principle to determine the precision of each parameter in matrix multiplication operation. As the first step towards applying the above discovery to large model inference, we develop a dynamic KV-Cache quantization technique to effectively reduce memory access latency. Different from existing quantization approaches that focus on memory saving, this work directly aims to accelerate LLM inference through quantifying floating numbers. The proposed technique attains a 25% saving of memory access and delivers up to 1.3x speedup in the computation of attention in the decoding phase of LLM, with almost no loss of precision.
Authors: Hrishikesh Patel, Ruihong Qiu, Adam Irwin, Shazia Sadiq, Sen Wang
Abstract: Irregular time series, where data points are recorded at uneven intervals, are prevalent in healthcare settings, such as emergency wards where vital signs and laboratory results are captured at varying times. This variability, which reflects critical fluctuations in patient health, is essential for informed clinical decision-making. Existing self-supervised learning research on irregular time series often relies on generic pretext tasks like forecasting, which may not fully utilise the signal provided by irregular time series. There is a significant need for specialised pretext tasks designed for the characteristics of irregular time series to enhance model performance and robustness, especially in scenarios with limited data availability. This paper proposes a novel pretraining framework, EMIT, an event-based masking for irregular time series. EMIT focuses on masking-based reconstruction in the latent space, selecting masking points based on the rate of change in the data. This method preserves the natural variability and timing of measurements while enhancing the model's ability to process irregular intervals without losing essential information. Extensive experiments on the MIMIC-III and PhysioNet Challenge datasets demonstrate the superior performance of our event-based masking strategy. The code has been released at https://github.com/hrishi-ds/EMIT .
Authors: Jonathan E. Lee, Min Zhu, Ziqiao Xi, Kun Wang, Yanhua O. Yuan, Lu Lu
Abstract: Geological carbon sequestration (GCS) involves injecting CO$_2$ into subsurface geological formations for permanent storage. Numerical simulations could guide decisions in GCS projects by predicting CO$_2$ migration pathways and the pressure distribution in storage formation. However, these simulations are often computationally expensive due to highly coupled physics and large spatial-temporal simulation domains. Surrogate modeling with data-driven machine learning has become a promising alternative to accelerate physics-based simulations. Among these, the Fourier neural operator (FNO) has been applied to three-dimensional synthetic subsurface models. Here, to further improve performance, we have developed a nested Fourier-DeepONet by combining the expressiveness of the FNO with the modularity of a deep operator network (DeepONet). This new framework is twice as efficient as a nested FNO for training and has at least 80% lower GPU memory requirement due to its flexibility to treat temporal coordinates separately. These performance improvements are achieved without compromising prediction accuracy. In addition, the generalization and extrapolation ability of nested Fourier-DeepONet beyond the training range has been thoroughly evaluated. Nested Fourier-DeepONet outperformed the nested FNO for extrapolation in time with more than 50% reduced error. It also exhibited good extrapolation accuracy beyond the training range in terms of reservoir properties, number of wells, and injection rate.
Authors: Tengfei Lyu, Weijia Zhang, Jinliang Deng, Hao Liu
Abstract: Spatio-temporal forecasting is a critical component of various smart city applications, such as transportation optimization, energy management, and socio-economic analysis. Recently, several automated spatio-temporal forecasting methods have been proposed to automatically search the optimal neural network architecture for capturing complex spatio-temporal dependencies. However, the existing automated approaches suffer from expensive neural architecture search overhead, which hinders their practical use and the further exploration of diverse spatio-temporal operators in a finer granularity. In this paper, we propose AutoSTF, a decoupled automatic neural architecture search framework for cost-effective automated spatio-temporal forecasting. From the efficiency perspective, we first decouple the mixed search space into temporal space and spatial space and respectively devise representation compression and parameter-sharing schemes to mitigate the parameter explosion. The decoupled spatio-temporal search not only expedites the model optimization process but also leaves new room for more effective spatio-temporal dependency modeling. From the effectiveness perspective, we propose a multi-patch transfer module to jointly capture multi-granularity temporal dependencies and extend the spatial search space to enable finer-grained layer-wise spatial dependency search. Extensive experiments on eight datasets demonstrate the superiority of AutoSTF in terms of both accuracy and efficiency. Specifically, our proposed method achieves up to 13.48x speed-up compared to state-of-the-art automatic spatio-temporal forecasting methods while maintaining the best forecasting accuracy.
Authors: Yuchen Li, Haoyi Xiong, Linghe Kong, Zeyi Sun, Hongyang Chen, Shuaiqiang Wang, Dawei Yin
Abstract: Both Transformer and Graph Neural Networks (GNNs) have been employed in the domain of learning to rank (LTR). However, these approaches adhere to two distinct yet complementary problem formulations: ranking score regression based on query-webpage pairs, and link prediction within query-webpage bipartite graphs, respectively. While it is possible to pre-train GNNs or Transformers on source datasets and subsequently fine-tune them on sparsely annotated LTR datasets, the distributional shifts between the pair-based and bipartite graph domains present significant challenges in integrating these heterogeneous models into a unified LTR framework at web scale. To address this, we introduce the novel MPGraf model, which leverages a modular and capsule-based pre-training strategy, aiming to cohesively integrate the regression capabilities of Transformers with the link prediction strengths of GNNs. We conduct extensive offline and online experiments to rigorously evaluate the performance of MPGraf.
Authors: Meredith G. L. Brown, Matt Peterson, Irina Tezaur, Kara Peterson, Diana Bull
Abstract: Disturbances to the climate system, both natural and anthropogenic, have far reaching impacts that are not always easy to identify or quantify using traditional climate science analyses or causal modeling techniques. In this paper, we develop a novel technique for discovering and ranking the chain of spatio-temporal downstream impacts of a climate source, referred to herein as a source-impact pathway, using Random Forest Regression (RFR) and SHapley Additive exPlanation (SHAP) feature importances. Rather than utilizing RFR for classification or regression tasks (the most common use case for RFR), we propose a fundamentally new RFR-based workflow in which we: (i) train random forest (RF) regressors on a set of spatio-temporal features of interest, (ii) calculate their pair-wise feature importances using the SHAP weights associated with those features, and (iii) translate these feature importances into a weighted pathway network (i.e., a weighted directed graph), which can be used to trace out and rank interdependencies between climate features and/or modalities. We adopt a tiered verification approach to verify our new pathway identification methodology. In this approach, we apply our method to ensembles of data generated by running two increasingly complex benchmarks: (i) a set of synthetic coupled equations, and (ii) a fully coupled simulation of the 1991 eruption of Mount Pinatubo in the Philippines performed using a modified version 2 of the U.S. Department of Energy's Energy Exascale Earth System Model (E3SMv2). We find that our RFR feature importance-based approach can accurately detect known pathways of impact for both test cases.
Authors: Yuanyong Luo, Zhongxing Zhang, Richard Wu, Hu Liu, Ying Jin, Kai Zheng, Minmin Wang, Zhanying He, Guipeng Hu, Luyao Chen, Tianchi Hu, Junsong Wang, Minqi Chen, Mikhaylov Dmitry, Korviakov Vladimir, Bobrin Maxim, Yuhao Hu, Guanfu Chen, Zeyi Huang
Abstract: This preliminary white paper proposes a novel 8-bit floating-point data format HiFloat8 (abbreviated as HiF8) for deep learning. HiF8 features tapered precision. For normal value encoding, it provides 7 exponents with 3-bit mantissa, 8 exponents with 2-bit mantissa, and 16 exponents with 1-bit mantissa. For denormal or subnormal value encoding, it extends the dynamic range by 7 extra powers of 2, from 31 to 38 binades (notice that FP16 covers 40 binades). Meanwhile, HiF8 encodes all the special values except that positive zero and negative zero are represented by only one bit-pattern. Thanks to the better balance between precision and dynamic range, HiF8 can be simultaneously used in both forward and backward passes of AI training. In this paper, we will describe the definition and rounding methods of HiF8, as well as the tentative training and inference solutions. To demonstrate the efficacy of HiF8 format, massive simulation results on various neural networks, including traditional neural networks and large language models (LLMs), will also be presented.
Authors: Bum Jun Kim, Sang Woo Kim
Abstract: Regularization of deep neural networks has been an important issue to achieve higher generalization performance without overfitting problems. Although the popular method of Dropout provides a regularization effect, it causes inconsistent properties in the output, which may degrade the performance of deep neural networks. In this study, we propose a new module called stochastic average pooling, which incorporates Dropout-like stochasticity in pooling. We describe the properties of stochastic subsampling and average pooling and leverage them to design a module without any inconsistency problem. The stochastic average pooling achieves a regularization effect without any potential performance degradation due to the inconsistency issue and can easily be plugged into existing architectures of deep neural networks. Experiments demonstrate that replacing existing average pooling with stochastic average pooling yields consistent improvements across a variety of tasks, datasets, and models.
Authors: Mengjing Wu, Junyu Xuan, Jie Lu
Abstract: Classical variational inference for Bayesian neural networks (BNNs) in parameter space usually suffers from unresolved prior issues such as knowledge encoding intractability and pathological behaviors in deep networks, which could lead to an improper posterior inference. Hence, functional variational inference has been proposed recently to resolve these issues via stochastic process priors. Beyond variational inference, stochastic gradient Markov Chain Monte Carlo (SGMCMC) is another scalable and effective inference method for BNNs to asymptotically generate samples from true posterior by simulating a continuous dynamic. However, the existing SGMCMC methods only work in parametric space, which has the same issues of parameter-space variational inference, and extending the parameter-space dynamics to function-space dynamics is not a trivial undertaking. In this paper, we introduce a new functional SGMCMC scheme via newly designed diffusion dynamics, which can incorporate more informative functional priors. Moreover, we prove that the stationary distribution of these functional dynamics is the target posterior distribution over functions. We demonstrate better performance in both accuracy and uncertainty quantification of our functional SGMCMC on several tasks compared with naive SGMCMC and functional variational inference methods.
Authors: Soorin Yim, Dae-Woong Jeong, Sung Moon Ko, Sumin Lee, Hyunseung Kim, Chanhui Lee, Sehui Han
Abstract: Training deep learning models on limited data while maintaining generalization is one of the fundamental challenges in molecular property prediction. One effective solution is transferring knowledge extracted from abundant datasets to those with scarce data. Recently, a novel algorithm called Geometrically Aligned Transfer Encoder (GATE) has been introduced, which uses soft parameter sharing by aligning the geometrical shapes of task-specific latent spaces. However, GATE faces limitations in scaling to multiple tasks due to computational costs. In this study, we propose a task addition approach for GATE to improve performance on target tasks with limited data while minimizing computational complexity. It is achieved through supervised multi-task pre-training on a large dataset, followed by the addition and training of task-specific modules for each target task. Our experiments demonstrate the superior performance of the task addition strategy for GATE over conventional multi-task methods, with comparable computational costs.
Authors: Ronald Richman, Salvatore Scognamiglio, Mario V. W\"uthrich
Abstract: Inspired by the large success of Transformers in Large Language Models, these architectures are increasingly applied to tabular data. This is achieved by embedding tabular data into low-dimensional Euclidean spaces resulting in similar structures as time-series data. We introduce a novel credibility mechanism to this Transformer architecture. This credibility mechanism is based on a special token that should be seen as an encoder that consists of a credibility weighted average of prior information and observation based information. We demonstrate that this novel credibility mechanism is very beneficial to stabilize training, and our Credibility Transformer leads to predictive models that are superior to state-of-the-art deep learning models.
Authors: Zhe-Rui Yang, Jindong Han, Chang-Dong Wang, Hao Liu
Abstract: Graph Neural Networks (GNNs) have demonstrated remarkable proficiency in handling a range of graph analytical tasks across various domains, such as e-commerce and social networks. Despite their versatility, GNNs face significant challenges in transferability, limiting their utility in real-world applications. Existing research in GNN transfer learning overlooks discrepancies in distribution among various graph datasets, facing challenges when transferring across different distributions. How to effectively adopt a well-trained GNN to new graphs with varying feature and structural distributions remains an under-explored problem. Taking inspiration from the success of Low-Rank Adaptation (LoRA) in adapting large language models to various domains, we propose GraphLoRA, an effective and parameter-efficient method for transferring well-trained GNNs to diverse graph domains. Specifically, we first propose a Structure-aware Maximum Mean Discrepancy (SMMD) to align divergent node feature distributions across source and target graphs. Moreover, we introduce low-rank adaptation by injecting a small trainable GNN alongside the pre-trained one, effectively bridging structural distribution gaps while mitigating the catastrophic forgetting. Additionally, a structure-aware regularization objective is proposed to enhance the adaptability of the pre-trained GNN to target graph with scarce supervision labels. Extensive experiments on six real-world datasets demonstrate the effectiveness of GraphLoRA against eleven baselines by tuning only 20% of parameters, even across disparate graph domains. The code is available at https://anonymous.4open.science/r/GraphLoRA.
Authors: Zhe-Rui Yang, Jindong Han, Chang-Dong Wang, Hao Liu
Abstract: Graph unlearning, which aims to eliminate the influence of specific nodes, edges, or attributes from a trained Graph Neural Network (GNN), is essential in applications where privacy, bias, or data obsolescence is a concern. However, existing graph unlearning techniques often necessitate additional training on the remaining data, leading to significant computational costs, particularly with large-scale graphs. To address these challenges, we propose a two-stage training-free approach, Erase then Rectify (ETR), designed for efficient and scalable graph unlearning while preserving the model utility. Specifically, we first build a theoretical foundation showing that masking parameters critical for unlearned samples enables effective unlearning. Building on this insight, the Erase stage strategically edits model parameters to eliminate the impact of unlearned samples and their propagated influence on intercorrelated nodes. To further ensure the GNN's utility, the Rectify stage devises a gradient approximation method to estimate the model's gradient on the remaining dataset, which is then used to enhance model performance. Overall, ETR achieves graph unlearning without additional training or full training data access, significantly reducing computational overhead and preserving data privacy. Extensive experiments on seven public datasets demonstrate the consistent superiority of ETR in model utility, unlearning efficiency, and unlearning effectiveness, establishing it as a promising solution for real-world graph unlearning challenges.
Authors: Li Liu, Tengchao Yu, Heng Yong
Abstract: The Universal Approximation Theorem posits that neural networks can theoretically possess unlimited approximation capacity with a suitable activation function and a freely chosen or trained set of parameters. However, a more practical scenario arises when these neural parameters, especially the nonlinear weights and biases, are bounded. This leads us to question: \textbf{Does the approximation capacity of a neural network remain universal, or does it have a limit when the parameters are practically bounded? And if it has a limit, how can it be measured?} Our theoretical study indicates that while universal approximation is theoretically feasible, in practical numerical scenarios, Deep Neural Networks (DNNs) with any analytic activation functions (such as Tanh and Sigmoid) can only be approximated by a finite-dimensional vector space under a bounded nonlinear parameter space (NP space), whether in a continuous or discrete sense. Based on this study, we introduce the concepts of \textit{$\epsilon$ outer measure} and \textit{Numerical Span Dimension (NSdim)} to quantify the approximation capacity limit of a family of networks both theoretically and practically. Furthermore, drawing on our new theoretical study and adopting a fresh perspective, we strive to understand the relationship between back-propagation neural networks and random parameter networks (such as the Extreme Learning Machine (ELM)) with both finite and infinite width. We also aim to provide fresh insights into regularization, the trade-off between width and depth, parameter space, width redundancy, condensation, and other related important issues.
Authors: Anahita Baninajjar, Kamran Hosseini, Ahmed Rezine, Amir Aminifar
Abstract: Given two Deep Neural Network (DNN) classifiers with the same input and output domains, our goal is to quantify the robustness of the two networks in relation to each other. Towards this, we introduce the notion of Relative Safety Margins (RSMs). Intuitively, given two classes and a common input, RSM of one classifier with respect to another reflects the relative margins with which decisions are made. The proposed notion is relevant in the context of several applications domains, including to compare a trained network and its corresponding compact network (e.g., pruned, quantized, distilled network). Not only can RSMs establish whether decisions are preserved, but they can also quantify their qualities. We also propose a framework to establish safe bounds on RSM gains or losses given an input and a family of perturbations. We evaluate our approach using the MNIST, CIFAR10, and two real-world medical datasets, to show the relevance of our results.
Authors: M. Sajid, A. Quadir, M. Tanveer
Abstract: The random vector functional link (RVFL) network is a prominent classification model with strong generalization ability. However, RVFL treats all samples uniformly, ignoring whether they are pure or noisy, and its scalability is limited due to the need for inverting the entire training matrix. To address these issues, we propose granular ball RVFL (GB-RVFL) model, which uses granular balls (GBs) as inputs instead of training samples. This approach enhances scalability by requiring only the inverse of the GB center matrix and improves robustness against noise and outliers through the coarse granularity of GBs. Furthermore, RVFL overlooks the dataset's geometric structure. To address this, we propose graph embedding GB-RVFL (GE-GB-RVFL) model, which fuses granular computing and graph embedding (GE) to preserve the topological structure of GBs. The proposed GB-RVFL and GE-GB-RVFL models are evaluated on KEEL, UCI, NDC and biomedical datasets, demonstrating superior performance compared to baseline models.
Authors: Eslam Eldeeb, Hirley Alves
Abstract: Reinforcement learning (RL) has proved to have a promising role in future intelligent wireless networks. Online RL has been adopted for radio resource management (RRM), taking over traditional schemes. However, due to its reliance on online interaction with the environment, its role becomes limited in practical, real-world problems where online interaction is not feasible. In addition, traditional RL stands short in front of the uncertainties and risks in real-world stochastic environments. In this manner, we propose an offline and distributional RL scheme for the RRM problem, enabling offline training using a static dataset without any interaction with the environment and considering the sources of uncertainties using the distributions of the return. Simulation results demonstrate that the proposed scheme outperforms conventional resource management models. In addition, it is the only scheme that surpasses online RL and achieves a $16 \%$ gain over online RL.
Authors: Kun Song, Zhiquan Tan, Bochao Zou, Jiansheng Chen, Huimin Ma, Weiran Huang
Abstract: In this paper, we utilize information-theoretic metrics like matrix entropy and mutual information to analyze supervised learning. We explore the information content of data representations and classification head weights and their information interplay during supervised training. Experiments show that matrix entropy cannot solely describe the interaction of the information content of data representation and classification head weights but it can effectively reflect the similarity and clustering behavior of the data. Inspired by this, we propose a cross-modal alignment loss to improve the alignment between the representations of the same class from different modalities. Moreover, in order to assess the interaction of the information content of data representation and classification head weights more accurately, we utilize new metrics like matrix mutual information ratio (MIR) and matrix information entropy difference ratio (HDR). Through theory and experiment, we show that HDR and MIR can not only effectively describe the information interplay of supervised training but also improve the performance of supervised and semi-supervised learning.
Authors: Marko Tuononen, Dani Korpi, Ville Hautam\"aki
Abstract: We propose a novel method for interpreting neural networks, focusing on convolutional neural network-based receiver model. The method identifies which unit or units of the model contain most (or least) information about the channel parameter(s) of the interest, providing insights at both global and local levels -- with global explanations aggregating local ones. Experiments on link-level simulations demonstrate the method's effectiveness in identifying units that contribute most (and least) to signal-to-noise ratio processing. Although we focus on a radio receiver model, the method generalizes to other neural network architectures and applications, offering robust estimation even in high-dimensional settings.
Authors: Jatin Chaudhary, Dipak Nidhi, Jukka Heikkonen, Haari Merisaari, Rajiv Kanth
Abstract: The objective of this paper is to enhance the optimization process for neural networks by developing a dynamic learning rate algorithm that effectively integrates exponential decay and advanced anti-overfitting strategies. Our primary contribution is the establishment of a theoretical framework where we demonstrate that the optimization landscape, under the influence of our algorithm, exhibits unique stability characteristics defined by Lyapunov stability principles. Specifically, we prove that the superlevel sets of the loss function, as influenced by our adaptive learning rate, are always connected, ensuring consistent training dynamics. Furthermore, we establish the "equiconnectedness" property of these superlevel sets, which maintains uniform stability across varying training conditions and epochs. This paper contributes to the theoretical understanding of dynamic learning rate mechanisms in neural networks and also pave the way for the development of more efficient and reliable neural optimization techniques. This study intends to formalize and validate the equiconnectedness of loss function as superlevel sets in the context of neural network training, opening newer avenues for future research in adaptive machine learning algorithms. We leverage previous theoretical discoveries to propose training mechanisms that can effectively handle complex and high-dimensional data landscapes, particularly in applications requiring high precision and reliability.
Authors: Alexander Hinterleitner, Thomas Bartz-Beielstein, Richard Schulz, Sebastian Spengler, Thomas Winter, Christoph Leitenmeier
Abstract: Research in Explainable Artificial Intelligence (XAI) is increasing, aiming to make deep learning models more transparent. Most XAI methods focus on justifying the decisions made by Artificial Intelligence (AI) systems in security-relevant applications. However, relatively little attention has been given to using these methods to improve the performance and robustness of deep learning algorithms. Additionally, much of the existing XAI work primarily addresses classification problems. In this study, we investigate the potential of feature attribution methods to filter out uninformative features in input data for regression problems, thereby improving the accuracy and stability of predictions. We introduce a feature selection pipeline that combines Integrated Gradients with k-means clustering to select an optimal set of variables from the initial data space. To validate the effectiveness of this approach, we apply it to a real-world industrial problem - blade vibration analysis in the development process of turbo machinery.
Authors: Mohsen Ghaffari, Mahsa Varshosaz, Einar Broch Johnsen, Andrzej W\k{a}sowski
Abstract: Tabular reinforcement learning methods cannot operate directly on continuous state spaces. One solution for this problem is to partition the state space. A good partitioning enables generalization during learning and more efficient exploitation of prior experiences. Consequently, the learning process becomes faster and produces more reliable policies. However, partitioning introduces approximation, which is particularly harmful in the presence of nonlinear relations between state components. An ideal partition should be as coarse as possible, while capturing the key structure of the state space for the given problem. This work extracts partitions from the environment dynamics by symbolic execution. We show that symbolic partitioning improves state space coverage with respect to environmental behavior and allows reinforcement learning to perform better for sparse rewards. We evaluate symbolic state space partitioning with respect to precision, scalability, learning agent performance and state space coverage for the learnt policies.
Authors: Alexander Rubinstein, Luca Scimeca, Damien Teney, Seong Joon Oh
Abstract: Training a diverse ensemble of models has several practical applications such as providing candidates for model selection with better out-of-distribution (OOD) generalization, and enabling the detection of OOD samples via Bayesian principles. An existing approach to diverse ensemble training encourages the models to disagree on provided OOD samples. However, the approach is computationally expensive and it requires well-separated ID and OOD examples, such that it has only been demonstrated in small-scale settings. $\textbf{Method.}$ This work presents a method for Scalable Ensemble Diversification (SED) applicable to large-scale settings (e.g. ImageNet) that does not require OOD samples. Instead, SED identifies hard training samples on the fly and encourages the ensemble members to disagree on these. To improve scaling, we show how to avoid the expensive computations in existing methods of exhaustive pairwise disagreements across models. $\textbf{Results.}$ We evaluate the benefits of diversification with experiments on ImageNet. First, for OOD generalization, we observe large benefits from the diversification in multiple settings including output-space (classical) ensembles and weight-space ensembles (model soups). Second, for OOD detection, we turn the diversity of ensemble hypotheses into a novel uncertainty score estimator that surpasses a large number of OOD detection baselines. Code is available here: https://github.com/AlexanderRubinstein/diverse-universe-public.
URLs: https://github.com/AlexanderRubinstein/diverse-universe-public.
Authors: Giorgos Armeniakos, Georgios Mentzos, Dimitrios Soudris
Abstract: The rapid growth of microcontroller-based IoT devices has opened up numerous applications, from smart manufacturing to personalized healthcare. Despite the widespread adoption of energy-efficient microcontroller units (MCUs) in the Tiny Machine Learning (TinyML) domain, they still face significant limitations in terms of performance and memory (RAM, Flash). In this work, we combine approximate computing and software kernel design to accelerate the inference of approximate CNN models on MCUs. Our kernel-based approximation framework firstly unpacks the operands of each convolution layer and then conducts an offline calculation to determine the significance of each operand. Subsequently, through a design space exploration, it employs a computation skipping approximation strategy based on the calculated significance. Our evaluation on an STM32-Nucleo board and 2 popular CNNs trained on the CIFAR-10 dataset shows that, compared to state-of-the-art exact inference, our Pareto optimal solutions can feature on average 21% latency reduction with no degradation in Top-1 classification accuracy, while for lower accuracy requirements, the corresponding reduction becomes even more pronounced.
Authors: Konstantinos Kevopoulos, Dongwei Ye
Abstract: Surrogate modelling is widely applied in computational science and engineering to mitigate computational efficiency issues for the real-time simulations of complex and large-scale computational models or for many-query scenarios, such as uncertainty quantification and design optimisation. In this work, we propose a parametric framework for kernel-based dynamic mode decomposition method based on the linear and nonlinear disambiguation optimization (LANDO) algorithm. The proposed parametric framework consists of two stages, offline and online. The offline stage prepares the essential component for prediction, namely a series of LANDO models that emulate the dynamics of the system with particular parameters from a training dataset. The online stage leverages those LANDO models to generate new data at a desired time instant, and approximate the mapping between parameters and the state with the data using deep learning techniques. Moreover, dimensionality reduction technique is applied to high-dimensional dynamical systems to reduce the computational cost of training. Three numerical examples including Lotka-Volterra model, heat equation and reaction-diffusion equation are presented to demonstrate the efficiency and effectiveness of the proposed framework.
Authors: Carlos E. Luis, Alessandro G. Bottero, Julia Vinogradska, Felix Berkenkamp, Jan Peters
Abstract: Optimal decision-making under partial observability requires reasoning about the uncertainty of the environment's hidden state. However, most reinforcement learning architectures handle partial observability with sequence models that have no internal mechanism to incorporate uncertainty in their hidden state representation, such as recurrent neural networks, deterministic state-space models and transformers. Inspired by advances in probabilistic world models for reinforcement learning, we propose a standalone Kalman filter layer that performs closed-form Gaussian inference in linear state-space models and train it end-to-end within a model-free architecture to maximize returns. Similar to efficient linear recurrent layers, the Kalman filter layer processes sequential data using a parallel scan, which scales logarithmically with the sequence length. By design, Kalman filter layers are a drop-in replacement for other recurrent layers in standard model-free architectures, but importantly they include an explicit mechanism for probabilistic filtering of the latent state representation. Experiments in a wide variety of tasks with partial observability show that Kalman filter layers excel in problems where uncertainty reasoning is key for decision-making, outperforming other stateful models.
Authors: \'Alvaro Fern\'andez Corral, Nicol\'as Mendoza, Armin Iske, Andrey Yachmenev, Jochen K\"upper
Abstract: We present a computational framework for obtaining multidimensional phase-space solutions of systems of non-linear coupled differential equations, using high-order implicit Runge-Kutta Physics- Informed Neural Networks (IRK-PINNs) schemes. Building upon foundational work originally solving differential equations for fields depending on coordinates [J. Comput. Phys. 378, 686 (2019)], we adapt the scheme to a context where the coordinates are treated as functions. This modification enables us to efficiently solve equations of motion for a particle in an external field. Our scheme is particularly useful for explicitly time-independent and periodic fields. We apply this approach to successfully solve the equations of motion for a mass particle placed in a central force field and a charged particle in a periodic electric field.
Authors: Lyudong Jin, Ming Tang, Jiayu Pan, Meng Zhang, Hao Wang
Abstract: In the realm of emerging real-time networked applications like cyber-physical systems (CPS), the Age of Information (AoI) has merged as a pivotal metric for evaluating the timeliness. To meet the high computational demands, such as those in intelligent manufacturing within CPS, mobile edge computing (MEC) presents a promising solution for optimizing computing and reducing AoI. In this work, we study the timeliness of computational-intensive updates and explores jointly optimize the task updating and offloading policies to minimize AoI. Specifically, we consider edge load dynamics and formulate a task scheduling problem to minimize the expected time-average AoI. The fractional objective introduced by AoI and the semi-Markov game nature of the problem render this challenge particularly difficult, with existing approaches not directly applicable. To this end, we present a comprehensive framework to fractional reinforcement learning (RL). We first introduce a fractional single-agent RL framework and prove its linear convergence. We then extend this to a fractional multi-agent RL framework with a convergence analysis. To tackle the challenge of asynchronous control in semi-Markov game, we further design an asynchronous model-free fractional multi-agent RL algorithm, where each device makes scheduling decisions with the hybrid action space without knowing the system dynamics and decisions of other devices. Experimental results show that our proposed algorithms reduce the average AoI by up to 52.6% compared with the best baseline algorithm in our experiments.
Authors: Ya Wen, Yulun Zhou
Abstract: Demographic data, such as income, education level, and employment rate, contain valuable information of urban regions, yet few studies have integrated demographic information to generate region embedding. In this study, we show how the simple and easy-to-access demographic data can improve the quality of state-of-the-art region embedding and provide better predictive performances in urban areas across three common urban tasks, namely check-in prediction, crime rate prediction, and house price prediction. We find that existing pre-train methods based on KL divergence are potentially biased towards mobility information and propose to use Jenson-Shannon divergence as a more appropriate loss function for multi-view representation learning. Experimental results from both New York and Chicago show that mobility + income is the best pre-train data combination, providing up to 10.22\% better predictive performances than existing models. Considering that mobility big data can be hardly accessible in many developing cities, we suggest geographic proximity + income to be a simple but effective data combination for region embedding pre-training.
Authors: Siyi Wang, Zifan Wang, Karl Henrik Johansson, Sandra Hirche
Abstract: In real-world scenarios, the impacts of decisions may not manifest immediately. Taking these delays into account facilitates accurate assessment and management of risk in real-world environments, thereby ensuring the efficacy of strategies. In this paper, we investigate risk-averse learning using Conditional Value at Risk (CVaR) as risk measure, while incorporating delayed feedback with unknown but bounded delays. We develop two risk-averse learning algorithms that rely on one-point and two-point zeroth-order optimization approaches, respectively. The regret achieved by the algorithms is analyzed in terms of the cumulative delay and the number of total samplings. The results suggest that the two-point risk-averse learning achieves a smaller regret bound than the one-point algorithm. Furthermore, the one-point risk-averse learning algorithm attains sublinear regret under certain delay conditions, and the two-point risk-averse learning algorithm achieves sublinear regret with minimal restrictions on the delay. We provide numerical experiments on a dynamic pricing problem to demonstrate the performance of the proposed algorithms.
Authors: Agni Bandyopadhyay, Guenther Waxenegger-Wilfing
Abstract: This research introduces a novel application of a masked Proximal Policy Optimization (PPO) algorithm from the field of deep reinforcement learning (RL), for determining the most efficient sequence of space debris visitation, utilizing the Lambert solver as per Izzo's adaptation for individual rendezvous. The aim is to optimize the sequence in which all the given debris should be visited to get the least total time for rendezvous for the entire mission. A neural network (NN) policy is developed, trained on simulated space missions with varying debris fields. After training, the neural network calculates approximately optimal paths using Izzo's adaptation of Lambert maneuvers. Performance is evaluated against standard heuristics in mission planning. The reinforcement learning approach demonstrates a significant improvement in planning efficiency by optimizing the sequence for debris rendezvous, reducing the total mission time by an average of approximately {10.96\%} and {13.66\%} compared to the Genetic and Greedy algorithms, respectively. The model on average identifies the most time-efficient sequence for debris visitation across various simulated scenarios with the fastest computational speed. This approach signifies a step forward in enhancing mission planning strategies for space debris clearance.
Authors: Yalan Qin, Nan Pu, Hanzhou Wu, Nicu Sebe
Abstract: Multi-view clustering aims to study the complementary information across views and discover the underlying structure. For solving the relatively high computational cost for the existing approaches, works based on anchor have been presented recently. Even with acceptable clustering performance, these methods tend to map the original representation from multiple views into a fixed shared graph based on the original dataset. However, most studies ignore the discriminative property of the learned anchors, which ruin the representation capability of the built model. Moreover, the complementary information among anchors across views is neglected to be ensured by simply learning the shared anchor graph without considering the quality of view-specific anchors. In this paper, we propose discriminative anchor learning for multi-view clustering (DALMC) for handling the above issues. We learn discriminative view-specific feature representations according to the original dataset and build anchors from different views based on these representations, which increase the quality of the shared anchor graph. The discriminative feature learning and consensus anchor graph construction are integrated into a unified framework to improve each other for realizing the refinement. The optimal anchors from multiple views and the consensus anchor graph are learned with the orthogonal constraints. We give an iterative algorithm to deal with the formulated problem. Extensive experiments on different datasets show the effectiveness and efficiency of our method compared with other methods.
Authors: Akiyoshi Sannai, Yuuki Takai, Matthieu Cordonnier
Abstract: In this paper, we develop a theory about the relationship between invariant and equivariant maps with regard to a group $G$. We then leverage this theory in the context of deep neural networks with group symmetries in order to obtain novel insight into their mechanisms. More precisely, we establish a one-to-one relationship between equivariant maps and certain invariant maps. This allows us to reduce arguments for equivariant maps to those for invariant maps and vice versa. As an application, we propose a construction of universal equivariant architectures built from universal invariant networks. We, in turn, explain how the universal architectures arising from our construction differ from standard equivariant architectures known to be universal. Furthermore, we explore the complexity, in terms of the number of free parameters, of our models, and discuss the relation between invariant and equivariant networks' complexity. Finally, we also give an approximation rate for G-equivariant deep neural networks with ReLU activation functions for finite group G.
Authors: MaryBeth Defrance, Maarten Buyl, Tijl De Bie
Abstract: Numerous methods have been implemented that pursue fairness with respect to sensitive features by mitigating biases in machine learning. Yet, the problem settings that each method tackles vary significantly, including the stage of intervention, the composition of sensitive features, the fairness notion, and the distribution of the output. Even in binary classification, these subtle differences make it highly complicated to benchmark fairness methods, as their performance can strongly depend on exactly how the bias mitigation problem was originally framed. Hence, we introduce ABCFair, a benchmark approach which allows adapting to the desiderata of the real-world problem setting, enabling proper comparability between methods for any use case. We apply ABCFair to a range of pre-, in-, and postprocessing methods on both large-scale, traditional datasets and on a dual label (biased and unbiased) dataset to sidestep the fairness-accuracy trade-off.
Authors: Jeffrey Redondo, Nauman Aslam, Juan Zhang, Zhenhui Yuan
Abstract: Nowadays, many machine learning (ML) solutions to improve the wireless standard IEEE802.11p for Vehicular Adhoc Network (VANET) are commonly evaluated in the simulated world. At the same time, this approach could be cost-effective compared to real-world testing due to the high cost of vehicles. There is a risk of unexpected outcomes when these solutions are implemented in the real world, potentially leading to wasted resources. To mitigate this challenge, the hardware-in-the-loop is the way to move forward as it enables the opportunity to test in the real world and simulated worlds together. Therefore, we have developed what we believe is the pioneering hardware-in-the-loop for testing artificial intelligence, multiple services, and HD map data (LiDAR), in both simulated and real-world settings.
Authors: Eddie Seabrook, Laurenz Wiskott
Abstract: (This is a work in progress. Feedback is welcome) An analytical comparison is made between slow feature analysis (SFA) and the successor representation (SR). While SFA and the SR stem from distinct areas of machine learning, they share important properties, both in terms of their mathematics and the types of information they are sensitive to. This work studies their connection along these two axes. In particular, multiple variants of the SFA algorithm are explored analytically and then applied to the setting of an MDP, leading to a family of eigenvalue problems involving the SR and other related quantities. These resulting eigenvalue problems are then illustrated in the toy setting of a gridworld, where it is demonstrated that the place- and grid-like fields often associated to the SR can equally be generated using SFA.
Authors: Shimao Chen, Zirui Liu, Zhiying Wu, Ce Zheng, Peizhuang Cong, Zihan Jiang, Lei Su, Tong Yang
Abstract: As the foundation of large language models (LLMs), self-attention module faces the challenge of quadratic time and memory complexity with respect to sequence length. FlashAttention accelerates attention computation and reduces its memory usage by leveraging the GPU memory hierarchy. A promising research direction is to integrate FlashAttention with quantization methods. This paper introduces INT-FlashAttention, the first INT8 quantization architecture compatible with the forward workflow of FlashAttention, which significantly improves the inference speed of FlashAttention on Ampere GPUs. We implement our INT-FlashAttention prototype with fully INT8 activations and general matrix-multiplication (GEMM) kernels, making it the first attention operator with fully INT8 input. As a general token-level post-training quantization framework, INT-FlashAttention is also compatible with other data formats like INT4, etc. Experimental results show INT-FlashAttention achieves 72% faster inference speed and 82% smaller quantization error compared to standard FlashAttention with FP16 and FP8 data format.
Authors: Jiayu Li, Zilong Zhao, Kevin Yee, Uzair Javaid, Biplab Sikdar
Abstract: The activation functions are fundamental to neural networks as they introduce non-linearity into data relationships, thereby enabling deep networks to approximate complex data relations. Existing efforts to enhance neural network performance have predominantly focused on developing new mathematical functions. However, we find that a well-designed combination of existing activation functions within a neural network can also achieve this objective. In this paper, we introduce the Combined Units activation (CombU), which employs different activation functions at various dimensions across different layers. This approach can be theoretically proven to fit most mathematical expressions accurately. The experiments conducted on four mathematical expression datasets, compared against six State-Of-The-Art (SOTA) activation function algorithms, demonstrate that CombU outperforms all SOTA algorithms in 10 out of 16 metrics and ranks in the top three for the remaining six metrics.
Authors: Ivi Chatzi, Nina Corvelo Benz, Eleni Straitouri, Stratis Tsirtsis, Manuel Gomez-Rodriguez
Abstract: "Sure, I am happy to generate a story for you: Captain Lyra stood at the helm of her trusty ship, the Maelstrom's Fury, gazing out at the endless sea. [...] Lyra's eyes welled up with tears as she realized the bitter truth - she had sacrificed everything for fleeting riches, and lost the love of her crew, her family, and herself." Although this story, generated by a large language model, is captivating, one may wonder -- how would the story have unfolded if the model had chosen "Captain Maeve" as the protagonist instead? We cannot know. State-of-the-art large language models are stateless -- they maintain no internal memory or state. Given a prompt, they generate a sequence of tokens as an output using an autoregressive process. As a consequence, they cannot reason about counterfactual alternatives to tokens they have generated in the past. In this work, our goal is to enhance them with this functionality. To this end, we develop a causal model of token generation that builds upon the Gumbel-Max structural causal model. Our model allows any large language model to perform counterfactual token generation at almost no cost in comparison with vanilla token generation, it is embarrassingly simple to implement, and it does not require any fine-tuning nor prompt engineering. We implement our model on Llama 3 8B-instruct and conduct both qualitative and quantitative analyses of counterfactually generated text. We conclude with a demonstrative application of counterfactual token generation for bias detection, unveiling interesting insights about the model of the world constructed by large language models.
Authors: Sivaram Krishnan, Jihong Park, Gregory Sherman, Benjamin Campbell, Jinho Choi
Abstract: Low Probability of Detection (LPD) communication aims to obscure the presence of radio frequency (RF) signals to evade surveillance. In the context of mobile surveillance utilizing unmanned aerial vehicles (UAVs), achieving LPD communication presents significant challenges due to the UAVs' rapid and continuous movements, which are characterized by unknown nonlinear dynamics. Therefore, accurately predicting future locations of UAVs is essential for enabling real-time LPD communication. In this paper, we introduce a novel framework termed predictive covert communication, aimed at minimizing detectability in terrestrial ad-hoc networks under multi-UAV surveillance. Our data-driven method synergistically integrates graph neural networks (GNN) with Koopman theory to model the complex interactions within a multi-UAV network and facilitating long-term predictions by linearizing the dynamics, even with limited historical data. Extensive simulation results substantiate that the predicted trajectories using our method result in at least 63%-75% lower probability of detection when compared to well-known state-of-the-art baseline approaches, showing promise in enabling low-latency covert operations in practical scenarios.
Authors: Ved Prakash, Kartavya Kothari
Abstract: Dream11 is a fantasy sports platform that allows users to create their own virtual teams for real-life sports events. We host multiple sports and matches for our 200M+ user base. In this RMG (real money gaming) setting, users pay an entry amount to participate in various contest products that we provide to users. In our current work, we discuss the problem of predicting the user's propensity to spend in a gaming round, so it can be utilized for various downstream applications. e.g. Upselling users by incentivizing them marginally as per their spending propensity, or personalizing the product listing based on the user's propensity to spend. We aim to model the spending propensity of each user based on past transaction data. In this paper, we benchmark tree-based and deep-learning models that show good results on structured data, and we propose a new architecture change that is specifically designed to capture the rich interactions among the input features. We show that our proposed architecture outperforms the existing models on the task of predicting the user's propensity to spend in a gaming round. Our new transformer model surpasses the state-of-the-art FT-Transformer, improving MAE by 2.5\% and MSE by 21.8\%.
Authors: Dongfang Sun, Yingzhen Yang
Abstract: Sparse graphs built by sparse representation has been demonstrated to be effective in clustering high-dimensional data. Albeit the compelling empirical performance, the vanilla sparse graph ignores the geometric information of the data by performing sparse representation for each datum separately. In order to obtain a sparse graph aligned with the local geometric structure of data, we propose a novel Support Regularized Sparse Graph, abbreviated as SRSG, for data clustering. SRSG encourages local smoothness on the neighborhoods of nearby data points by a well-defined support regularization term. We propose a fast proximal gradient descent method to solve the non-convex optimization problem of SRSG with the convergence matching the Nesterov's optimal convergence rate of first-order methods on smooth and convex objective function with Lipschitz continuous gradient. Extensive experimental results on various real data sets demonstrate the superiority of SRSG over other competing clustering methods.
Authors: Ian Colbert, Fabian Grob, Giuseppe Franco, Jinjie Zhang, Rayan Saab
Abstract: Several recent studies have investigated low-precision accumulation, reporting improvements in throughput, power, and area across various platforms. However, the accompanying proposals have only considered the quantization-aware training (QAT) paradigm, in which models are fine-tuned or trained from scratch with quantization in the loop. As models continue to grow in size, QAT techniques become increasingly more expensive, which has motivated the recent surge in post-training quantization (PTQ) research. To the best of our knowledge, ours marks the first formal study of accumulator-aware quantization in the PTQ setting. To bridge this gap, we introduce AXE, a practical framework of accumulator-aware extensions designed to endow overflow avoidance guarantees to existing layer-wise PTQ algorithms. We theoretically motivate AXE and demonstrate its flexibility by implementing it on top of two state-of-the-art PTQ algorithms: GPFQ and OPTQ. We further generalize AXE to support multi-stage accumulation for the first time, opening the door for full datapath optimization and scaling to large language models (LLMs). We evaluate AXE across image classification and language generation models, and observe significant improvements in the trade-off between accumulator bit width and model accuracy over baseline methods.
Authors: Jett Janiak, Jacek Karwowski, Chatrik Singh Mangat, Giorgi Giglemiani, Nora Petrova, Stefan Heimersheim
Abstract: We identify "stable regions" in the residual stream of Transformers, where the model's output remains insensitive to small activation changes, but exhibits high sensitivity at region boundaries. These regions emerge during training and become more defined as training progresses or model size increases. The regions appear to be much larger than previously studied polytopes. Our analysis suggests that these stable regions align with semantic distinctions, where similar prompts cluster within regions, and activations from the same region lead to similar next token predictions.
Authors: Yao Ni, Shan Zhang, Piotr Koniusz
Abstract: Parameter-Efficient Fine-Tuning (PEFT) effectively adapts pre-trained vision transformers to downstream tasks. However, the optimization for tasks performance often comes at the cost of generalizability in fine-tuned models. To address this issue, we theoretically connect smaller weight gradient norms during training and larger datasets to the improved model generalization. Motivated by this connection, we propose reducing gradient norms for enhanced generalization and aligning fine-tuned model with the pre-trained counterpart to retain knowledge from large-scale pre-training data. Yet, naive alignment does not guarantee gradient reduction and can potentially cause gradient explosion, complicating efforts to manage gradients. To address such issues, we propose PACE, marrying generalization of PArameter-efficient fine-tuning with Consistency rEgularization. We perturb features learned from the adapter with the multiplicative noise and ensure the fine-tuned model remains consistent for same sample under different perturbations. Theoretical analysis shows that PACE not only implicitly regularizes gradients for enhanced generalization, but also implicitly aligns the fine-tuned and pre-trained models to retain knowledge. Experimental evidence supports our theories. PACE outperforms existing PEFT methods in four visual adaptation tasks: VTAB-1k, FGVC, few-shot learning and domain adaptation. Code will be available at https://github.com/MaxwellYaoNi/PACE
Authors: Francisco Aguilera-Mart\'inez, Fernando Berzal
Abstract: Training machine learning models based on neural networks requires large datasets, which may contain sensitive information. The models, however, should not expose private information from these datasets. Differentially private SGD [DP-SGD] requires the modification of the standard stochastic gradient descent [SGD] algorithm for training new models. In this short paper, a novel regularization strategy is proposed to achieve the same goal in a more efficient manner.
Authors: Weimin Xiong, Yifan Song, Xiutian Zhao, Wenhao Wu, Xun Wang, Ke Wang, Cheng Li, Wei Peng, Sujian Li
Abstract: Large language model agents have exhibited exceptional performance across a range of complex interactive tasks. Recent approaches have utilized tuning with expert trajectories to enhance agent performance, yet they primarily concentrate on outcome rewards, which may lead to errors or suboptimal actions due to the absence of process supervision signals. In this paper, we introduce the Iterative step-level Process Refinement (IPR) framework, which provides detailed step-by-step guidance to enhance agent training. Specifically, we adopt the Monte Carlo method to estimate step-level rewards. During each iteration, the agent explores along the expert trajectory and generates new actions. These actions are then evaluated against the corresponding step of expert trajectory using step-level rewards. Such comparison helps identify discrepancies, yielding contrastive action pairs that serve as training data for the agent. Our experiments on three complex agent tasks demonstrate that our framework outperforms a variety of strong baselines. Moreover, our analytical findings highlight the effectiveness of IPR in augmenting action efficiency and its applicability to diverse models.
Authors: Md Ferdous Alam, Faez Ahmed
Abstract: The creation of manufacturable and editable 3D shapes through Computer-Aided Design (CAD) remains a highly manual and time-consuming task, hampered by the complex topology of boundary representations of 3D solids and unintuitive design tools. This paper introduces GenCAD, a generative model that employs autoregressive transformers and latent diffusion models to transform image inputs into parametric CAD command sequences, resulting in editable 3D shape representations. GenCAD integrates an autoregressive transformer-based architecture with a contrastive learning framework, enhancing the generation of CAD programs from input images and providing a representation learning framework for multiple data modalities relevant to engineering designs. Extensive evaluations demonstrate that GenCAD significantly outperforms existing state-of-the-art methods in terms of the precision and modifiability of generated 3D shapes. Notably, GenCAD shows a marked improvement in the accuracy of 3D shape generation for long sequences, supporting its application in complex design tasks. Additionally, the contrastive embedding feature of GenCAD facilitates the retrieval of CAD models using image queries from databases which is a critical challenge within the CAD community. While most work in the 3D shape generation literature focuses on representations like meshes, voxels, or point clouds, practical engineering applications demand modifiability and the ability for multi-modal conditional generation. Our results provide a significant step forward in this direction, highlighting the potential of generative models to expedite the entire design-to-production pipeline and seamlessly integrate different design modalities.
Authors: Andy T. Liu, Yi-Cheng Lin, Haibin Wu, Stefan Winkler, Hung-yi Lee
Abstract: Despite their impressive success, training foundation models remains computationally costly. This paper investigates how to efficiently train speech foundation models with self-supervised learning (SSL) under a limited compute budget. We examine critical factors in SSL that impact the budget, including model architecture, model size, and data size. Our goal is to make analytical steps toward understanding the training dynamics of speech foundation models. We benchmark SSL objectives in an entirely comparable setting and find that other factors contribute more significantly to the success of SSL. Our results show that slimmer model architectures outperform common small architectures under the same compute and parameter budget. We demonstrate that the size of the pre-training data remains crucial, even with data augmentation during SSL training, as performance suffers when iterating over limited data. Finally, we identify a trade-off between model size and data size, highlighting an optimal model size for a given compute budget.
Authors: Yannick Vogt, Mehdi Naouar, Maria Kalweit, Christoph Cornelius Miething, Justus Duyster, Joschka Boedecker, Gabriel Kalweit
Abstract: Antibodies offer great potential for the treatment of various diseases. However, the discovery of therapeutic antibodies through traditional wet lab methods is expensive and time-consuming. The use of generative models in designing antibodies therefore holds great promise, as it can reduce the time and resources required. Recently, the class of diffusion models has gained considerable traction for their ability to synthesize diverse and high-quality samples. In their basic form, however, they lack mechanisms to optimize for specific properties, such as binding affinity to an antigen. In contrast, the class of offline Reinforcement Learning (RL) methods has demonstrated strong performance in navigating large search spaces, including scenarios where frequent real-world interaction, such as interaction with a wet lab, is impractical. Our novel method, BetterBodies, which combines Variational Autoencoders (VAEs) with RL guided latent diffusion, is able to generate novel sets of antibody CDRH3 sequences from different data distributions. Using the Absolut! simulator, we demonstrate the improved affinity of our novel sequences to the SARS-CoV spike receptor-binding domain. Furthermore, we reflect biophysical properties in the VAE latent space using a contrastive loss and add a novel Q-function based filtering to enhance the affinity of generated sequences. In conclusion, methods such as ours have the potential to have great implications for real-world biological sequence design, where the generation of novel high-affinity binders is a cost-intensive endeavor.
Authors: Xingpeng Xia, Jason J. Choi, Ayush Agrawal, Koushil Sreenath, Claire J. Tomlin, Somil Bansal
Abstract: Learning-based approaches have recently shown notable success in legged locomotion. However, these approaches often lack accountability, necessitating empirical tests to determine their effectiveness. In this work, we are interested in designing a learning-based locomotion controller whose stability can be examined and guaranteed. This can be achieved by verifying regions of attraction (RoAs) of legged robots to their stable walking gaits. This is a non-trivial problem for legged robots due to their hybrid dynamics. Although previous work has shown the utility of Hamilton-Jacobi (HJ) reachability to solve this problem, its practicality was limited by its poor scalability. The core contribution of our work is the employment of a deep learning-based HJ reachability solution to the hybrid legged robot dynamics, which overcomes the previous work's limitation. With the learned reachability solution, first, we can estimate a library of RoAs for various gaits. Second, we can design a one-step predictive controller that effectively stabilizes to an individual gait within the verified RoA. Finally, we can devise a strategy that switches gaits, in response to external perturbations, whose feasibility is guided by the RoA analysis. We demonstrate our method in a two-link walker simulation, whose mathematical model is well established. Our method achieves improved stability than previous model-based methods, while ensuring transparency that was not present in the existing learning-based approaches.
Authors: Teresa Dorszewski, Albert Kj{\o}ller Jacobsen, Lenka T\v{e}tkov\'a, Lars Kai Hansen
Abstract: Self-supervised speech representation models, particularly those leveraging transformer architectures, have demonstrated remarkable performance across various tasks such as speech recognition, speaker identification, and emotion detection. Recent studies on transformer models revealed a high redundancy between layers and the potential for significant pruning, which we will investigate here for transformer-based speech representation models. We perform a detailed analysis of layer similarity in speech representation models using three similarity metrics: cosine similarity, centered kernel alignment, and mutual nearest-neighbor alignment. Our findings reveal a block-like structure of high similarity, suggesting two main processing steps and significant redundancy of layers. We demonstrate the effectiveness of pruning transformer-based speech representation models without the need for post-training, achieving up to 40% reduction in transformer layers while maintaining over 95% of the model's predictive capacity. Furthermore, we employ a knowledge distillation method to substitute the entire transformer stack with mimicking layers, reducing the network size 95-98% and the inference time by up to 94%. This substantial decrease in computational load occurs without considerable performance loss, suggesting that the transformer stack is almost completely redundant for downstream applications of speech representation models.
Authors: Luis Gustavo Gioacon Villani, Samuel da Silva, Americo Cunha Jr, Michael D. Todd
Abstract: The damage detection problem becomes a more difficult task when the intrinsically nonlinear behavior of the structures and the natural data variation are considered in the analysis because both phenomena can be confused with damage if linear and deterministic approaches are implemented. Therefore, this work aims the experimental application of a stochastic version of the Volterra series combined with a novelty detection approach to detect damage in an initially nonlinear system taking into account the measured data variation, caused by the presence of uncertainties. The experimental setup is composed by a cantilever beam operating in a nonlinear regime of motion, even in the healthy condition, induced by the presence of a magnet near to the free extremity. The damage associated with mass changes in a bolted connection (nuts loosed) is detected based on the comparison between linear and nonlinear contributions of the stochastic Volterra kernels in the total response, estimated in the reference and damaged conditions. The experimental measurements were performed on different days to add natural variation to the data measured. The results obtained through the stochastic proposed approach are compared with those obtained by the deterministic version of the Volterra series, showing the advantage of the stochastic model use when we consider the experimental data variation with the capability to detect the presence of the damage with statistical confidence. Besides, the nonlinear metric used presented a higher sensitivity to the occurrence of the damage compared with the linear one, justifying the application of a nonlinear metric when the system exhibits intrinsically nonlinear behavior.
Authors: Teerapong Panboonyuen
Abstract: Forecasting sea surface currents is essential for applications such as maritime navigation, environmental monitoring, and climate analysis, particularly in regions like the Gulf of Thailand and the Andaman Sea. This paper introduces SEA-ViT, an advanced deep learning model that integrates Vision Transformer (ViT) with bidirectional Gated Recurrent Units (GRUs) to capture spatio-temporal covariance for predicting sea surface currents (U, V) using high-frequency radar (HF) data. The name SEA-ViT is derived from ``Sea Surface Currents Forecasting using Vision Transformer,'' highlighting the model's emphasis on ocean dynamics and its use of the ViT architecture to enhance forecasting capabilities. SEA-ViT is designed to unravel complex dependencies by leveraging a rich dataset spanning over 30 years and incorporating ENSO indices (El Ni\~no, La Ni\~na, and neutral phases) to address the intricate relationship between geographic coordinates and climatic variations. This development enhances the predictive capabilities for sea surface currents, supporting the efforts of the Geo-Informatics and Space Technology Development Agency (GISTDA) in Thailand's maritime regions. The code and pretrained models are available at \url{https://github.com/kaopanboonyuen/gistda-ai-sea-surface-currents}.
URLs: https://github.com/kaopanboonyuen/gistda-ai-sea-surface-currents
Authors: K. R. Schuurman, A. Meyer
Abstract: Accurate estimates of surface solar irradiance (SSI) are essential for solar resource assessments and solar energy forecasts in grid integration and building control applications. SSI estimates for spatially extended regions can be retrieved from geostationary satellites such as Meteosat. Traditional SSI satellite retrievals like Heliosat rely on physical radiative transfer modelling. We introduce the first machine-learning-based satellite retrieval for instantaneous SSI and demonstrate its capability to provide accurate and generalizable SSI estimates across Europe. Our deep learning retrieval provides near real-time SSI estimates based on data-driven emulation of Heliosat and fine-tuning on pyranometer networks. By including SSI from ground stations, our SSI retrieval model can outperform Heliosat accuracy and generalize well to regions with other climates and surface albedos in cloudy conditions (clear-sky index < 0.8). We also show that the SSI retrieved from Heliosat exhibits large biases in mountain regions, and that training and fine-tuning our retrieval models on SSI data from ground stations strongly reduces these biases, outperforming Heliosat. Furthermore, we quantify the relative importance of the Meteosat channels and other predictor variables like solar zenith angle for the accuracy of our deep learning SSI retrieval model in different cloud conditions. We find that in cloudy conditions multiple near-infrared and infrared channels enhance the performance. Our results can facilitate the development of more accurate satellite retrieval models of surface solar irradiance.
Authors: Syed Muhammad Aqdas Rizvi
Abstract: This literature review surveys the advancements of keyword spotting (KWS) technologies, specifically focusing on Urdu, Pakistan's low-resource language (LRL), which has complex phonetics. Despite the global strides in speech technology, Urdu presents unique challenges requiring more tailored solutions. The review traces the evolution from foundational Gaussian Mixture Models to sophisticated neural architectures like deep neural networks and transformers, highlighting significant milestones such as integrating multi-task learning and self-supervised approaches that leverage unlabeled data. It examines emerging technologies' role in enhancing KWS systems' performance within multilingual and resource-constrained settings, emphasizing the need for innovations that cater to languages like Urdu. Thus, this review underscores the need for context-specific research addressing the inherent complexities of Urdu and similar URLs and the means of regions communicating through such languages for a more inclusive approach to speech technology.
Authors: Suwichaya Suwanwimolkul, Natanon Tongamrak, Nuttamon Thungka, Naebboon Hoonchareon, Jitkomut Songsiri
Abstract: This paper presents an online platform that shows Thailand's solar irradiance map every 30 minutes. It is available at https://www.cusolarforecast.com. The methodology for estimating global horizontal irradiance (GHI) across Thailand relies on cloud index extracted from Himawari-8 satellite imagery, Ineichen clear-sky model with locally-tuned Linke turbidity, and machine learning models. The methods take clear-sky irradiance, cloud index, re-analyzed GHI and temperature data from the MERRA-2 database, and date-time as inputs for GHI estimation models, including LightGBM, LSTM, Informer, and Transformer. These are benchmarked with the estimate from the SolCast service by evaluation of 15-minute ground GHI data from 53 ground stations over 1.5 years during 2022-2023. The results show that the four models have competitive performances and outperform the SolCast service. The best model is LightGBM, with an MAE of 78.58 W/sqm and RMSE of 118.97 W/sqm. Obtaining re-analyzed MERRA-2 data for Thailand is not economically feasible for deployment. When removing these features, the Informer model has a winning performance of 78.67 W/sqm in MAE. The obtained performance aligns with existing literature by taking the climate zone and time granularity of data into consideration. As the map shows an estimate of GHI over 93,000 grids with a frequent update, the paper also describes a computational framework for displaying the entire map. It tests the runtime performance of deep learning models in the GHI estimation process.
Authors: Junchao Gong, Tao Han, Kang Chen, Lei Bai
Abstract: Numerical Weather Prediction (NWP) system is an infrastructure that exerts considerable impacts on modern society.Traditional NWP system, however, resolves it by solving complex partial differential equations with a huge computing cluster, resulting in tons of carbon emission. Exploring efficient and eco-friendly solutions for NWP attracts interest from Artificial Intelligence (AI) and earth science communities. To narrow the performance gap between the AI-based methods and physic predictor, this work proposes a new transformer-based NWP framework, termed as WeatherFormer, to model the complex spatio-temporal atmosphere dynamics and empowering the capability of data-driven NWP. WeatherFormer innovatively introduces the space-time factorized transformer blocks to decrease the parameters and memory consumption, in which Position-aware Adaptive Fourier Neural Operator (PAFNO) is proposed for location sensible token mixing. Besides, two data augmentation strategies are utilized to boost the performance and decrease training consumption. Extensive experiments on WeatherBench dataset show WeatherFormer achieves superior performance over existing deep learning methods and further approaches the most advanced physical model.
Authors: Jiawen Kang, Dongrui Han, Lingwei Meng, Jingyan Zhou, Jinchao Li, Xixin Wu, Helen Meng
Abstract: Alzheimer's Disease (AD) detection has emerged as a promising research area that employs machine learning classification models to distinguish between individuals with AD and those without. Unlike conventional classification tasks, we identify within-class variation as a critical challenge in AD detection: individuals with AD exhibit a spectrum of cognitive impairments. Given that many AD detection tasks lack fine-grained labels, simplistic binary classification may overlook two crucial aspects: within-class differences and instance-level imbalance. The former compels the model to map AD samples with varying degrees of impairment to a single diagnostic label, disregarding certain changes in cognitive function. While the latter biases the model towards overrepresented severity levels. This work presents early efforts to address these challenges. We propose two novel methods: Soft Target Distillation (SoTD) and Instance-level Re-balancing (InRe), targeting two problems respectively. Experiments on the ADReSS and ADReSSo datasets demonstrate that the proposed methods significantly improve detection accuracy. Further analysis reveals that SoTD effectively harnesses the strengths of multiple component models, while InRe substantially alleviates model over-fitting. These findings provide insights for developing more robust and reliable AD detection models.
Authors: David Narganes-Carlon, Anniek Myatt, Mani Mudaliar, Daniel J. Crowther
Abstract: Target selection is crucial in pharmaceutical drug discovery, directly influencing clinical trial success. Despite its importance, drug development remains resource-intensive, often taking over a decade with significant financial costs. High failure rates highlight the need for better early-stage target selection. We present GATher, a graph attention network designed to predict therapeutic gene-disease links by integrating data from diverse biomedical sources into a graph with over 4.4 million edges. GATher incorporates GATv3, a novel graph attention convolution layer, and GATv3HeteroConv, which aggregates transformations for each edge type, enhancing its ability to manage complex interactions within this extensive dataset. Utilizing hard negative sampling and multi-task pre-training, GATher addresses topological imbalances and improves specificity. Trained on data up to 2018 and evaluated through 2024, our results show GATher predicts clinical trial outcomes with a ROC AUC of 0.69 for unmet efficacy failures and 0.79 for positive efficacy. Feature attribution methods, using Captum, highlight key nodes and relationships, enhancing model interpretability. By 2024, GATher improved precision in prioritizing the top 200 clinical trial targets to 14.1%, an absolute increase of over 3.5% compared to other methods. GATher outperforms existing models like GAT, GATv2, and HGT in predicting clinical trial outcomes, demonstrating its potential in enhancing target validation and predicting clinical efficacy and safety.
Authors: Stanislav Koz\'ak
Abstract: Radiomics is a relatively new field which utilises automatically identified features from radiological scans. It has found a widespread application, particularly in oncology because many of the important oncological biomarkers are not visible to the naked eye. The recent advent of big data, including in medical imaging, and the development of new ML techniques brought the possibility of faster and more accurate oncological diagnosis. Furthermore, standardised mathematical feature extraction based on radiomics helps to eliminate possible radiologist bias. This paper reviews the recent development in the oncological use of MRI radiomic features. It focuses on the identification of the isocitrate dehydrogenase (IDH) mutation status, which is an important biomarker for the diagnosis of glioblastoma and grade IV astrocytoma.
Authors: Jiaxing Yang
Abstract: Structural prediction has long been considered critical in RNA research, especially following the success of AlphaFold2 in protein studies, which has drawn significant attention to the field. While recent advances in machine learning and data accumulation have effectively addressed many biological tasks, particularly in protein related research. RNA structure prediction remains a significant challenge due to data limitations. Obtaining RNA structural data is difficult because traditional methods such as nuclear magnetic resonance spectroscopy, Xray crystallography, and electron microscopy are expensive and time consuming. Although several RNA 3D structure prediction methods have been proposed, their accuracy is still limited. Predicting RNA structural information at another level, such as distance maps, remains highly valuable. Distance maps provide a simplified representation of spatial constraints between nucleotides, capturing essential relationships without requiring a full 3D model. This intermediate level of structural information can guide more accurate 3D modeling and is computationally less intensive, making it a useful tool for improving structural predictions. In this work, we demonstrate that using only primary sequence information, we can accurately infer the distances between RNA bases by utilizing a large pretrained RNA language model coupled with a well trained downstream transformer.
Authors: Samuele Grossi, Marco Letizia, Riccardo Torre
Abstract: We propose a robust methodology to evaluate the performance and computational efficiency of non-parametric two-sample tests, specifically designed for high-dimensional generative models in scientific applications such as in particle physics. The study focuses on tests built from univariate integral probability measures: the sliced Wasserstein distance and the mean of the Kolmogorov-Smirnov statistics, already discussed in the literature, and the novel sliced Kolmogorov-Smirnov statistic. These metrics can be evaluated in parallel, allowing for fast and reliable estimates of their distribution under the null hypothesis. We also compare these metrics with the recently proposed unbiased Fr\'echet Gaussian Distance and the unbiased quadratic Maximum Mean Discrepancy, computed with a quartic polynomial kernel. We evaluate the proposed tests on various distributions, focusing on their sensitivity to deformations parameterized by a single parameter $\epsilon$. Our experiments include correlated Gaussians and mixtures of Gaussians in 5, 20, and 100 dimensions, and a particle physics dataset of gluon jets from the JetNet dataset, considering both jet- and particle-level features. Our results demonstrate that one-dimensional-based tests provide a level of sensitivity comparable to other multivariate metrics, but with significantly lower computational cost, making them ideal for evaluating generative models in high-dimensional settings. This methodology offers an efficient, standardized tool for model comparison and can serve as a benchmark for more advanced tests, including machine-learning-based approaches.
Authors: Yuezhou Zhang, Callum Stewart, Yatharth Ranjan, Pauline Conde, Heet Sankesara, Zulqarnain Rashid, Shaoxiong Sun, Richard J B Dobson, Amos A Folarin
Abstract: Digital phenotyping offers a novel and cost-efficient approach for managing depression and anxiety. Previous studies, often limited to small-to-medium or specific populations, may lack generalizability. We conducted a cross-sectional analysis of data from 10,129 participants recruited from a UK-based general population between June 2020 and August 2022. Participants shared wearable (Fitbit) data and self-reported questionnaires on depression (PHQ-8), anxiety (GAD-7), and mood via a study app. We first examined the correlations between PHQ-8/GAD-7 scores and wearable-derived features, demographics, health data, and mood assessments. Subsequently, unsupervised clustering was used to identify behavioural patterns associated with depression or anxiety. Finally, we employed separate XGBoost models to predict depression and anxiety and compared the results using different subsets of features. We observed significant associations between the severity of depression and anxiety with several factors, including mood, age, gender, BMI, sleep patterns, physical activity, and heart rate. Clustering analysis revealed that participants simultaneously exhibiting lower physical activity levels and higher heart rates reported more severe symptoms. Prediction models incorporating all types of variables achieved the best performance ($R^2$=0.41, MAE=3.42 for depression; $R^2$=0.31, MAE=3.50 for anxiety) compared to those using subsets of variables. This study identified potential indicators for depression and anxiety, highlighting the utility of digital phenotyping and machine learning technologies for rapid screening of mental disorders in general populations. These findings provide robust real-world insights for future healthcare applications.
Authors: Palaash Agrawal, Hari Om Bansal, Aditya R. Gautam, Om Prakash Mahela, Baseem Khan
Abstract: This paper proposes an improved deep learning based maximum power point tracking (MPPT) in solar photovoltaic cells considering various time series based environmental inputs. Generally, artificial neural network based MPPT algorithms use basic neural network architectures and inputs which do not represent the ambient conditions in a comprehensive manner. In this article, the ambient conditions of a location are represented through a comprehensive set of environmental features. Furthermore, the inclusion of time based features in the input data is considered to model cyclic patterns temporally within the atmospheric conditions leading to robust modeling of the MPPT algorithm. A transformer based deep learning architecture is trained as a time series prediction model using multidimensional time series input features. The model is trained on a dataset containing typical meteorological year data points of ambient weather conditions from 50 locations. The attention mechanism in the transformer modules allows the model to learn temporal patterns in the data efficiently. The proposed model achieves a 0.47% mean average percentage error of prediction on non zero operating voltage points in a test dataset consisting of data collected over a period of 200 consecutive hours resulting in the average power efficiency of 99.54% and peak power efficiency of 99.98%. The proposed model is validated through real time simulations. The proposed model performs power point tracking in a robust, dynamic, and nonlatent manner, over a wide range of atmospheric conditions.
Authors: Yuxuan Zhang, Roeland Wiersema, Juan Carrasquilla, Lukasz Cincio, Yong Baek Kim
Abstract: Quantum dynamics compilation is an important task for improving quantum simulation efficiency: It aims to synthesize multi-qubit target dynamics into a circuit consisting of as few elementary gates as possible. Compared to deterministic methods such as Trotterization, variational quantum compilation (VQC) methods employ variational optimization to reduce gate costs while maintaining high accuracy. In this work, we explore the potential of a VQC scheme by making use of out-of-distribution generalization results in quantum machine learning (QML): By learning the action of a given many-body dynamics on a small data set of product states, we can obtain a unitary circuit that generalizes to highly entangled states such as the Haar random states. The efficiency in training allows us to use tensor network methods to compress such time-evolved product states by exploiting their low entanglement features. Our approach exceeds state-of-the-art compilation results in both system size and accuracy in one dimension ($1$D). For the first time, we extend VQC to systems on two-dimensional (2D) strips with a quasi-1D treatment, demonstrating a significant resource advantage over standard Trotterization methods, highlighting the method's promise for advancing quantum simulation tasks on near-term quantum processors.
Authors: Valeria Martin, K. Brent Venable, Derek Morgan
Abstract: Forest loss due to natural events, such as wildfires, represents an increasing global challenge that demands advanced analytical methods for effective detection and mitigation. To this end, the integration of satellite imagery with deep learning (DL) methods has become essential. Nevertheless, this approach requires substantial amounts of labeled data to produce accurate results. In this study, we use bi-temporal Sentinel-2 satellite imagery sourced from Google Earth Engine (GEE) to build the California Wildfire GeoImaging Dataset (CWGID), a high-resolution labeled satellite imagery dataset with over 100,000 labeled before and after forest wildfire image pairs for wildfire detection through DL. Our methods include data acquisition from authoritative sources, data processing, and an initial dataset analysis using three pre-trained Convolutional Neural Network (CNN) architectures. Our results show that the EF EfficientNet-B0 model achieves the highest accuracy of over 92% in detecting forest wildfires. The CWGID and the methodology used to build it, prove to be a valuable resource for training and testing DL architectures for forest wildfire detection.
Authors: Jiho Lee, Nisar R. Ahmed, Kyle H. Wray, Zachary N. Sunberg
Abstract: Partially Observable Markov Decision Processes (POMDPs) provide a structured framework for decision-making under uncertainty, but their application requires efficient belief updates. Sequential Importance Resampling Particle Filters (SIRPF), also known as Bootstrap Particle Filters, are commonly used as belief updaters in large approximate POMDP solvers, but they face challenges such as particle deprivation and high computational costs as the system's state dimension grows. To address these issues, this study introduces Rao-Blackwellized POMDP (RB-POMDP) approximate solvers and outlines generic methods to apply Rao-Blackwellization in both belief updates and online planning. We compare the performance of SIRPF and Rao-Blackwellized Particle Filters (RBPF) in a simulated localization problem where an agent navigates toward a target in a GPS-denied environment using POMCPOW and RB-POMCPOW planners. Our results not only confirm that RBPFs maintain accurate belief approximations over time with fewer particles, but, more surprisingly, RBPFs combined with quadrature-based integration improve planning quality significantly compared to SIRPF-based planning under the same computational limits.
Authors: Oscar Clivio, Avi Feller, Chris Holmes
Abstract: Reweighting a distribution to minimize a distance to a target distribution is a powerful and flexible strategy for estimating a wide range of causal effects, but can be challenging in practice because optimal weights typically depend on knowledge of the underlying data generating process. In this paper, we focus on design-based weights, which do not incorporate outcome information; prominent examples include prospective cohort studies, survey weighting, and the weighting portion of augmented weighting estimators. In such applications, we explore the central role of representation learning in finding desirable weights in practice. Unlike the common approach of assuming a well-specified representation, we highlight the error due to the choice of a representation and outline a general framework for finding suitable representations that minimize this error. Building on recent work that combines balancing weights and neural networks, we propose an end-to-end estimation procedure that learns a flexible representation, while retaining promising theoretical properties. We show that this approach is competitive in a range of common causal inference tasks.
Authors: Kevin Paeth, Daniel Atherton, Nikiforos Pittaras, Heather Frase, Sean McGregor
Abstract: As artificial intelligence (AI) systems become increasingly deployed across the world, they are also increasingly implicated in AI incidents - harm events to individuals and society. As a result, industry, civil society, and governments worldwide are developing best practices and regulations for monitoring and analyzing AI incidents. The AI Incident Database (AIID) is a project that catalogs AI incidents and supports further research by providing a platform to classify incidents for different operational and research-oriented goals. This study reviews the AIID's dataset of 750+ AI incidents and two independent taxonomies applied to these incidents to identify common challenges to indexing and analyzing AI incidents. We find that certain patterns of AI incidents present structural ambiguities that challenge incident databasing and explore how epistemic uncertainty in AI incident reporting is unavoidable. We therefore report mitigations to make incident processes more robust to uncertainty related to cause, extent of harm, severity, or technical details of implicated systems. With these findings, we discuss how to develop future AI incident reporting practices.
Authors: Mohamad Yamen AL Mohamad, Hossein Bevrani, Ali Akbar Haydari
Abstract: Neural networks are often regarded as "black boxes" due to their complex functions and numerous parameters, which poses significant challenges for interpretability. This study addresses these challenges by introducing methods to enhance the understanding of neural networks, focusing specifically on models with a single hidden layer. We establish a theoretical framework by demonstrating that the neural network estimator can be interpreted as a nonparametric regression model. Building on this foundation, we propose statistical tests to assess the significance of input neurons and introduce algorithms for dimensionality reduction, including clustering and (PCA), to simplify the network and improve its interpretability and accuracy. The key contributions of this study include the development of a bootstrapping technique for evaluating artificial neural network (ANN) performance, applying statistical tests and logistic regression to analyze hidden neurons, and assessing neuron efficiency. We also investigate the behavior of individual hidden neurons in relation to out-put neurons and apply these methodologies to the IDC and Iris datasets to validate their practical utility. This research advances the field of Explainable Artificial Intelligence by presenting robust statistical frameworks for interpreting neural networks, thereby facilitating a clearer understanding of the relationships between inputs, outputs, and individual network components.
Authors: Ruo Yang, Binghui Wang, Mustafa Bilgic
Abstract: Numerous explanation methods have been recently developed to interpret the decisions made by deep neural network (DNN) models. For image classifiers, these methods typically provide an attribution score to each pixel in the image to quantify its contribution to the prediction. However, most of these explanation methods appropriate attribution scores to pixels independently, even though both humans and DNNs make decisions by analyzing a set of closely related pixels simultaneously. Hence, the attribution score of a pixel should be evaluated jointly by considering itself and its structurally-similar pixels. We propose a method called IProp, which models each pixel's individual attribution score as a source of explanatory information and explains the image prediction through the dynamic propagation of information across all pixels. To formulate the information propagation, IProp adopts the Markov Reward Process, which guarantees convergence, and the final status indicates the desired pixels' attribution scores. Furthermore, IProp is compatible with any existing attribution-based explanation method. Extensive experiments on various explanation methods and DNN models verify that IProp significantly improves them on a variety of interpretability metrics.
Authors: Avisha Kumar, Kunal Kotkar, Kelly Jiang, Meghana Bhimreddy, Daniel Davidar, Carly Weber-Levine, Siddharth Krishnan, Max J. Kerensky, Ruixing Liang, Kelley Kempski Leadingham, Denis Routkevitch, Andrew M. Hersh, Kimberly Ashayeri, Betty Tyler, Ian Suk, Jennifer Son, Nicholas Theodore, Nitish Thakor, Amir Manbachi
Abstract: While deep learning has catalyzed breakthroughs across numerous domains, its broader adoption in clinical settings is inhibited by the costly and time-intensive nature of data acquisition and annotation. To further facilitate medical machine learning, we present an ultrasound dataset of 10,223 Brightness-mode (B-mode) images consisting of sagittal slices of porcine spinal cords (N=25) before and after a contusion injury. We additionally benchmark the performance metrics of several state-of-the-art object detection algorithms to localize the site of injury and semantic segmentation models to label the anatomy for comparison and creation of task-specific architectures. Finally, we evaluate the zero-shot generalization capabilities of the segmentation models on human ultrasound spinal cord images to determine whether training on our porcine dataset is sufficient for accurately interpreting human data. Our results show that the YOLOv8 detection model outperforms all evaluated models for injury localization, achieving a mean Average Precision (mAP50-95) score of 0.606. Segmentation metrics indicate that the DeepLabv3 segmentation model achieves the highest accuracy on unseen porcine anatomy, with a Mean Dice score of 0.587, while SAMed achieves the highest Mean Dice score generalizing to human anatomy (0.445). To the best of our knowledge, this is the largest annotated dataset of spinal cord ultrasound images made publicly available to researchers and medical professionals, as well as the first public report of object detection and segmentation architectures to assess anatomical markers in the spinal cord for methodology development and clinical applications.
Authors: Talha Bozkus, Urbashi Mitra
Abstract: Q-learning is a powerful tool for network control and policy optimization in wireless networks, but it struggles with large state spaces. Recent advancements, like multi-environment mixed Q-learning (MEMQ), improves performance and reduces complexity by integrating multiple Q-learning algorithms across multiple related environments so-called digital cousins. However, MEMQ is designed for centralized single-agent networks and is not suitable for decentralized or multi-agent networks. To address this challenge, we propose a novel multi-agent MEMQ algorithm for partially decentralized wireless networks with multiple mobile transmitters (TXs) and base stations (BSs), where TXs do not have access to each other's states and actions. In uncoordinated states, TXs act independently to minimize their individual costs. In coordinated states, TXs use a Bayesian approach to estimate the joint state based on local observations and share limited information with leader TX to minimize joint cost. The cost of information sharing scales linearly with the number of TXs and is independent of the joint state-action space size. The proposed scheme is 50% faster than centralized MEMQ with only a 20% increase in average policy error (APE) and is 25% faster than several advanced decentralized Q-learning algorithms with 40% less APE. The convergence of the algorithm is also demonstrated.
Authors: Mo Zhou, Stanley Osher, Wuchen Li
Abstract: Classical neural ordinary differential equations (ODEs) are powerful tools for approximating the log-density functions in high-dimensional spaces along trajectories, where neural networks parameterize the velocity fields. This paper proposes a system of neural differential equations representing first- and second-order score functions along trajectories based on deep neural networks. We reformulate the mean field control (MFC) problem with individual noises into an unconstrained optimization problem framed by the proposed neural ODE system. Additionally, we introduce a novel regularization term to enforce characteristics of viscous Hamilton--Jacobi--Bellman (HJB) equations to be satisfied based on the evolution of the second-order score function. Examples include regularized Wasserstein proximal operators (RWPOs), probability flow matching of Fokker--Planck (FP) equations, and linear quadratic (LQ) MFC problems, which demonstrate the effectiveness and accuracy of the proposed method.
Authors: Harshith Bachimanchi, Giovanni Volpe
Abstract: Diffusion models have emerged as a prominent technique in generative modeling with neural networks, making their mark in tasks like text-to-image translation and super-resolution. In this tutorial, we provide a comprehensive guide to build denoising diffusion probabilistic models (DDPMs) from scratch, with a specific focus on transforming low-resolution microscopy images into their corresponding high-resolution versions. We provide the theoretical background, mathematical derivations, and a detailed Python code implementation using PyTorch, along with techniques to enhance model performance.
Authors: Alexander Scarlatos, Andrew Lan
Abstract: Recent advances in large language models (LLMs) have led to the development of artificial intelligence (AI)-powered tutoring chatbots, showing promise in providing broad access to high-quality personalized education. Existing works have primarily studied how to make LLMs follow tutoring principles but not how to model student behavior in dialogues. However, analyzing student dialogue turns can serve as a formative assessment, since open-ended student discourse may indicate their knowledge levels and reveal specific misconceptions. In this work, we present a first attempt at performing knowledge tracing (KT) in tutor-student dialogues. We propose LLM prompting methods to identify the knowledge components/skills involved in each dialogue turn and diagnose whether the student responds correctly to the tutor, and verify the LLM's effectiveness via an expert human evaluation. We then apply a range of KT methods on the resulting labeled data to track student knowledge levels over an entire dialogue. We conduct experiments on two tutoring dialogue datasets, and show that a novel yet simple LLM-based method, LLMKT, significantly outperforms existing KT methods in predicting student response correctness in dialogues. We perform extensive qualitative analyses to highlight the challenges in dialogue KT and outline multiple avenues for future work.
Authors: Gennady Sidorov, Malik Mohrat, Ksenia Lebedeva, Ruslan Rakhimov, Sergey Kolyubin
Abstract: Although various visual localization approaches exist, such as scene coordinate and pose regression, these methods often struggle with high memory consumption or extensive optimization requirements. To address these challenges, we utilize recent advancements in novel view synthesis, particularly 3D Gaussian Splatting (3DGS), to enhance localization. 3DGS allows for the compact encoding of both 3D geometry and scene appearance with its spatial features. Our method leverages the dense description maps produced by XFeat's lightweight keypoint detection and description model. We propose distilling these dense keypoint descriptors into 3DGS to improve the model's spatial understanding, leading to more accurate camera pose predictions through 2D-3D correspondences. After estimating an initial pose, we refine it using a photometric warping loss. Benchmarking on popular indoor and outdoor datasets shows that our approach surpasses state-of-the-art Neural Render Pose (NRP) methods, including NeRFMatch and PNeRFLoc.
Authors: Simon Varailhon, Masih Aminbeidokhti, Marco Pedersoli, Eric Granger
Abstract: Source-free domain adaptation (SFDA) is a challenging problem in object detection, where a pre-trained source model is adapted to a new target domain without using any source domain data for privacy and efficiency reasons. Most state-of-the-art SFDA methods for object detection have been proposed for Faster-RCNN, a detector that is known to have high computational complexity. This paper focuses on domain adaptation techniques for real-world vision systems, particularly for the YOLO family of single-shot detectors known for their fast baselines and practical applications. Our proposed SFDA method - Source-Free YOLO (SF-YOLO) - relies on a teacher-student framework in which the student receives images with a learned, target domain-specific augmentation, allowing the model to be trained with only unlabeled target data and without requiring feature alignment. A challenge with self-training using a mean-teacher architecture in the absence of labels is the rapid decline of accuracy due to noisy or drifting pseudo-labels. To address this issue, a teacher-to-student communication mechanism is introduced to help stabilize the training and reduce the reliance on annotated target data for model selection. Despite its simplicity, our approach is competitive with state-of-the-art detectors on several challenging benchmark datasets, even sometimes outperforming methods that use source data for adaptation.
Authors: Jiaheng Hu, Rose Hendrix, Ali Farhadi, Aniruddha Kembhavi, Roberto Martin-Martin, Peter Stone, Kuo-Hao Zeng, Kiana Ehsan
Abstract: In recent years, the Robotics field has initiated several efforts toward building generalist robot policies through large-scale multi-task Behavior Cloning. However, direct deployments of these policies have led to unsatisfactory performance, where the policy struggles with unseen states and tasks. How can we break through the performance plateau of these models and elevate their capabilities to new heights? In this paper, we propose FLaRe, a large-scale Reinforcement Learning fine-tuning framework that integrates robust pre-trained representations, large-scale training, and gradient stabilization techniques. Our method aligns pre-trained policies towards task completion, achieving state-of-the-art (SoTA) performance both on previously demonstrated and on entirely novel tasks and embodiments. Specifically, on a set of long-horizon mobile manipulation tasks, FLaRe achieves an average success rate of 79.5% in unseen environments, with absolute improvements of +23.6% in simulation and +30.7% on real robots over prior SoTA methods. By utilizing only sparse rewards, our approach can enable generalizing to new capabilities beyond the pretraining data with minimal human effort. Moreover, we demonstrate rapid adaptation to new embodiments and behaviors with less than a day of fine-tuning. Videos can be found on the project website at https://robot-flare.github.io/
Authors: Tong Wu, Zhiyong Chen, Meixia Tao, Yaping Sun, Xiaodong Xu, Wenjun Zhang, Ping Zhang
Abstract: Lightweight and efficient neural network models for deep joint source-channel coding (JSCC) are crucial for semantic communications. In this paper, we propose a novel JSCC architecture, named MambaJSCC, that achieves state-of-the-art performance with low computational and parameter overhead. MambaJSCC utilizes the visual state space model with channel adaptation (VSSM-CA) blocks as its backbone for transmitting images over wireless channels, where the VSSM-CA primarily consists of the generalized state space models (GSSM) and the zero-parameter, zero-computational channel adaptation method (CSI-ReST). We design the GSSM module, leveraging reversible matrix transformations to express generalized scan expanding operations, and theoretically prove that two GSSM modules can effectively capture global information. We discover that GSSM inherently possesses the ability to adapt to channels, a form of endogenous intelligence. Based on this, we design the CSI-ReST method, which injects channel state information (CSI) into the initial state of GSSM to utilize its native response, and into the residual state to mitigate CSI forgetting, enabling effective channel adaptation without introducing additional computational and parameter overhead. Experimental results show that MambaJSCC not only outperforms existing JSCC methods (e.g., SwinJSCC) across various scenarios but also significantly reduces parameter size, computational overhead, and inference delay.
Authors: Yuchen Li, Haoyi Xiong, Linghe Kong, Jiang Bian, Shuaiqiang Wang, Guihai Chen, Dawei Yin
Abstract: Learning to rank (LTR) is widely employed in web searches to prioritize pertinent webpages from retrieved content based on input queries. However, traditional LTR models encounter two principal obstacles that lead to suboptimal performance: (1) the lack of well-annotated query-webpage pairs with ranking scores covering a diverse range of search query popularities, which hampers their ability to address queries across the popularity spectrum, and (2) inadequately trained models that fail to induce generalized representations for LTR, resulting in overfitting. To address these challenges, we propose a \emph{\uline{G}enerative \uline{S}emi-\uline{S}upervised \uline{P}re-trained} (GS2P) LTR model. We conduct extensive offline experiments on both a publicly available dataset and a real-world dataset collected from a large-scale search engine. Furthermore, we deploy GS2P in a large-scale web search engine with realistic traffic, where we observe significant improvements in the real-world application.
Authors: Ethan Lin, Zhiyuan Peng, Yi Fang
Abstract: Recent studies have evaluated the creativity/novelty of large language models (LLMs) primarily from a semantic perspective, using benchmarks from cognitive science. However, accessing the novelty in scholarly publications is a largely unexplored area in evaluating LLMs. In this paper, we introduce a scholarly novelty benchmark (SchNovel) to evaluate LLMs' ability to assess novelty in scholarly papers. SchNovel consists of 15000 pairs of papers across six fields sampled from the arXiv dataset with publication dates spanning 2 to 10 years apart. In each pair, the more recently published paper is assumed to be more novel. Additionally, we propose RAG-Novelty, which simulates the review process taken by human reviewers by leveraging the retrieval of similar papers to assess novelty. Extensive experiments provide insights into the capabilities of different LLMs to assess novelty and demonstrate that RAG-Novelty outperforms recent baseline models.
Authors: Pingyi Huo, Anusha Devulapally, Hasan Al Maruf, Minseo Park, Krishnakumar Nair, Meena Arunachalam, Gulsum Gudukbay Akbulut, Mahmut Taylan Kandemir, Vijaykrishnan Narayanan
Abstract: Deep Learning Recommendation Models (DLRMs) have become increasingly popular and prevalent in today's datacenters, consuming most of the AI inference cycles. The performance of DLRMs is heavily influenced by available bandwidth due to their large vector sizes in embedding tables and concurrent accesses. To achieve substantial improvements over existing solutions, novel approaches towards DLRM optimization are needed, especially, in the context of emerging interconnect technologies like CXL. This study delves into exploring CXL-enabled systems, implementing a process-in-fabric-switch (PIFS) solution to accelerate DLRMs while optimizing their memory and bandwidth scalability. We present an in-depth characterization of industry-scale DLRM workloads running on CXL-ready systems, identifying the predominant bottlenecks in existing CXL systems. We, therefore, propose PIFS-Rec, a PIFS-based scheme that implements near-data processing through downstream ports of the fabric switch. PIFS-Rec achieves a latency that is 3.89x lower than Pond, an industry-standard CXL-based system, and also outperforms BEACON, a state-of-the-art scheme, by 2.03x.
Authors: Ishan Karunanayake, Mashael AlSabah, Nadeem Ahmed, Sanjay Jha
Abstract: Despite being the most popular privacy-enhancing network, Tor is increasingly adopted by cybercriminals to obfuscate malicious traffic, hindering the identification of malware-related communications between compromised devices and Command and Control (C&C) servers. This malicious traffic can induce congestion and reduce Tor's performance, while encouraging network administrators to block Tor traffic. Recent research, however, demonstrates the potential for accurately classifying captured Tor traffic as malicious or benign. While existing efforts have addressed malware class identification, their performance remains limited, with micro-average precision and recall values around 70%. Accurately classifying specific malware classes is crucial for effective attack prevention and mitigation. Furthermore, understanding the unique patterns and attack vectors employed by different malware classes helps the development of robust and adaptable defence mechanisms. We utilise a multi-label classification technique based on Message-Passing Neural Networks, demonstrating its superiority over previous approaches such as Binary Relevance, Classifier Chains, and Label Powerset, by achieving micro-average precision (MAP) and recall (MAR) exceeding 90%. Compared to previous work, we significantly improve performance by 19.98%, 10.15%, and 59.21% in MAP, MAR, and Hamming Loss, respectively. Next, we employ Explainable Artificial Intelligence (XAI) techniques to interpret the decision-making process within these models. Finally, we assess the robustness of all techniques by crafting adversarial perturbations capable of manipulating classifier predictions and generating false positives and negatives.
Authors: Kota Dohi, Aoi Ito, Harsh Purohit, Tomoya Nishida, Takashi Endo, Yohei Kawaguchi
Abstract: Due to scarcity of time-series data annotated with descriptive texts, training a model to generate descriptive texts for time-series data is challenging. In this study, we propose a method to systematically generate domain-independent descriptive texts from time-series data. We identify two distinct approaches for creating pairs of time-series data and descriptive texts: the forward approach and the backward approach. By implementing the novel backward approach, we create the Temporal Automated Captions for Observations (TACO) dataset. Experimental results demonstrate that a contrastive learning based model trained using the TACO dataset is capable of generating descriptive texts for time-series data in novel domains.
Authors: Seokwon Shin, Hyungrok Do, Youngdoo Son
Abstract: Multi-task learning is a popular machine learning approach that enables simultaneous learning of multiple related tasks, improving algorithmic efficiency and effectiveness. In the hard parameter sharing approach, an encoder shared through multiple tasks generates data representations passed to task-specific predictors. Therefore, it is crucial to have a shared encoder that provides decent representations for every and each task. However, despite recent advances in multi-task learning, the question of how to improve the quality of representations generated by the shared encoder remains open. To address this gap, we propose a novel approach called Dummy Gradient norm Regularization that aims to improve the universality of the representations generated by the shared encoder. Specifically, the method decreases the norm of the gradient of the loss function with repect to dummy task-specific predictors to improve the universality of the shared encoder's representations. Through experiments on multiple multi-task learning benchmark datasets, we demonstrate that DGR effectively improves the quality of the shared representations, leading to better multi-task prediction performances. Applied to various classifiers, the shared representations generated by DGR also show superior performance compared to existing multi-task learning methods. Moreover, our approach takes advantage of computational efficiency due to its simplicity. The simplicity also allows us to seamlessly integrate DGR with the existing multi-task learning algorithms.
Authors: Alexander Popov, Alperen Degirmenci, David Wehr, Shashank Hegde, Ryan Oldja, Alexey Kamenev, Bertrand Douillard, David Nist\'er, Urs Muller, Ruchi Bhargava, Stan Birchfield, Nikolai Smolyanskiy
Abstract: We propose the use of latent space generative world models to address the covariate shift problem in autonomous driving. A world model is a neural network capable of predicting an agent's next state given past states and actions. By leveraging a world model during training, the driving policy effectively mitigates covariate shift without requiring an excessive amount of training data. During end-to-end training, our policy learns how to recover from errors by aligning with states observed in human demonstrations, so that at runtime it can recover from perturbations outside the training distribution. Additionally, we introduce a novel transformer-based perception encoder that employs multi-view cross-attention and a learned scene query. We present qualitative and quantitative results, demonstrating significant improvements upon prior state of the art in closed-loop testing in the CARLA simulator, as well as showing the ability to handle perturbations in both CARLA and NVIDIA's DRIVE Sim.
Authors: Guanyi Mou, Yun Yue, Kyumin Lee, Ziming Zhang
Abstract: Wildlife trafficking (WLT) has emerged as a global issue, with traffickers expanding their operations from offline to online platforms, utilizing e-commerce websites and social networks to enhance their illicit trade. This paper addresses the challenge of detecting and recognizing wildlife product sales promotion behaviors in online social networks, a crucial aspect in combating these environmentally harmful activities. To counter these environmentally damaging illegal operations, in this research, we focus on wildlife product sales promotion behaviors in online social networks. Specifically, 1) A scalable dataset related to wildlife product trading is collected using a network-based approach. This dataset is labeled through a human-in-the-loop machine learning process, distinguishing positive class samples containing wildlife product selling posts and hard-negatives representing normal posts misclassified as potential WLT posts, subsequently corrected by human annotators. 2) We benchmark the machine learning results on the proposed dataset and build a practical framework that automatically identifies suspicious wildlife selling posts and accounts, sufficiently leveraging the multi-modal nature of online social networks. 3) This research delves into an in-depth analysis of trading posts, shedding light on the systematic and organized selling behaviors prevalent in the current landscape. We provide detailed insights into the nature of these behaviors, contributing valuable information for understanding and countering illegal wildlife product trading.
Authors: Guanyi Mou, Pengyi Ye, Kyumin Lee
Abstract: Hate speech detection on online social networks has become one of the emerging hot topics in recent years. With the broad spread and fast propagation speed across online social networks, hate speech makes significant impacts on society by increasing prejudice and hurting people. Therefore, there are aroused attention and concern from both industry and academia. In this paper, we address the hate speech problem and propose a novel hate speech detection framework called SWE2, which only relies on the content of messages and automatically identifies hate speech. In particular, our framework exploits both word-level semantic information and sub-word knowledge. It is intuitively persuasive and also practically performs well under a situation with/without character-level adversarial attack. Experimental results show that our proposed model achieves 0.975 accuracy and 0.953 macro F1, outperforming 7 state-of-the-art baselines under no adversarial attack. Our model robustly and significantly performed well under extreme adversarial attack (manipulation of 50% messages), achieving 0.967 accuracy and 0.934 macro F1.
Authors: Jiaqi Xue, Yancheng Zhang, Yanshan Wang, Xueqiang Wang, Hao Zheng, Qian Lou
Abstract: Secure training, while protecting the confidentiality of both data and model weights, typically incurs significant training overhead. Traditional Fully Homomorphic Encryption (FHE)-based non-inter-active training models are heavily burdened by computationally demanding bootstrapping. To develop an efficient secure training system, we established a foundational framework, CryptoTrain-B, utilizing a hybrid cryptographic protocol that merges FHE with Oblivious Transfer (OT) for handling linear and non-linear operations, respectively. This integration eliminates the need for costly bootstrapping. Although CryptoTrain-B sets a new baseline in performance, reducing its training overhead remains essential. We found that ciphertext-ciphertext multiplication (CCMul) is a critical bottleneck in operations involving encrypted inputs and models. Our solution, the CCMul-Precompute technique, involves precomputing CCMul offline and resorting to the less resource-intensive ciphertext-plaintext multiplication (CPMul) during private training. Furthermore, conventional polynomial convolution in FHE systems tends to encode irrelevant and redundant values into polynomial slots, necessitating additional polynomials and ciphertexts for input representation and leading to extra multiplications. Addressing this, we introduce correlated polynomial convolution, which encodes only related input values into polynomials, thus drastically reducing the number of computations and overheads. By integrating CCMul-Precompute and correlated polynomial convolution into CryptoTrain-B, we facilitate a rapid and efficient secure training framework, CryptoTrain. Extensive experiments demonstrate that CryptoTrain achieves a ~5.3X training time reduction compared to prior methods.
Authors: Tingting Yang, Liang Xiao, Yizhe Zhang
Abstract: A global threshold (e.g., 0.5) is often applied to determine which bounding boxes should be included in the final results for an object detection task. A higher threshold reduces false positives but may result in missing a significant portion of true positives. A lower threshold can increase detection recall but may also result in more false positives. Because of this, using a preset global threshold (e.g., 0.5) applied to all the bounding box candidates may lead to suboptimal solutions. In this paper, we propose a Test-time Self-guided Bounding-box Propagation (TSBP) method, leveraging Earth Mover's Distance (EMD) to enhance object detection in histology images. TSBP utilizes bounding boxes with high confidence to influence those with low confidence, leveraging visual similarities between them. This propagation mechanism enables bounding boxes to be selected in a controllable, explainable, and robust manner, which surpasses the effectiveness of using simple thresholds and uncertainty calibration methods. Importantly, TSBP does not necessitate additional labeled samples for model training or parameter estimation, unlike calibration methods. We conduct experiments on gland detection and cell detection tasks in histology images. The results show that our proposed TSBP significantly improves detection outcomes when working in conjunction with state-of-the-art deep learning-based detection networks. Compared to other methods such as uncertainty calibration, TSBP yields more robust and accurate object detection predictions while using no additional labeled samples. The code is available at https://github.com/jwhgdeu/TSBP.
Authors: Shoma Iwai, Atsuki Osanai, Shunsuke Kitada, Shinichiro Omachi
Abstract: Layout generation is a task to synthesize a harmonious layout with elements characterized by attributes such as category, position, and size. Human designers experiment with the placement and modification of elements to create aesthetic layouts, however, we observed that current discrete diffusion models (DDMs) struggle to correct inharmonious layouts after they have been generated. In this paper, we first provide novel insights into layout sticking phenomenon in DDMs and then propose a simple yet effective layout-assessment module Layout-Corrector, which works in conjunction with existing DDMs to address the layout sticking problem. We present a learning-based module capable of identifying inharmonious elements within layouts, considering overall layout harmony characterized by complex composition. During the generation process, Layout-Corrector evaluates the correctness of each token in the generated layout, reinitializing those with low scores to the ungenerated state. The DDM then uses the high-scored tokens as clues to regenerate the harmonized tokens. Layout-Corrector, tested on common benchmarks, consistently boosts layout-generation performance when in conjunction with various state-of-the-art DDMs. Furthermore, our extensive analysis demonstrates that the Layout-Corrector (1) successfully identifies erroneous tokens, (2) facilitates control over the fidelity-diversity trade-off, and (3) significantly mitigates the performance drop associated with fast sampling.
Authors: Ruihao Gong, Yifu Ding, Zining Wang, Chengtao Lv, Xingyu Zheng, Jinyang Du, Haotong Qin, Jinyang Guo, Michele Magno, Xianglong Liu
Abstract: Large language models (LLMs) have achieved remarkable advancements in natural language processing, showcasing exceptional performance across various tasks. However, the expensive memory and computational requirements present significant challenges for their practical deployment. Low-bit quantization has emerged as a critical approach to mitigate these challenges by reducing the bit-width of model parameters, activations, and gradients, thus decreasing memory usage and computational demands. This paper presents a comprehensive survey of low-bit quantization methods tailored for LLMs, covering the fundamental principles, system implementations, and algorithmic strategies. An overview of basic concepts and new data formats specific to low-bit LLMs is first introduced, followed by a review of frameworks and systems that facilitate low-bit LLMs across various hardware platforms. Then, we categorize and analyze techniques and toolkits for efficient low-bit training and inference of LLMs. Finally, we conclude with a discussion of future trends and potential advancements of low-bit LLMs. Our systematic overview from basic, system, and algorithm perspectives can offer valuable insights and guidelines for future works to enhance the efficiency and applicability of LLMs through low-bit quantization.
Authors: Ming Li, Jike Zhong, Chenxin Li, Liuzhuozheng Li, Nie Lin, Masashi Sugiyama
Abstract: Recent advances in fine-tuning Vision-Language Models (VLMs) have witnessed the success of prompt tuning and adapter tuning, while the classic model fine-tuning on inherent parameters seems to be overlooked. It is believed that fine-tuning the parameters of VLMs with few-shot samples corrupts the pre-trained knowledge since fine-tuning the CLIP model even degrades performance. In this paper, we revisit this viewpoint, and propose a new perspective: fine-tuning the specific parameters instead of all will uncover the power of classic model fine-tuning on VLMs. Through our meticulous study, we propose ClipFit, a simple yet effective method to fine-tune CLIP without introducing any overhead of extra parameters. We demonstrate that by only fine-tuning the specific bias terms and normalization layers, ClipFit can improve the performance of zero-shot CLIP by 7.27\% average harmonic mean accuracy. Lastly, to understand how fine-tuning in CLIPFit affects the pre-trained models, we conducted extensive experimental analyses w.r.t. changes in internal parameters and representations. We found that low-level text bias layers and the first layer normalization layer change much more than other layers. The code is available at \url{https://github.com/minglllli/CLIPFit}.
Authors: Xian Wang, Jin Zhou, Yuanli Feng, Jiahao Mei, Jiming Chen, Shuo Li
Abstract: Recent innovations in autonomous drones have facilitated time-optimal flight in single-drone configurations and enhanced maneuverability in multi-drone systems through the application of optimal control and learning-based methods. However, few studies have achieved time-optimal motion planning for multi-drone systems, particularly during highly agile maneuvers or in dynamic scenarios. This paper presents a decentralized policy network for time-optimal multi-drone flight using multi-agent reinforcement learning. To strike a balance between flight efficiency and collision avoidance, we introduce a soft collision penalty inspired by optimization-based methods. By customizing PPO in a centralized training, decentralized execution (CTDE) fashion, we unlock higher efficiency and stability in training, while ensuring lightweight implementation. Extensive simulations show that, despite slight performance trade-offs compared to single-drone systems, our multi-drone approach maintains near-time-optimal performance with low collision rates. Real-world experiments validate our method, with two quadrotors using the same network as simulation achieving a maximum speed of 13.65 m/s and a maximum body rate of 13.4 rad/s in a 5.5 m * 5.5 m * 2.0 m space across various tracks, relying entirely on onboard computation.
Authors: Qibin Wang, Xiaolin Hu, Weikai Xu, Wei Liu, Jian Luan, Bin Wang
Abstract: Low-rank adaptation (LoRA) and its variants have recently gained much interest due to their ability to avoid excessive inference costs. However, LoRA still encounters the following challenges: (1) Limitation of low-rank assumption; and (2) Its initialization method may be suboptimal. To this end, we propose PMSS(Pre-trained Matrices Skeleton Selection), which enables high-rank updates with low costs while leveraging semantic and linguistic information inherent in pre-trained weight. It achieves this by selecting skeletons from the pre-trained weight matrix and only learning a small matrix instead. Experiments demonstrate that PMSS outperforms LoRA and other fine-tuning methods across tasks with much less trainable parameters. We demonstrate its effectiveness, especially in handling complex tasks such as DROP benchmark(+3.4%/+5.9% on LLaMA2-7B/13B) and math reasoning(+12.89%/+5.61%/+3.11% on LLaMA2-7B, Mistral-7B and Gemma-7B of GSM8K). The code and model will be released soon.
Authors: Katharina Anderer, Andreas Reich, Matthias W\"olfel
Abstract: This paper presents a benchmark dataset for aligning lecture videos with corresponding slides and introduces a novel multimodal algorithm leveraging features from speech, text, and images. It achieves an average accuracy of 0.82 in comparison to SIFT (0.56) while being approximately 11 times faster. Using dynamic programming the algorithm tries to determine the optimal slide sequence. The results show that penalizing slide transitions increases accuracy. Features obtained via optical character recognition (OCR) contribute the most to a high matching accuracy, followed by image features. The findings highlight that audio transcripts alone provide valuable information for alignment and are beneficial if OCR data is lacking. Variations in matching accuracy across different lectures highlight the challenges associated with video quality and lecture style. The novel multimodal algorithm demonstrates robustness to some of these challenges, underscoring the potential of the approach.
Authors: Hang Lai, Jiahang Cao, Jiafeng Xu, Hongtao Wu, Yunfeng Lin, Tao Kong, Yong Yu, Weinan Zhang
Abstract: Legged locomotion over various terrains is challenging and requires precise perception of the robot and its surroundings from both proprioception and vision. However, learning directly from high-dimensional visual input is often data-inefficient and intricate. To address this issue, traditional methods attempt to learn a teacher policy with access to privileged information first and then learn a student policy to imitate the teacher's behavior with visual input. Despite some progress, this imitation framework prevents the student policy from achieving optimal performance due to the information gap between inputs. Furthermore, the learning process is unnatural since animals intuitively learn to traverse different terrains based on their understanding of the world without privileged knowledge. Inspired by this natural ability, we propose a simple yet effective method, World Model-based Perception (WMP), which builds a world model of the environment and learns a policy based on the world model. We illustrate that though completely trained in simulation, the world model can make accurate predictions of real-world trajectories, thus providing informative signals for the policy controller. Extensive simulated and real-world experiments demonstrate that WMP outperforms state-of-the-art baselines in traversability and robustness. Videos and Code are available at: https://wmp-loco.github.io/.
Authors: Ujjawal Sharma, Madhav Biyani, Akhil Dev Suresh, Debi Prasad Bhuyan, Saroj Kanta Mishra, Tanmoy Chakraborty
Abstract: Reliable prediction of the All India Summer Monsoon Rainfall (AISMR) is pivotal for informed policymaking for the country, impacting the lives of billions of people. However, accurate simulation of AISMR has been a persistent challenge due to the complex interplay of various muti-scale factors and the inherent variability of the monsoon system. This research focuses on adapting and fine-tuning the latest LLM model, PatchTST, to accurately predict AISMR with a lead time of three months. The fine-tuned PatchTST model, trained with historical AISMR data, the Ni\~no3.4 index, and categorical Indian Ocean Dipole values, outperforms several popular neural network models and statistical models. This fine-tuned LLM model exhibits an exceptionally low RMSE percentage of 0.07% and a Spearman correlation of 0.976. This is particularly impressive, since it is nearly 80% more accurate than the best-performing NN models. The model predicts an above-normal monsoon for the year 2024, with an accumulated rainfall of 921.6 mm in the month of June-September for the entire country.
Authors: Yiming Zhong, Yinuo Ren, Guangyao Cao, Feng Li, Haobo Qi
Abstract: Recent advances on time series forecasting mainly focus on improving the forecasting models themselves. However, managing the length of the input data can also significantly enhance prediction performance. In this paper, we introduce a novel approach called Optimal Starting Point Time Series Forecast (OSP-TSP) to capture the intrinsic characteristics of time series data. By adjusting the sequence length via leveraging the XGBoost and LightGBM models, the proposed approach can determine optimal starting point (OSP) of the time series and thus enhance the prediction performances. The performances of the OSP-TSP approach are then evaluated across various frequencies on the M4 dataset and other real-world datasets. Empirical results indicate that predictions based on the OSP-TSP approach consistently outperform those using the complete dataset. Moreover, recognizing the necessity of sufficient data to effectively train models for OSP identification, we further propose targeted solutions to address the issue of data insufficiency.
Authors: Sven Kruschel, Lasse Bohlen, Julian Rosenberger, Patrick Zschech, Mathias Kraus
Abstract: Generalized Additive Models (GAMs) offer a balance between performance and interpretability in machine learning. The interpretability aspect of GAMs is expressed through shape plots, representing the model's decision-making process. However, the visual properties of these plots, e.g. number of kinks (number of local maxima and minima), can impact their complexity and the cognitive load imposed on the viewer, compromising interpretability. Our study, including 57 participants, investigates the relationship between the visual properties of GAM shape plots and cognitive load they induce. We quantify various visual properties of shape plots and evaluate their alignment with participants' perceived cognitive load, based on 144 plots. Our results indicate that the number of kinks metric is the most effective, explaining 86.4% of the variance in users' ratings. We develop a simple model based on number of kinks that provides a practical tool for predicting cognitive load, enabling the assessment of one aspect of GAM interpretability without direct user involvement.
Authors: Haocheng Lin
Abstract: The popularisation of applying AI in businesses poses significant challenges relating to ethical principles, governance, and legal compliance. Although businesses have embedded AI into their day-to-day processes, they lack a unified approach for mitigating its potential risks. This paper introduces a framework ensuring that AI must be ethical, controllable, viable, and desirable. Balancing these factors ensures the design of a framework that addresses its trade-offs, such as balancing performance against explainability. A successful framework provides practical advice for businesses to meet regulatory requirements in sectors such as finance and healthcare, where it is critical to comply with standards like GPDR and the EU AI Act. Different case studies validate this framework by integrating AI in both academic and practical environments. For instance, large language models are cost-effective alternatives for generating synthetic opinions that emulate attitudes to environmental issues. These case studies demonstrate how having a structured framework could enhance transparency and maintain performance levels as shown from the alignment between synthetic and expected distributions. This alignment is quantified using metrics like Chi-test scores, normalized mutual information, and Jaccard indexes. Future research should explore the framework's empirical validation in diverse industrial settings further, ensuring the model's scalability and adaptability.
Authors: Leon Greiser, Ozan Demir, Benjamin Hartmann, Henrik Hose, Sebastian Trimpe
Abstract: Complicated first principles modelling and controller synthesis can be prohibitively slow and expensive for high-mix, low-volume products such as hydraulic excavators. Instead, in a data-driven approach, recorded trajectories from the real system can be used to train local model networks (LMNs), for which feedforward controllers are derived via feedback linearization. However, previous works required LMNs without zero dynamics for feedback linearization, which restricts the model structure and thus modelling capacity of LMNs. In this paper, we overcome this restriction by providing a criterion for when feedback linearization of LMNs with zero dynamics yields a valid controller. As a criterion we propose the bounded-input bounded-output stability of the resulting controller. In two additional contributions, we extend this approach to consider measured disturbance signals and multiple inputs and outputs. We illustrate the effectiveness of our contributions in a hydraulic excavator control application with hardware experiments. To this end, we train LMNs from recorded, noisy data and derive feedforward controllers used as part of a leveling assistance system on the excavator. In our experiments, incorporating disturbance signals and multiple inputs and outputs enhances tracking performance of the learned controller. A video of our experiments is available at https://youtu.be/lrrWBx2ASaE.
Authors: Vineet Punyamoorty, Pascal Jutras-Dub\'e, Ruqi Zhang, Vaneet Aggarwal, Damon Conover, Aniket Bera
Abstract: By framing reinforcement learning as a sequence modeling problem, recent work has enabled the use of generative models, such as diffusion models, for planning. While these models are effective in predicting long-horizon state trajectories in deterministic environments, they face challenges in dynamic settings with moving obstacles. Effective collision avoidance demands continuous monitoring and adaptive decision-making. While replanning at every timestep could ensure safety, it introduces substantial computational overhead due to the repetitive prediction of overlapping state sequences -- a process that is particularly costly with diffusion models, known for their intensive iterative sampling procedure. We propose an adaptive generative planning approach that dynamically adjusts replanning frequency based on the uncertainty of action predictions. Our method minimizes the need for frequent, computationally expensive, and redundant replanning while maintaining robust collision avoidance performance. In experiments, we obtain a 13.5% increase in the mean trajectory length and a 12.7% increase in mean reward over long-horizon planning, indicating a reduction in collision rates and an improved ability to navigate the environment safely.
Authors: Lorenzo Fiaschi, Marco Cococcioni
Abstract: This work proposes a novel approach to the deep hierarchical classification task, i.e., the problem of classifying data according to multiple labels organized in a rigid parent-child structure. It consists in a multi-output deep neural network equipped with specific projection operators placed before each output layer. The design of such an architecture, called lexicographic hybrid deep neural network (LH-DNN), has been possible by combining tools from different and quite distant research fields: lexicographic multi-objective optimization, non-standard analysis, and deep learning. To assess the efficacy of the approach, the resulting network is compared against the B-CNN, a convolutional neural network tailored for hierarchical classification tasks, on the CIFAR10, CIFAR100 (where it has been originally and recently proposed before being adopted and tuned for multiple real-world applications) and Fashion-MNIST benchmarks. Evidence states that an LH-DNN can achieve comparable if not superior performance, especially in the learning of the hierarchical relations, in the face of a drastic reduction of the learning parameters, training epochs, and computational time, without the need for ad-hoc loss functions weighting values.
Authors: Rafael Mendoza, Isabella Cruz, Richard Liu, Aarav Deshmukh, David Williams, Jesscia Peng, Rohan Iyer
Abstract: Large language models (LLMs) have revolutionized how we interact with technology, but their personalization to individual user preferences remains a significant challenge, particularly in on-device applications. Traditional methods often depend heavily on labeled datasets and can be resource-intensive. To address these issues, we present Adaptive Self-Supervised Learning Strategies (ASLS), which utilizes self-supervised learning techniques to personalize LLMs dynamically. The framework comprises a user profiling layer for collecting interaction data and a neural adaptation layer for real-time model fine-tuning. This innovative approach enables continuous learning from user feedback, allowing the model to generate responses that align closely with user-specific contexts. The adaptive mechanisms of ASLS minimize computational demands and enhance personalization efficiency. Experimental results across various user scenarios illustrate the superior performance of ASLS in boosting user engagement and satisfaction, highlighting its potential to redefine LLMs as highly responsive and context-aware systems on-device.
Authors: Elisa Nguyen, Johannes Bertram, Evgenii Kortukov, Jean Y. Song, Seong Joon Oh
Abstract: While Explainable AI (XAI) aims to make AI understandable and useful to humans, it has been criticised for relying too much on formalism and solutionism, focusing more on mathematical soundness than user needs. We propose an alternative to this bottom-up approach inspired by design thinking: the XAI research community should adopt a top-down, user-focused perspective to ensure user relevance. We illustrate this with a relatively young subfield of XAI, Training Data Attribution (TDA). With the surge in TDA research and growing competition, the field risks repeating the same patterns of solutionism. We conducted a needfinding study with a diverse group of AI practitioners to identify potential user needs related to TDA. Through interviews (N=10) and a systematic survey (N=31), we uncovered new TDA tasks that are currently largely overlooked. We invite the TDA and XAI communities to consider these novel tasks and improve the user relevance of their research outcomes.
Authors: Anjana Wijekoon, Adrito Das, Roxana R. Herrera, Danyal Z. Khan, John Hanrahan, Eleanor Carter, Valpuri Luoma, Danail Stoyanov, Hani J. Marcus, Sophia Bano
Abstract: Accurate intra-operative Remaining Surgery Duration (RSD) predictions allow for anaesthetists to more accurately decide when to administer anaesthetic agents and drugs, as well as to notify hospital staff to send in the next patient. Therefore RSD plays an important role in improving patient care and minimising surgical theatre costs via efficient scheduling. In endoscopic pituitary surgery, it is uniquely challenging due to variable workflow sequences with a selection of optional steps contributing to high variability in surgery duration. This paper presents PitRSDNet for predicting RSD during pituitary surgery, a spatio-temporal neural network model that learns from historical data focusing on workflow sequences. PitRSDNet integrates workflow knowledge into RSD prediction in two forms: 1) multi-task learning for concurrently predicting step and RSD; and 2) incorporating prior steps as context in temporal learning and inference. PitRSDNet is trained and evaluated on a new endoscopic pituitary surgery dataset with 88 videos to show competitive performance improvements over previous statistical and machine learning methods. The findings also highlight how PitRSDNet improve RSD precision on outlier cases utilising the knowledge of prior steps.
Authors: Rinor Cakaj, Jens Mehnert, Bin Yang
Abstract: We introduce Mixture-of-Depths (MoD) for Convolutional Neural Networks (CNNs), a novel approach that enhances the computational efficiency of CNNs by selectively processing channels based on their relevance to the current prediction. This method optimizes computational resources by dynamically selecting key channels in feature maps for focused processing within the convolutional blocks (Conv-Blocks), while skipping less relevant channels. Unlike conditional computation methods that require dynamic computation graphs, CNN MoD uses a static computation graph with fixed tensor sizes which improve hardware efficiency. It speeds up the training and inference processes without the need for customized CUDA kernels, unique loss functions, or finetuning. CNN MoD either matches the performance of traditional CNNs with reduced inference times, GMACs, and parameters, or exceeds their performance while maintaining similar inference times, GMACs, and parameters. For example, on ImageNet, ResNet86-MoD exceeds the performance of the standard ResNet50 by 0.45% with a 6% speedup on CPU and 5% on GPU. Moreover, ResNet75-MoD achieves the same performance as ResNet50 with a 25% speedup on CPU and 15% on GPU.
Authors: Francesco Verdini, Pierfrancesco Melucci, Stefano Perna, Francesco Cariaggi, Marco Gaido, Sara Papi, Szymon Mazurek, Marek Kasztelnik, Luisa Bentivogli, S\'ebastien Brati\`eres, Paolo Merialdo, Simone Scardapane
Abstract: The remarkable performance achieved by Large Language Models (LLM) has driven research efforts to leverage them for a wide range of tasks and input modalities. In speech-to-text (S2T) tasks, the emerging solution consists of projecting the output of the encoder of a Speech Foundational Model (SFM) into the LLM embedding space through an adapter module. However, no work has yet investigated how much the downstream-task performance depends on each component (SFM, adapter, LLM) nor whether the best design of the adapter depends on the chosen SFM and LLM. To fill this gap, we evaluate the combination of 5 adapter modules, 2 LLMs (Mistral and Llama), and 2 SFMs (Whisper and SeamlessM4T) on two widespread S2T tasks, namely Automatic Speech Recognition and Speech Translation. Our results demonstrate that the SFM plays a pivotal role in downstream performance, while the adapter choice has moderate impact and depends on the SFM and LLM.
Authors: Lucas Robinet, Ahmad Berjaoui, Ziad Kheil, Elizabeth Cohen-Jonathan Moyal
Abstract: Real-life medical data is often multimodal and incomplete, fueling the growing need for advanced deep learning models capable of integrating them efficiently. The use of diverse modalities, including histopathology slides, MRI, and genetic data, offers unprecedented opportunities to improve prognosis prediction and to unveil new treatment pathways. Contrastive learning, widely used for deriving representations from paired data in multimodal tasks, assumes that different views contain the same task-relevant information and leverages only shared information. This assumption becomes restrictive when handling medical data since each modality also harbors specific knowledge relevant to downstream tasks. We introduce DRIM, a new multimodal method for capturing these shared and unique representations, despite data sparsity. More specifically, given a set of modalities, we aim to encode a representation for each one that can be divided into two components: one encapsulating patient-related information common across modalities and the other, encapsulating modality-specific details. This is achieved by increasing the shared information among different patient modalities while minimizing the overlap between shared and unique components within each modality. Our method outperforms state-of-the-art algorithms on glioma patients survival prediction tasks, while being robust to missing modalities. To promote reproducibility, the code is made publicly available at https://github.com/Lucas-rbnt/DRIM
Authors: Neda Zamanitajeddin, Mostafa Jahanifar, Kesi Xu, Fouzia Siraj, Nasir Rajpoot
Abstract: Deep learning models have shown immense promise in computational pathology (CPath) tasks, but their performance often suffers when applied to unseen data due to domain shifts. Addressing this requires domain generalization (DG) algorithms. However, a systematic evaluation of DG algorithms in the CPath context is lacking. This study aims to benchmark the effectiveness of 30 DG algorithms on 3 CPath tasks of varying difficulty through 7,560 cross-validation runs. We evaluate these algorithms using a unified and robust platform, incorporating modality-specific techniques and recent advances like pretrained foundation models. Our extensive cross-validation experiments provide insights into the relative performance of various DG strategies. We observe that self-supervised learning and stain augmentation consistently outperform other methods, highlighting the potential of pretrained models and data augmentation. Furthermore, we introduce a new pan-cancer tumor detection dataset (HISTOPANTUM) as a benchmark for future research. This study offers valuable guidance to researchers in selecting appropriate DG approaches for CPath tasks.
Authors: Tashi Namgyal, Alexander Hepburn, Raul Santos-Rodriguez, Valero Laparra, Jesus Malo
Abstract: The subjective quality of natural signals can be approximated with objective perceptual metrics. Designed to approximate the perceptual behaviour of human observers, perceptual metrics often reflect structures found in natural signals and neurological pathways. Models trained with perceptual metrics as loss functions can capture perceptually meaningful features from the structures held within these metrics. We demonstrate that using features extracted from autoencoders trained with perceptual losses can improve performance on music understanding tasks, i.e. genre classification, over using these metrics directly as distances when learning a classifier. This result suggests improved generalisation to novel signals when using perceptual metrics as loss functions for representation learning.
Authors: Luigi Russo, Francesco Mauro, Alessandro Sebastianelli, Paolo Gamba, Silvia Liberata Ullo
Abstract: Climate change and increasing droughts pose significant challenges to water resource management around the world. These problems lead to severe water shortages that threaten ecosystems, agriculture, and human communities. To advance the fight against these challenges, we present a new dataset, SEN12-WATER, along with a benchmark using a novel end-to-end Deep Learning (DL) framework for proactive drought-related analysis. The dataset, identified as a spatiotemporal datacube, integrates SAR polarization, elevation, slope, and multispectral optical bands. Our DL framework enables the analysis and estimation of water losses over time in reservoirs of interest, revealing significant insights into water dynamics for drought analysis by examining temporal changes in physical quantities such as water volume. Our methodology takes advantage of the multitemporal and multimodal characteristics of the proposed dataset, enabling robust generalization and advancing understanding of drought, contributing to climate change resilience and sustainable water resource management. The proposed framework involves, among the several components, speckle noise removal from SAR data, a water body segmentation through a U-Net architecture, the time series analysis, and the predictive capability of a Time-Distributed-Convolutional Neural Network (TD-CNN). Results are validated through ground truth data acquired on-ground via dedicated sensors and (tailored) metrics, such as Precision, Recall, Intersection over Union, Mean Squared Error, Structural Similarity Index Measure and Peak Signal-to-Noise Ratio.
Authors: Xinrui Zhou, Yuhao Huang, Haoran Dou, Shijing Chen, Ao Chang, Jia Liu, Weiran Long, Jian Zheng, Erjiao Xu, Jie Ren, Ruobing Huang, Jun Cheng, Wufeng Xue, Dong Ni
Abstract: In the medical field, the limited availability of large-scale datasets and labor-intensive annotation processes hinder the performance of deep models. Diffusion-based generative augmentation approaches present a promising solution to this issue, having been proven effective in advancing downstream medical recognition tasks. Nevertheless, existing works lack sufficient semantic and sequential steerability for challenging video/3D sequence generation, and neglect quality control of noisy synthesized samples, resulting in unreliable synthetic databases and severely limiting the performance of downstream tasks. In this work, we present Ctrl-GenAug, a novel and general generative augmentation framework that enables highly semantic- and sequential-customized sequence synthesis and suppresses incorrectly synthesized samples, to aid medical sequence classification. Specifically, we first design a multimodal conditions-guided sequence generator for controllably synthesizing diagnosis-promotive samples. A sequential augmentation module is integrated to enhance the temporal/stereoscopic coherence of generated samples. Then, we propose a noisy synthetic data filter to suppress unreliable cases at semantic and sequential levels. Extensive experiments on 3 medical datasets, using 11 networks trained on 3 paradigms, comprehensively analyze the effectiveness and generality of Ctrl-GenAug, particularly in underrepresented high-risk populations and out-domain conditions.
Authors: Luxu Liang, Ariel Neufeld, Ying Zhang
Abstract: In this paper, we provide a non-asymptotic analysis of the convergence of the stochastic gradient Hamiltonian Monte Carlo (SGHMC) algorithm to a target measure in Wasserstein-1 and Wasserstein-2 distance. Crucially, compared to the existing literature on SGHMC, we allow its stochastic gradient to be discontinuous. This allows us to provide explicit upper bounds, which can be controlled to be arbitrarily small, for the expected excess risk of non-convex stochastic optimization problems with discontinuous stochastic gradients, including, among others, the training of neural networks with ReLU activation function. To illustrate the applicability of our main results, we consider numerical experiments on quantile estimation and on several optimization problems involving ReLU neural networks relevant in finance and artificial intelligence.
Authors: Fan Zhou, Zengzhi Wang, Qian Liu, Junlong Li, Pengfei Liu
Abstract: Large language model pre-training has traditionally relied on human experts to craft heuristics for improving the corpora quality, resulting in numerous rules developed to date. However, these rules lack the flexibility to address the unique characteristics of individual example effectively. Meanwhile, applying tailored rules to every example is impractical for human experts. In this paper, we demonstrate that even small language models, with as few as 0.3B parameters, can exhibit substantial data refining capabilities comparable to those of human experts. We introduce Programming Every Example (ProX), a novel framework that treats data refinement as a programming task, enabling models to refine corpora by generating and executing fine-grained operations, such as string normalization, for each individual example at scale. Experimental results show that models pre-trained on ProX-curated data outperform either original data or data filtered by other selection methods by more than 2% across various downstream benchmarks. Its effectiveness spans various model sizes and pre-training corpora, including C4, RedPajama-V2, and FineWeb. Furthermore, ProX exhibits significant potential in domain-specific continual pre-training: without domain specific design, models trained on OpenWebMath refined by ProX outperform human-crafted rule-based methods, improving average accuracy by 7.6% over Mistral-7B, with 14.6% for Llama-2-7B and 20.3% for CodeLlama-7B, all within 10B tokens to be comparable to models like Llemma-7B trained on 200B tokens. Further analysis highlights that ProX significantly saves training FLOPs, offering a promising path for efficient LLM pre-training.We are open-sourcing ProX with >100B corpus, models, and sharing all training and implementation details for reproducible research and future innovation. Code: https://github.com/GAIR-NLP/ProX
Authors: Benji Peng, Xuanhe Pan, Yizhu Wen, Ziqian Bi, Keyu Chen, Ming Li, Ming Liu, Qian Niu, Junyu Liu, Jinlang Wang, Sen Zhang, Jiawei Xu, Pohsun Feng
Abstract: This book explores the role of Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL) in driving the progress of big data analytics and management. The book focuses on simplifying the complex mathematical concepts behind deep learning, offering intuitive visualizations and practical case studies to help readers understand how neural networks and technologies like Convolutional Neural Networks (CNNs) work. It introduces several classic models and technologies such as Transformers, GPT, ResNet, BERT, and YOLO, highlighting their applications in fields like natural language processing, image recognition, and autonomous driving. The book also emphasizes the importance of pre-trained models and how they can enhance model performance and accuracy, with instructions on how to apply these models in various real-world scenarios. Additionally, it provides an overview of key big data management technologies like SQL and NoSQL databases, as well as distributed computing frameworks such as Apache Hadoop and Spark, explaining their importance in managing and processing vast amounts of data. Ultimately, the book underscores the value of mastering deep learning and big data management skills as critical tools for the future workforce, making it an essential resource for both beginners and experienced professionals.
Authors: Andrew Goldberg, Kavish Kondap, Tianshuang Qiu, Zehan Ma, Letian Fu, Justin Kerr, Huang Huang, Kaiyuan Chen, Kuan Fang, Ken Goldberg
Abstract: Generative AI systems have shown impressive capabilities in creating text, code, and images. Inspired by the rich history of research in industrial ''Design for Assembly'', we introduce a novel problem: Generative Design-for-Robot-Assembly (GDfRA). The task is to generate an assembly based on a natural language prompt (e.g., ''giraffe'') and an image of available physical components, such as 3D-printed blocks. The output is an assembly, a spatial arrangement of these components, and instructions for a robot to build this assembly. The output must 1) resemble the requested object and 2) be reliably assembled by a 6 DoF robot arm with a suction gripper. We then present Blox-Net, a GDfRA system that combines generative vision language models with well-established methods in computer vision, simulation, perturbation analysis, motion planning, and physical robot experimentation to solve a class of GDfRA problems with minimal human supervision. Blox-Net achieved a Top-1 accuracy of 63.5% in the ''recognizability'' of its designed assemblies (eg, resembling giraffe as judged by a VLM). These designs, after automated perturbation redesign, were reliably assembled by a robot, achieving near-perfect success across 10 consecutive assembly iterations with human intervention only during reset prior to assembly. Surprisingly, this entire design process from textual word (''giraffe'') to reliable physical assembly is performed with zero human intervention.
Authors: Xin Chen, Yifan Hu, Minda Zhao
Abstract: Policy gradient methods are widely used in reinforcement learning. Yet, the nonconvexity of policy optimization imposes significant challenges in understanding the global convergence of policy gradient methods. For a class of finite-horizon Markov Decision Processes (MDPs) with general state and action spaces, we develop a framework that provides a set of easily verifiable assumptions to ensure the Kurdyka-Lojasiewicz (KL) condition of the policy optimization. Leveraging the KL condition, policy gradient methods converge to the globally optimal policy with a non-asymptomatic rate despite nonconvexity. Our results find applications in various control and operations models, including entropy-regularized tabular MDPs, Linear Quadratic Regulator (LQR) problems, stochastic inventory models, and stochastic cash balance problems, for which we show an $\epsilon$-optimal policy can be obtained using a sample size in $\tilde{\mathcal{O}}(\epsilon^{-1})$ and polynomial in terms of the planning horizon by stochastic policy gradient methods. Our result establishes the first sample complexity for multi-period inventory systems with Markov-modulated demands and stochastic cash balance problems in the literature.
Authors: Ran Zhang (Linda), Bowei Li (Linda), Liyuan Zhang (Linda), Jiang (Linda), Xie, Miao Wang
Abstract: Unmanned Aerial Vehicle (UAV) based communication networks (UCNs) are a key component in future mobile networking. To handle the dynamic environments in UCNs, reinforcement learning (RL) has been a promising solution attributed to its strong capability of adaptive decision-making free of the environment models. However, most existing RL-based research focus on control strategy design assuming a fixed set of UAVs. Few works have investigated how UCNs should be adaptively regulated when the serving UAVs change dynamically. This article discusses RL-based strategy design for adaptive UCN regulation given a dynamic UAV set, addressing both reactive strategies in general UCNs and proactive strategies in solar-powered UCNs. An overview of the UCN and the RL framework is first provided. Potential research directions with key challenges and possible solutions are then elaborated. Some of our recent works are presented as case studies to inspire innovative ways to handle dynamic UAV crew with different RL algorithms.
Authors: Fazal Mittu, Yihuan Bu, Akshat Gupta, Ashok Devireddy, Alp Eren Ozdarendeli, Anant Singh, Gopala Anumanchipalli
Abstract: While the language modeling objective has been shown to be deeply connected with compression, it is surprising that modern LLMs are not employed in practical text compression systems. In this paper, we provide an in-depth analysis of neural network and transformer-based compression techniques to answer this question. We compare traditional text compression systems with neural network and LLM-based text compression methods. Although LLM-based systems significantly outperform conventional compression methods, they are highly impractical. Specifically, LLMZip, a recent text compression system using Llama3-8B requires 9.5 days to compress just 10 MB of text, although with huge improvements in compression ratios. To overcome this, we present FineZip - a novel LLM-based text compression system that combines ideas of online memorization and dynamic context to reduce the compression time immensely. FineZip can compress the above corpus in approximately 4 hours compared to 9.5 days, a 54 times improvement over LLMZip and comparable performance. FineZip outperforms traditional algorithmic compression methods with a large margin, improving compression ratios by approximately 50\%. With this work, we take the first step towards making lossless text compression with LLMs a reality. While FineZip presents a significant step in that direction, LLMs are still not a viable solution for large-scale text compression. We hope our work paves the way for future research and innovation to solve this problem.
Authors: Yukun Huang, Jianan Wang, Ailing Zeng, Zheng-Jun Zha, Lei Zhang, Xihui Liu
Abstract: Leveraging pretrained 2D diffusion models and score distillation sampling (SDS), recent methods have shown promising results for text-to-3D avatar generation. However, generating high-quality 3D avatars capable of expressive animation remains challenging. In this work, we present DreamWaltz-G, a novel learning framework for animatable 3D avatar generation from text. The core of this framework lies in Skeleton-guided Score Distillation and Hybrid 3D Gaussian Avatar representation. Specifically, the proposed skeleton-guided score distillation integrates skeleton controls from 3D human templates into 2D diffusion models, enhancing the consistency of SDS supervision in terms of view and human pose. This facilitates the generation of high-quality avatars, mitigating issues such as multiple faces, extra limbs, and blurring. The proposed hybrid 3D Gaussian avatar representation builds on the efficient 3D Gaussians, combining neural implicit fields and parameterized 3D meshes to enable real-time rendering, stable SDS optimization, and expressive animation. Extensive experiments demonstrate that DreamWaltz-G is highly effective in generating and animating 3D avatars, outperforming existing methods in both visual quality and animation expressiveness. Our framework further supports diverse applications, including human video reenactment and multi-subject scene composition.
Authors: Matt Deitke, Christopher Clark, Sangho Lee, Rohun Tripathi, Yue Yang, Jae Sung Park, Mohammadreza Salehi, Niklas Muennighoff, Kyle Lo, Luca Soldaini, Jiasen Lu, Taira Anderson, Erin Bransom, Kiana Ehsani, Huong Ngo, YenSung Chen, Ajay Patel, Mark Yatskar, Chris Callison-Burch, Andrew Head, Rose Hendrix, Favyen Bastani, Eli VanderBilt, Nathan Lambert, Yvonne Chou, Arnavi Chheda, Jenna Sparks, Sam Skjonsberg, Michael Schmitz, Aaron Sarnat, Byron Bischoff, Pete Walsh, Chris Newell, Piper Wolters, Tanmay Gupta, Kuo-Hao Zeng, Jon Borchardt, Dirk Groeneveld, Jen Dumas, Crystal Nam, Sophie Lebrecht, Caitlin Wittlif, Carissa Schoenick, Oscar Michel, Ranjay Krishna, Luca Weihs, Noah A. Smith, Hannaneh Hajishirzi, Ross Girshick, Ali Farhadi, Aniruddha Kembhavi
Abstract: Today's most advanced multimodal models remain proprietary. The strongest open-weight models rely heavily on synthetic data from proprietary VLMs to achieve good performance, effectively distilling these closed models into open ones. As a result, the community is still missing foundational knowledge about how to build performant VLMs from scratch. We present Molmo, a new family of VLMs that are state-of-the-art in their class of openness. Our key innovation is a novel, highly detailed image caption dataset collected entirely from human annotators using speech-based descriptions. To enable a wide array of user interactions, we also introduce a diverse dataset mixture for fine-tuning that includes in-the-wild Q&A and innovative 2D pointing data. The success of our approach relies on careful choices for the model architecture details, a well-tuned training pipeline, and, most critically, the quality of our newly collected datasets, all of which will be released. The best-in-class 72B model within the Molmo family not only outperforms others in the class of open weight and data models but also compares favorably against proprietary systems like GPT-4o, Claude 3.5, and Gemini 1.5 on both academic benchmarks and human evaluation. We will be releasing all of our model weights, captioning and fine-tuning data, and source code in the near future. Select model weights, inference code, and demo are available at https://molmo.allenai.org.
Authors: Bingyang Wu, Yinmin Zhong, Zili Zhang, Shengyu Liu, Fangyue Liu, Yuanhang Sun, Gang Huang, Xuanzhe Liu, Xin Jin
Abstract: Large language models (LLMs) power a new generation of interactive AI applications exemplified by ChatGPT. The interactive nature of these applications demands low latency for LLM inference. Existing LLM serving systems use run-to-completion processing for inference jobs, which suffers from head-of-line blocking and long latency. We present FastServe, a distributed inference serving system for LLMs. FastServe exploits the autoregressive pattern of LLM inference to enable preemption at the granularity of each output token. FastServe uses preemptive scheduling to minimize latency with a novel skip-join Multi-Level Feedback Queue scheduler. Based on the new semi-information-agnostic setting of LLM inference, the scheduler leverages the input length information to assign an appropriate initial queue for each arrival job to join. The higher priority queues than the joined queue are skipped to reduce demotions. We design an efficient GPU memory management mechanism that proactively offloads and uploads intermediate state between GPU memory and host memory for LLM inference. We build a system prototype of FastServe and experimental results show that compared to the state-of-the-art solution vLLM, FastServe improves the throughput by up to 31.4x and 17.9x under the same average and tail latency requirements, respectively.
Authors: Tomoya Yamashita, Masanori Yamada, Takashi Shibata
Abstract: Ethical and privacy issues inherent in artificial intelligence (AI) applications have been a growing concern with the rapid spread of deep learning. Machine unlearning (MU) is the research area that addresses these issues by making a trained AI model forget about undesirable training data. Unfortunately, most existing MU methods incur significant time and computational costs for forgetting. Therefore, it is often difficult to apply these methods to practical datasets and sophisticated architectures, e.g., ImageNet and Transformer. To tackle this problem, we propose a lightweight and effective MU method. Our method identifies the model parameters sensitive to the forgetting targets and adds perturbation to such model parameters. We identify the sensitive parameters by calculating the Fisher Information Matrix (FIM). This approach does not require time-consuming additional training for forgetting. In addition, we introduce class-specific random signals called mnemonic code to reduce the cost of FIM calculation, which generally requires the entire training data and incurs significant computational costs. In our method, we train the model with mnemonic code; when forgetting, we use a small number of mnemonic codes to calculate the FIM and get the effective perturbation for forgetting. Comprehensive experiments demonstrate that our method is faster and better at forgetting than existing MU methods. Furthermore, we show that our method can scale to more practical datasets and sophisticated architectures.
Authors: Yu-Zhen Janice Chen, Daniel S. Menasch\'e, Don Towsley
Abstract: Effective resource allocation in sensor networks, IoT systems, and distributed computing is essential for applications such as environmental monitoring, surveillance, and smart infrastructure. Sensors or agents must optimize their resource allocation to maximize the accuracy of parameter estimation. In this work, we consider a group of sensors or agents, each sampling from a different variable of a multivariate Gaussian distribution and having a different estimation objective. We formulate a sensor or agent's data collection and collaboration policy design problem as a Fisher information maximization (or Cramer-Rao bound minimization) problem. This formulation captures a novel trade-off in energy use, between locally collecting univariate samples and collaborating to produce multivariate samples. When knowledge of the correlation between variables is available, we analytically identify two cases: (1) where the optimal data collection policy entails investing resources to transfer information for collaborative sampling, and (2) where knowledge of the correlation between samples cannot enhance estimation efficiency. When knowledge of certain correlations is unavailable, but collaboration remains potentially beneficial, we propose novel approaches that apply multi-armed bandit algorithms to learn the optimal data collection and collaboration policy in our sequential distributed parameter estimation problem. We illustrate the effectiveness of the proposed algorithms, DOUBLE-F, DOUBLE-Z, UCB-F, UCB-Z, through simulation.
Authors: Jingtan Wang, Xinyang Lu, Zitong Zhao, Zhongxiang Dai, Chuan-Sheng Foo, See-Kiong Ng, Bryan Kian Hsiang Low
Abstract: The impressive performances of Large Language Models (LLMs) and their immense potential for commercialization have given rise to serious concerns over the Intellectual Property (IP) of their training data. In particular, the synthetic texts generated by LLMs may infringe the IP of the data being used to train the LLMs. To this end, it is imperative to be able to perform source attribution by identifying the data provider who contributed to the generation of a synthetic text by an LLM. In this paper, we show that this problem can be tackled by watermarking, i.e., by enabling an LLM to generate synthetic texts with embedded watermarks that contain information about their source(s). We identify the key properties of such watermarking frameworks (e.g., source attribution accuracy, robustness against adversaries), and propose a source attribution framework that satisfies these key properties due to our algorithmic designs. Our framework enables an LLM to learn an accurate mapping from the generated texts to data providers, which sets the foundation for effective source attribution. Extensive empirical evaluations show that our framework achieves effective source attribution.
Authors: Seonghyun Park, Narae Ryu, Gahee Kim, Dongyeop Woo, Se-Young Yun, Sungsoo Ahn
Abstract: The celebrated message-passing updates for graph neural networks allow representing large-scale graphs with local and computationally tractable updates. However, the updates suffer from backtracking, i.e., a message flowing through the same edge twice and revisiting the previously visited node. Since the number of message flows increases exponentially with the number of updates, the redundancy in local updates prevents the graph neural network from accurately recognizing a particular message flow relevant for downstream tasks. In this work, we propose to resolve such a redundancy issue via the non-backtracking graph neural network (NBA-GNN) that updates a message without incorporating the message from the previously visited node. We theoretically investigate how NBA-GNN alleviates the over-squashing of GNNs, and establish a connection between NBA-GNN and the impressive performance of non-backtracking updates for stochastic block model recovery. Furthermore, we empirically verify the effectiveness of our NBA-GNN on the long-range graph benchmark and transductive node classification problems.
Authors: Xing Shen, Hengguan Huang, Brennan Nichyporuk, Tal Arbel
Abstract: Ensemble deep learning has been shown to achieve high predictive accuracy and uncertainty estimation in a wide variety of medical imaging contexts. However, perturbations in the input images at test time (e.g. noise, domain shifts) can still lead to significant performance degradation, posing challenges for trustworthy clinical deployment. In order to address this, we propose LaDiNE, a novel and robust probabilistic method that is capable of inferring informative and invariant latent variables from the input images. These latent variables are then used to recover the robust predictive distribution without relying on a predefined functional-form. This results in improved (i) generalization capabilities and (ii) calibration of prediction confidence. Extensive experiments were performed on the task of disease classification based on the Tuberculosis chest X-ray and the ISIC Melanoma skin cancer datasets. Here the performance of LaDiNE was analysed under a range of challenging covariate shift conditions, where training was based on "clean" images, and unseen noisy inputs and adversarial perturbations were presented at test time. Results show that LaDiNE outperforms existing state-of-the-art baseline methods in terms of accuracy and confidence calibration. This increases the feasibility of deploying reliable medical machine learning models in real clinical settings, where accurate and trustworthy predictions are crucial for patient care and clinical decision support.
Authors: Aytijhya Saha, Nikhil R. Pal
Abstract: In this paper, we present a novel embedded feature selection method based on a Multi-layer Perceptron (MLP) network and generalize it for group-feature or sensor selection problems, which can control the level of redundancy among the selected features or groups. Additionally, we have generalized the group lasso penalty for feature selection to encompass a mechanism for selecting valuable group features while simultaneously maintaining a control over redundancy. We establish the monotonicity and convergence of the proposed algorithm, with a smoothed version of the penalty terms, under suitable assumptions. Experimental results on several benchmark datasets demonstrate the promising performance of the proposed methodology for both feature selection and group feature selection over some state-of-the-art methods.
Authors: Shushman Choudhury, Abdul Rahman Kreidieh, Iveel Tsogsuren, Neha Arora, Carolina Osorio, Alexandre Bayen
Abstract: We propose and study a data-driven framework for identifying traffic congestion functions (numerical relationships between observations of traffic variables) at global scale and segment-level granularity. In contrast to methods that estimate a separate set of parameters for each roadway, ours learns a single black-box function over all roadways in a metropolitan area. First, we pool traffic data from all segments into one dataset, combining static attributes with dynamic time-dependent features. Second, we train a feed-forward neural network on this dataset, which we can then use on any segment in the area. We evaluate how well our framework identifies congestion functions on observed segments and how it generalizes to unobserved segments and predicts segment attributes on a large dataset covering multiple cities worldwide. For identification error on observed segments, our single data-driven congestion function compares favorably to segment-specific model-based functions on highway roads, but has room to improve on arterial roads. For generalization, our approach shows strong performance across cities and road types: both on unobserved segments in the same city and on zero-shot transfer learning between cities. Finally, for predicting segment attributes, we find that our approach can approximate critical densities for individual segments using their static properties.
Authors: Jo\~ao Vitor Pamplona, Jan Pablo Burgard
Abstract: To ensure unbiased and ethical automated predictions, fairness must be a core principle in machine learning applications. Fairness in machine learning aims to mitigate biases present in the training data and model imperfections that could lead to discriminatory outcomes. This is achieved by preventing the model from making decisions based on sensitive characteristics like ethnicity or sexual orientation. A fundamental assumption in machine learning is the independence of observations. However, this assumption often does not hold true for data describing social phenomena, where data points are often clustered based. Hence, if the machine learning models do not account for the cluster correlations, the results may be biased. Especially high is the bias in cases where the cluster assignment is correlated to the variable of interest. We present a fair mixed effects support vector machine algorithm that can handle both problems simultaneously. With a reproducible simulation study we demonstrate the impact of clustered data on the quality of fair machine learning predictions.
Authors: Kazuki Sakamoto, Connor T. Jerzak, Adel Daoud
Abstract: Earth observation (EO) data such as satellite imagery can have far-reaching impacts on our understanding of the geography of poverty, especially when coupled with machine learning (ML) and computer vision. Early research in computer vision used predictive models to estimate living conditions, especially in contexts where data availability on poverty was scarce. Recent work has progressed beyond using EO data to predict such outcomes -- now also using it to conduct causal inference. However, how such EO-ML models are used for causality remains incompletely mapped. To address this gap, we conduct a scoping review where we first document the growth of interest in using satellite images and other sources of EO data in causal analysis. We then trace the methodological relationship between spatial statistics and ML methods before discussing five ways in which EO data has been used in scientific workflows -- (1) outcome imputation for downstream causal analysis, (2) EO image deconfounding, (3) EO-based treatment effect heterogeneity, (4) EO-based transportability analysis, and (5) image-informed causal discovery. We consolidate these observations by providing a detailed workflow for how researchers can incorporate EO data in causal analysis going forward -- from data requirements to choice of computer vision model and evaluation metrics. While our discussion focuses on health and living conditions outcomes, our workflow applies to other measures of sustainable development where EO data are informative.
Authors: Jesse van Oostrum, Carlotta Langer, Nihat Ay
Abstract: In this paper we present a concise mathematical description of active inference in discrete time. The main part of the paper serves as a basic introduction to the topic, including a detailed example illustrating the theory on action selection. In the appendix the more subtle mathematical details are discussed. This part is aimed at readers who have already studied the active inference literature but struggle to make sense of the mathematical details and derivations. Throughout the whole manuscript, special attention has been paid to adopting notation that is both precise and in line with standard mathematical texts. All equations and derivations are linked to specific equation numbers in other popular text on the topic. Furthermore, Python code is provided that implements the action selection mechanism described in this paper and is compatible with pymdp environments.
Authors: Byung-Kwan Lee, Sangyun Chung, Chae Won Kim, Beomchan Park, Yong Man Ro
Abstract: Large language and vision models (LLVMs) have been driven by the generalization power of large language models (LLMs) and the advent of visual instruction tuning. Along with scaling them up directly, these models enable LLVMs to showcase powerful vision language (VL) performances by covering diverse tasks via natural language instructions. However, existing open-source LLVMs that perform comparably to closed-source LLVMs such as GPT-4V are often considered too large (e.g., 26B, 34B, and 110B parameters), having a larger number of layers. These large models demand costly, high-end resources for both training and inference. To address this issue, we present a new efficient LLVM family with 1.8B, 3.8B, and 7B LLM model sizes, Traversal of Layers (TroL), which enables the reuse of layers in a token-wise manner. This layer traversing technique simulates the effect of looking back and retracing the answering stream while increasing the number of forward propagation layers without physically adding more layers. We demonstrate that TroL employs a simple layer traversing approach yet efficiently outperforms the open-source LLVMs with larger model sizes and rivals the performances of the closed-source LLVMs with substantial sizes.
Authors: John Mango, Ronald Katende
Abstract: This paper introduces a dynamic, error-bounded hierarchical matrix (H-matrix) compression method tailored for Physics-Informed Neural Networks (PINNs). The proposed approach reduces the computational complexity and memory demands of large-scale physics-based models while preserving the essential properties of the Neural Tangent Kernel (NTK). By adaptively refining hierarchical matrix approximations based on local error estimates, our method ensures efficient training and robust model performance. Empirical results demonstrate that this technique outperforms traditional compression methods, such as Singular Value Decomposition (SVD), pruning, and quantization, by maintaining high accuracy and improving generalization capabilities. Additionally, the dynamic H-matrix method enhances inference speed, making it suitable for real-time applications. This approach offers a scalable and efficient solution for deploying PINNs in complex scientific and engineering domains, bridging the gap between computational feasibility and real-world applicability.
Authors: Ahmet Kapki\c{c}, Pratanu Mandal, Shu Wan, Paras Sheth, Abhinav Gorantla, Yoonhyuk Choi, Huan Liu, K. Sel\c{c}uk Candan
Abstract: While witnessing the exceptional success of machine learning (ML) technologies in many applications, users are starting to notice a critical shortcoming of ML: correlation is a poor substitute for causation. The conventional way to discover causal relationships is to use randomized controlled experiments (RCT); in many situations, however, these are impractical or sometimes unethical. Causal learning from observational data offers a promising alternative. While being relatively recent, causal learning aims to go far beyond conventional machine learning, yet several major challenges remain. Unfortunately, advances are hampered due to the lack of unified benchmark datasets, algorithms, metrics, and evaluation service interfaces for causal learning. In this paper, we introduce {\em CausalBench}, a transparent, fair, and easy-to-use evaluation platform, aiming to (a) enable the advancement of research in causal learning by facilitating scientific collaboration in novel algorithms, datasets, and metrics and (b) promote scientific objectivity, reproducibility, fairness, and awareness of bias in causal learning research. CausalBench provides services for benchmarking data, algorithms, models, and metrics, impacting the needs of a broad of scientific and engineering disciplines.
Authors: Bo-Yi Lin, Kai Chun Lin
Abstract: This paper presents a comprehensive numerical analysis of centrifugal clutch systems integrated with a two-speed automatic transmission, a key component in automotive torque transfer. Centrifugal clutches enable torque transmission based on rotational speed without external controls. The study systematically examines various clutch configurations effects on transmission dynamics, focusing on torque transfer, upshifting, and downshifting behaviors under different conditions. A Deep Neural Network (DNN) model predicts clutch engagement using parameters such as spring preload and shoe mass, offering an efficient alternative to complex simulations. The integration of deep learning and numerical modeling provides critical insights for optimizing clutch designs, enhancing transmission performance and efficiency.
Authors: East Sun, Yan Wang, Lan Tian
Abstract: We introduce Block-Attention, an attention mechanism designed to address the increased inference latency and cost in Retrieval-Augmented Generation (RAG) scenarios. Unlike existing works that encodes the whole context, its main idea lies in dividing the retrieved documents into blocks, where each block calculates 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, significantly reducing the latency and the computation cost during inference. 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 (the time to first token) and FLOPs (floating point operations) 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 and corresponding FLOPs are reduced by 98.7\% and 99.8\%, respectively.
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: 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: 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: Alexandre d'Aspremont, Damien Scieur, Adrien Taylor
Abstract: This monograph covers some recent advances in a range of acceleration techniques frequently used in convex optimization. We first use quadratic optimization problems to introduce two key families of methods, namely momentum and nested optimization schemes. They coincide in the quadratic case to form the Chebyshev method. We discuss momentum methods in detail, starting with the seminal work of Nesterov and structure convergence proofs using a few master templates, such as that for optimized gradient methods, which provide the key benefit of showing how momentum methods optimize convergence guarantees. We further cover proximal acceleration, at the heart of the Catalyst and Accelerated Hybrid Proximal Extragradient frameworks, using similar algorithmic patterns. Common acceleration techniques rely directly on the knowledge of some of the regularity parameters in the problem at hand. We conclude by discussing restart schemes, a set of simple techniques for reaching nearly optimal convergence rates while adapting to unobserved regularity parameters.
Authors: El Mehdi Achour (IMT), Fran\c{c}ois Malgouyres (IMT), S\'ebastien Gerchinovitz (IMT)
Abstract: We study the optimization landscape of deep linear neural networks with the square loss. It is known that, under weak assumptions, there are no spurious local minima and no local maxima. However, the existence and diversity of non-strict saddle points, which can play a role in first-order algorithms' dynamics, have only been lightly studied. We go a step further with a full analysis of the optimization landscape at order 2. We characterize, among all critical points, which are global minimizers, strict saddle points, and non-strict saddle points. We enumerate all the associated critical values. The characterization is simple, involves conditions on the ranks of partial matrix products, and sheds some light on global convergence or implicit regularization that have been proved or observed when optimizing linear neural networks. In passing, we provide an explicit parameterization of the set of all global minimizers and exhibit large sets of strict and non-strict saddle points.
Authors: Alina Jade Barnett, Zhicheng Guo, Jin Jing, Wendong Ge, Peter W. Kaplan, Wan Yee Kong, Ioannis Karakis, Aline Herlopian, Lakshman Arcot Jayagopal, Olga Taraschenko, Olga Selioutski, Gamaleldin Osman, Daniel Goldenholz, Cynthia Rudin, M. Brandon Westover
Abstract: In intensive care units (ICUs), critically ill patients are monitored with electroencephalograms (EEGs) to prevent serious brain injury. The number of patients who can be monitored is constrained by the availability of trained physicians to read EEGs, and EEG interpretation can be subjective and prone to inter-observer variability. Automated deep learning systems for EEG could reduce human bias and accelerate the diagnostic process. However, black box deep learning models are untrustworthy, difficult to troubleshoot, and lack accountability in real-world applications, leading to a lack of trust and adoption by clinicians. To address these challenges, we propose a novel interpretable deep learning model that not only predicts the presence of harmful brainwave patterns but also provides high-quality case-based explanations of its decisions. Our model performs better than the corresponding black box model, despite being constrained to be interpretable. The learned 2D embedded space provides the first global overview of the structure of ictal-interictal-injury continuum brainwave patterns. The ability to understand how our model arrived at its decisions will not only help clinicians to diagnose and treat harmful brain activities more accurately but also increase their trust and adoption of machine learning models in clinical practice; this could be an integral component of the ICU neurologists' standard workflow.
Authors: Ryan Koo, Minhwa Lee, Vipul Raheja, Jong Inn Park, Zae Myung Kim, Dongyeop Kang
Abstract: Large Language Models are cognitively biased judges. Large Language Models (LLMs) have recently been shown to be effective as automatic evaluators with simple prompting and in-context learning. In this work, we assemble 15 LLMs of four different size ranges and evaluate their output responses by preference ranking from the other LLMs as evaluators, such as System Star is better than System Square. We then evaluate the quality of ranking outputs introducing the Cognitive Bias Benchmark for LLMs as Evaluators (CoBBLEr), a benchmark to measure six different cognitive biases in LLM evaluation outputs, such as the Egocentric bias where a model prefers to rank its own outputs highly in evaluation. We find that LLMs are biased text quality evaluators, exhibiting strong indications on our bias benchmark (average of 40% of comparisons across all models) within each of their evaluations that question their robustness as evaluators. Furthermore, we examine the correlation between human and machine preferences and calculate the average Rank-Biased Overlap (RBO) score to be 49.6%, indicating that machine preferences are misaligned with humans. According to our findings, LLMs may still be unable to be utilized for automatic annotation aligned with human preferences. Our project page is at: https://minnesotanlp.github.io/cobbler.
Authors: Quanqi Hu, Dixian Zhu, Tianbao Yang
Abstract: This paper investigates new families of compositional optimization problems, called $\underline{\bf n}$on-$\underline{\bf s}$mooth $\underline{\bf w}$eakly-$\underline{\bf c}$onvex $\underline{\bf f}$inite-sum $\underline{\bf c}$oupled $\underline{\bf c}$ompositional $\underline{\bf o}$ptimization (NSWC FCCO). There has been a growing interest in FCCO due to its wide-ranging applications in machine learning and AI, as well as its ability to address the shortcomings of stochastic algorithms based on empirical risk minimization. However, current research on FCCO presumes that both the inner and outer functions are smooth, limiting their potential to tackle a more diverse set of problems. Our research expands on this area by examining non-smooth weakly-convex FCCO, where the outer function is weakly convex and non-decreasing, and the inner function is weakly-convex. We analyze a single-loop algorithm and establish its complexity for finding an $\epsilon$-stationary point of the Moreau envelop of the objective function. Additionally, we also extend the algorithm to solving novel non-smooth weakly-convex tri-level finite-sum coupled compositional optimization problems, which feature a nested arrangement of three functions. Lastly, we explore the applications of our algorithms in deep learning for two-way partial AUC maximization and multi-instance two-way partial AUC maximization, using empirical studies to showcase the effectiveness of the proposed algorithms.
Authors: Xin Bing, Dian Jin, Yuqian Zhang
Abstract: Vintage factor analysis is one important type of factor analysis that aims to first find a low-dimensional representation of the original data, and then to seek a rotation such that the rotated low-dimensional representation is scientifically meaningful. The most widely used vintage factor analysis is the Principal Component Analysis (PCA) followed by the varimax rotation. Despite its popularity, little theoretical guarantee can be provided to date mainly because varimax rotation requires to solve a non-convex optimization over the set of orthogonal matrices. In this paper, we propose a deflation varimax procedure that solves each row of an orthogonal matrix sequentially. In addition to its net computational gain and flexibility, we are able to fully establish theoretical guarantees for the proposed procedure in a broader context. Adopting this new deflation varimax as the second step after PCA, we further analyze this two step procedure under a general class of factor models. Our results show that it estimates the factor loading matrix in the minimax optimal rate when the signal-to-noise-ratio (SNR) is moderate or large. In the low SNR regime, we offer possible improvement over using PCA and the deflation varimax when the additive noise under the factor model is structured. The modified procedure is shown to be minimax optimal in all SNR regimes. Our theory is valid for finite sample and allows the number of the latent factors to grow with the sample size as well as the ambient dimension to grow with, or even exceed, the sample size. Extensive simulation and real data analysis further corroborate our theoretical findings.
Authors: Saad Zafar Khan, Nazeefa Muzammil, Salman Ghafoor, Haibat Khan, Syed Mohammad Hasan Zaidi, Abdulah Jeza Aljohani, Imran Aziz
Abstract: Accurate solar power forecasting is pivotal for the global transition towards sustainable energy systems. This study conducts a meticulous comparison between Quantum Long Short-Term Memory (QLSTM) and classical Long Short-Term Memory (LSTM) models for solar power production forecasting. The primary objective is to evaluate the potential advantages of QLSTMs, leveraging their exponential representational capabilities, in capturing the intricate spatiotemporal patterns inherent in renewable energy data. Through controlled experiments on real-world photovoltaic datasets, our findings reveal promising improvements offered by QLSTMs, including accelerated training convergence and substantially reduced test loss within the initial epoch compared to classical LSTMs. These empirical results demonstrate QLSTM's potential to swiftly assimilate complex time series relationships, enabled by quantum phenomena like superposition. However, realizing QLSTM's full capabilities necessitates further research into model validation across diverse conditions, systematic hyperparameter optimization, hardware noise resilience, and applications to correlated renewable forecasting problems. With continued progress, quantum machine learning can offer a paradigm shift in renewable energy time series prediction, potentially ushering in an era of unprecedented accuracy and reliability in solar power forecasting worldwide. This pioneering work provides initial evidence substantiating quantum advantages over classical LSTM models while acknowledging present limitations. Through rigorous benchmarking grounded in real-world data, our study illustrates a promising trajectory for quantum learning in renewable forecasting.
Authors: Yuhui Zhang, Brandon McKinzie, Zhe Gan, Vaishaal Shankar, Alexander Toshev
Abstract: Recent advances in image tokenizers, such as VQ-VAE, have enabled text-to-image generation using auto-regressive methods, similar to language modeling. However, these methods have yet to leverage pre-trained language models, despite their adaptability to various downstream tasks. In this work, we explore this gap by adapting a pre-trained language model for auto-regressive text-to-image generation, and find that pre-trained language models offer limited help. We provide a two-fold explanation by analyzing tokens from each modality. First, we demonstrate that image tokens possess significantly different semantics compared to text tokens, rendering pre-trained language models no more effective in modeling them than randomly initialized ones. Second, the text tokens in the image-text datasets are too simple compared to normal language model pre-training data, which causes the catastrophic degradation of language models' capability.
Authors: Qiang Liu, Nils Thuerey
Abstract: Leveraging neural networks as surrogate models for turbulence simulation is a topic of growing interest. At the same time, embodying the inherent uncertainty of simulations in the predictions of surrogate models remains very challenging. The present study makes a first attempt to use denoising diffusion probabilistic models (DDPMs) to train an uncertainty-aware surrogate model for turbulence simulations. Due to its prevalence, the simulation of flows around airfoils with various shapes, Reynolds numbers, and angles of attack is chosen as the learning objective. Our results show that DDPMs can successfully capture the whole distribution of solutions and, as a consequence, accurately estimate the uncertainty of the simulations. The performance of DDPMs is also compared with varying baselines in the form of Bayesian neural networks and heteroscedastic models. Experiments demonstrate that DDPMs outperform the other methods regarding a variety of accuracy metrics. Besides, it offers the advantage of providing access to the complete distributions of uncertainties rather than providing a set of parameters. As such, it can yield realistic and detailed samples from the distribution of solutions. We also evaluate an emerging generative modeling variant, flow matching, in comparison to regular diffusion models. The results demonstrate that flow matching addresses the problem of slow sampling speed typically associated with diffusion models. As such, it offers a promising new paradigm for uncertainty quantification with generative models.
Authors: Qian Wang, Yaoyao Liu, Hefei Ling, Yingwei Li, Qihao Liu, Ping Li, Jiazhong Chen, Alan Yuille, Ning Yu
Abstract: In response to the rapidly evolving nature of adversarial attacks against visual classifiers on a monthly basis, numerous defenses have been proposed to generalize against as many known attacks as possible. However, designing a defense method that generalizes to all types of attacks is not realistic because the environment in which defense systems operate is dynamic and comprises various unique attacks that emerge as time goes on. A well-matched approach to the dynamic environment lies in a defense system that continuously collects adversarial data online to quickly improve itself. Therefore, we put forward a practical defense deployment against a challenging threat model and propose, for the first time, the Continual Adversarial Defense (CAD) framework that adapts to attack sequences under four principles: (1) continual adaptation to new attacks without catastrophic forgetting, (2) few-shot adaptation, (3) memory-efficient adaptation, and (4) high accuracy on both clean and adversarial data. We explore and integrate cutting-edge continual learning, few-shot learning, and ensemble learning techniques to qualify the principles. Extensive experiments validate the effectiveness of our approach against multiple stages of modern adversarial attacks and demonstrate significant improvements over numerous baseline methods. In particular, CAD is capable of quickly adapting with minimal budget and a low cost of defense failure while maintaining good performance against previous attacks. Our research sheds light on a brand-new paradigm for continual defense adaptation against dynamic and evolving attacks.
Authors: Zeping Yu, Sophia Ananiadou
Abstract: Identifying important neurons for final predictions is essential for understanding the mechanisms of large language models. Due to computational constraints, current attribution techniques struggle to operate at neuron level. In this paper, we propose a static method for pinpointing significant neurons. Compared to seven other methods, our approach demonstrates superior performance across three metrics. Additionally, since most static methods typically only identify "value neurons" directly contributing to the final prediction, we propose a method for identifying "query neurons" which activate these "value neurons". Finally, we apply our methods to analyze six types of knowledge across both attention and feed-forward network (FFN) layers. Our method and analysis are helpful for understanding the mechanisms of knowledge storage and set the stage for future research in knowledge editing. The code is available on https://github.com/zepingyu0512/neuron-attribution.
Authors: Siddhant Bhambri, Mudit Verma, Upasana Biswas, Anil Murthy, Subbarao Kambhampati
Abstract: Preference-based Reinforcement Learning (PbRL) has made significant strides in single-agent settings, but has not been studied for multi-agent frameworks. On the other hand, modeling cooperation between multiple agents, specifically, Human-AI Teaming settings while ensuring successful task completion is a challenging problem. To this end, we perform the first investigation of multi-agent PbRL by extending single-agent PbRL to the two-agent teaming settings and formulate it as a Human-AI PbRL Cooperation Game, where the RL agent queries the human-in-the-loop to elicit task objective and human's preferences on the joint team behavior. Under this game formulation, we first introduce the notion of Human Flexibility to evaluate team performance based on if humans prefer to follow a fixed policy or adapt to the RL agent on the fly. Secondly, we study the RL agent's varying access to the human policy. We highlight a special case along these two dimensions, which we call Specified Orchestration, where the human is least flexible and agent has complete access to human policy. We motivate the need for taking Human Flexibility into account and the usefulness of Specified Orchestration through a gamified user study. We evaluate state-of-the-art PbRL algorithms for Human-AI cooperative setups through robot locomotion based domains that explicitly require forced cooperation. Our findings highlight the challenges associated with PbRL by varying Human Flexibility and agent's access to the human policy. Finally, we draw insights from our user study and empirical results, and conclude that Specified Orchestration can be seen as an upper bound PbRL performance for future research in Human-AI teaming scenarios.
Authors: Hongcheng Liu, Jindong Tong
Abstract: This paper studies sample average approximation (SAA) in solving convex or strongly convex stochastic programming (SP) problems. Under some common regularity conditions, we show -- perhaps for the first time -- that SAA's sample complexity can be completely free from any quantification of metric entropy (such as the logarithm of the covering number), leading to a significantly more efficient rate with dimensionality $d$ than most existing results. From the newly established complexity bounds, an important revelation is that SAA and the canonical stochastic mirror descent (SMD) method, two mainstream solution approaches to SP, entail almost identical rates of sample efficiency, rectifying a persistent theoretical discrepancy of SAA from SMD by the order of $O(d)$. Furthermore, this paper explores non-Lipschitzian scenarios where SAA maintains provable efficacy but the corresponding results for SMD remain mostly unexplored, indicating the potential of SAA's better applicability in some irregular settings.
Authors: Seyed Mohammad Hossein Hashemi, Leila Safari, Amirhossein Dadashzadeh Taromi
Abstract: In the field of medical sciences, reliable detection and classification of brain tumors from images remains a formidable challenge due to the rarity of tumors within the population of patients. Therefore, the ability to detect tumors in anomaly scenarios is paramount for ensuring timely interventions and improved patient outcomes. This study addresses the issue by leveraging deep learning (DL) techniques to detect and classify brain tumors in challenging situations. The curated data set from the National Brain Mapping Lab (NBML) comprises 81 patients, including 30 Tumor cases and 51 Normal cases. The detection and classification pipelines are separated into two consecutive tasks. The detection phase involved comprehensive data analysis and pre-processing to modify the number of image samples and the number of patients of each class to anomaly distribution (9 Normal per 1 Tumor) to comply with real world scenarios. Next, in addition to common evaluation metrics for the testing, we employed a novel performance evaluation method called Patient to Patient (PTP), focusing on the realistic evaluation of the model. In the detection phase, we fine-tuned a YOLOv8n detection model to detect the tumor region. Subsequent testing and evaluation yielded competitive performance both in Common Evaluation Metrics and PTP metrics. Furthermore, using the Data Efficient Image Transformer (DeiT) module, we distilled a Vision Transformer (ViT) model from a fine-tuned ResNet152 as a teacher in the classification phase. This approach demonstrates promising strides in reliable tumor detection and classification, offering potential advancements in tumor diagnosis for real-world medical imaging scenarios.
Authors: Salar Nouri, Mojdeh Karbalaee Motalleb, Vahid Shah-Mansouri, Seyed Pooya Shariatpanahi
Abstract: This paper introduces an innovative approach to the resource allocation problem, aiming to coordinate multiple independent x-applications (xAPPs) for network slicing and resource allocation in the Open Radio Access Network (O-RAN). Our approach maximizes the weighted throughput among user equipment (UE) and allocates physical resource blocks (PRBs). We prioritize two service types: enhanced Mobile Broadband and Ultra-Reliable Low-Latency Communication. Two xAPPs have been designed to achieve this: a power control xAPP for each UE and a PRB allocation xAPP. The method consists of a two-part training phase. The first part uses supervised learning with a Variational Autoencoder trained to regress the power transmission, UE association, and PRB allocation decisions, and the second part uses unsupervised learning with a contrastive loss approach to improve the generalization and robustness of the model. We evaluate the performance by comparing its results to those obtained from an exhaustive search and deep Q-network algorithms and reporting performance metrics for the regression task. The results demonstrate the superior efficiency of this approach in different scenarios among the service types, reaffirming its status as a more efficient and effective solution for network slicing problems compared to state-of-the-art methods. This innovative approach not only sets our research apart but also paves the way for exciting future advancements in resource allocation in O-RAN.
Authors: Zeping Yu, Sophia Ananiadou
Abstract: We investigate the mechanism of in-context learning (ICL) on sentence classification tasks with semantically-unrelated labels ("foo"/"bar"). We find intervening in only 1\% heads (named "in-context heads") significantly affects ICL accuracy from 87.6\% to 24.4\%. To understand this phenomenon, we analyze the value-output vectors in these heads and discover that the vectors at each label position contain substantial information about the corresponding labels. Furthermore, we observe that the prediction shift from "foo" to "bar" is due to the respective reduction and increase in these heads' attention scores at "foo" and "bar" positions. Therefore, we propose a hypothesis for ICL: in in-context heads, the value-output matrices extract label features, while the query-key matrices compute the similarity between the features at the last position and those at each label position. The query and key matrices can be considered as two towers that learn the similarity metric between the last position's features and each demonstration at label positions. Using this hypothesis, we explain the majority label bias and recency bias in ICL and propose two methods to reduce these biases by 22\% and 17\%, respectively.
Authors: Santiago Miret, N M Anoop Krishnan
Abstract: Large Language Models (LLMs) create exciting possibilities for powerful language processing tools to accelerate research in materials science. While LLMs have great potential to accelerate materials understanding and discovery, they currently fall short in being practical materials science tools. In this position paper, we show relevant failure cases of LLMs in materials science that reveal current limitations of LLMs related to comprehending and reasoning over complex, interconnected materials science knowledge. Given those shortcomings, we outline a framework for developing Materials Science LLMs (MatSci-LLMs) that are grounded in materials science knowledge and hypothesis generation followed by hypothesis testing. The path to attaining performant MatSci-LLMs rests in large part on building high-quality, multi-modal datasets sourced from scientific literature where various information extraction challenges persist. As such, we describe key materials science information extraction challenges which need to be overcome in order to build large-scale, multi-modal datasets that capture valuable materials science knowledge. Finally, we outline a roadmap for applying future MatSci-LLMs for real-world materials discovery via: 1. Automated Knowledge Base Generation; 2. Automated In-Silico Material Design; and 3. MatSci-LLM Integrated Self-Driving Materials Laboratories.
Authors: Ezequiel Alvarez, Leandro Da Rold, Manuel Szewc, Alejandro Szynkman, Santiago A. Tanco, Tatiana Tarutina
Abstract: To find New Physics or to refine our knowledge of the Standard Model at the LHC is an enterprise that involves many factors. We focus on taking advantage of available information and pour our effort in re-thinking the usual data-driven ABCD method to improve it and to generalize it using Bayesian Machine Learning tools. We propose that a dataset consisting of a signal and many backgrounds is well described through a mixture model. Signal, backgrounds and their relative fractions in the sample can be well extracted by exploiting the prior knowledge and the dependence between the different observables at the event-by-event level with Bayesian tools. We show how, in contrast to the ABCD method, one can take advantage of understanding some properties of the different backgrounds and of having more than two independent observables to measure in each event. In addition, instead of regions defined through hard cuts, the Bayesian framework uses the information of continuous distribution to obtain soft-assignments of the events which are statistically more robust. To compare both methods we use a toy problem inspired by $pp\to hh\to b\bar b b \bar b$, selecting a reduced and simplified number of processes and analysing the flavor of the four jets and the invariant mass of the jet-pairs, modeled with simplified distributions. Taking advantage of all this information, and starting from a combination of biased and agnostic priors, leads us to a very good posterior once we use the Bayesian framework to exploit the data and the mutual information of the observables at the event-by-event level. We show how, in this simplified model, the Bayesian framework outperforms the ABCD method sensitivity in obtaining the signal fraction in scenarios with $1\%$ and $0.5\%$ true signal fractions in the dataset. We also show that the method is robust against the absence of signal.
Authors: Yujia Huang, Adishree Ghatare, Yuanzhe Liu, Ziniu Hu, Qinsheng Zhang, Chandramouli S Sastry, Siddharth Gururani, Sageev Oore, Yisong Yue
Abstract: We study the problem of symbolic music generation (e.g., generating piano rolls), with a technical focus on non-differentiable rule guidance. Musical rules are often expressed in symbolic form on note characteristics, such as note density or chord progression, many of which are non-differentiable which pose a challenge when using them for guided diffusion. We propose Stochastic Control Guidance (SCG), a novel guidance method that only requires forward evaluation of rule functions that can work with pre-trained diffusion models in a plug-and-play way, thus achieving training-free guidance for non-differentiable rules for the first time. Additionally, we introduce a latent diffusion architecture for symbolic music generation with high time resolution, which can be composed with SCG in a plug-and-play fashion. Compared to standard strong baselines in symbolic music generation, this framework demonstrates marked advancements in music quality and rule-based controllability, outperforming current state-of-the-art generators in a variety of settings. For detailed demonstrations, code and model checkpoints, please visit our project website: https://scg-rule-guided-music.github.io/.
Authors: Zhongqi Yang, Elahe Khatibi, Nitish Nagesh, Mahyar Abbasian, Iman Azimi, Ramesh Jain, Amir M. Rahmani
Abstract: The profound impact of food on health necessitates advanced nutrition-oriented food recommendation services. Conventional methods often lack the crucial elements of personalization, explainability, and interactivity. While Large Language Models (LLMs) bring interpretability and explainability, their standalone use falls short of achieving true personalization. In this paper, we introduce ChatDiet, a novel LLM-powered framework designed specifically for personalized nutrition-oriented food recommendation chatbots. ChatDiet integrates personal and population models, complemented by an orchestrator, to seamlessly retrieve and process pertinent information. The personal model leverages causal discovery and inference techniques to assess personalized nutritional effects for a specific user, whereas the population model provides generalized information on food nutritional content. The orchestrator retrieves, synergizes and delivers the output of both models to the LLM, providing tailored food recommendations designed to support targeted health outcomes. The result is a dynamic delivery of personalized and explainable food recommendations, tailored to individual user preferences. Our evaluation of ChatDiet includes a compelling case study, where we establish a causal personal model to estimate individual nutrition effects. Our assessments, including a food recommendation test showcasing a 92\% effectiveness rate, coupled with illustrative dialogue examples, underscore ChatDiet's strengths in explainability, personalization, and interactivity.
Authors: Muhammad A. Shah, David Solans Noguero, Mikko A. Heikkila, Bhiksha Raj, Nicolas Kourtellis
Abstract: As Automatic Speech Recognition (ASR) models become ever more pervasive, it is important to ensure that they make reliable predictions under corruptions present in the physical and digital world. We propose Speech Robust Bench (SRB), a comprehensive benchmark for evaluating the robustness of ASR models to diverse corruptions. SRB is composed of 114 input perturbations which simulate an heterogeneous range of corruptions that ASR models may encounter when deployed in the wild. We use SRB to evaluate the robustness of several state-of-the-art ASR models and observe that model size and certain modeling choices such as the use of discrete representations, or self-training appear to be conducive to robustness. We extend this analysis to measure the robustness of ASR models on data from various demographic subgroups, namely English and Spanish speakers, and males and females. Our results revealed noticeable disparities in the model's robustness across subgroups. We believe that SRB will significantly facilitate future research towards robust ASR models, by making it easier to conduct comprehensive and comparable robustness evaluations.
Authors: Alessandro Ilic Mezza, Riccardo Giampiccolo, Enzo De Sena, Alberto Bernardini
Abstract: Over the past few decades, extensive research has been devoted to the design of artificial reverberation algorithms aimed at emulating the room acoustics of physical environments. Despite significant advancements, automatic parameter tuning of delay-network models remains an open challenge. We introduce a novel method for finding the parameters of a Feedback Delay Network (FDN) such that its output renders target attributes of a measured room impulse response. The proposed approach involves the implementation of a differentiable FDN with trainable delay lines, which, for the first time, allows us to simultaneously learn each and every delay-network parameter via backpropagation. The iterative optimization process seeks to minimize a perceptually-motivated time-domain loss function incorporating differentiable terms accounting for energy decay and echo density. Through experimental validation, we show that the proposed method yields time-invariant frequency-independent FDNs capable of closely matching the desired acoustical characteristics, and outperforms existing methods based on genetic algorithms and analytical FDN design.
Authors: Omar Elezabi, Marcos V. Conde, Radu Timofte
Abstract: In modern smartphone cameras, the Image Signal Processor (ISP) is the core element that converts the RAW readings from the sensor into perceptually pleasant RGB images for the end users. The ISP is typically proprietary and handcrafted and consists of several blocks such as white balance, color correction, and tone mapping. Deep learning-based ISPs aim to transform RAW images into DSLR-like RGB images using deep neural networks. However, most learned ISPs are trained using patches (small regions) due to computational limitations. Such methods lack global context, which limits their efficacy on full-resolution images and harms their ability to capture global properties such as color constancy or illumination. First, we propose a novel module that can be integrated into any neural ISP to capture the global context information from the full RAW images. Second, we propose an efficient and simple neural ISP that utilizes our proposed module. Our model achieves state-of-the-art results on different benchmarks using diverse and real smartphone images.
Authors: Cristian J. Vaca-Rubio, Luis Blanco, Roberto Pereira, M\`arius Caus
Abstract: This paper introduces a novel application of Kolmogorov-Arnold Networks (KANs) to time series forecasting, leveraging their adaptive activation functions for enhanced predictive modeling. Inspired by the Kolmogorov-Arnold representation theorem, KANs replace traditional linear weights with spline-parametrized univariate functions, allowing them to learn activation patterns dynamically. We demonstrate that KANs outperforms conventional Multi-Layer Perceptrons (MLPs) in a real-world satellite traffic forecasting task, providing more accurate results with considerably fewer number of learnable parameters. We also provide an ablation study of KAN-specific parameters impact on performance. The proposed approach opens new avenues for adaptive forecasting models, emphasizing the potential of KANs as a powerful tool in predictive analytics.
Authors: Qian Wang, Chen Li, Yuchen Luo, Hefei Ling, Ping Li, Jiazhong Chen, Shijuan Huang, Ning Yu
Abstract: As a defense strategy against adversarial attacks, adversarial detection aims to identify and filter out adversarial data from the data flow based on discrepancies in distribution and noise patterns between natural and adversarial data. Although previous detection methods achieve high performance in detecting gradient-based adversarial attacks, new attacks based on generative models with imbalanced and anisotropic noise patterns evade detection. Even worse, existing techniques either necessitate access to attack data before deploying a defense or incur a significant time cost for inference, rendering them impractical for defending against newly emerging attacks that are unseen by defenders. In this paper, we explore the proximity relationship between adversarial noise distributions and demonstrate the existence of an open covering for them. By learning to distinguish this open covering from the distribution of natural data, we can develop a detector with strong generalization capabilities against all types of adversarial attacks. Based on this insight, we heuristically propose Perturbation Forgery, which includes noise distribution perturbation, sparse mask generation, and pseudo-adversarial data production, to train an adversarial detector capable of detecting unseen gradient-based, generative-model-based, and physical adversarial attacks, while remaining agnostic to any specific models. Comprehensive experiments conducted on multiple general and facial datasets, with a wide spectrum of attacks, validate the strong generalization of our method.
Authors: Joseph Spracklen, Raveen Wijewickrama, A H M Nazmus Sakib, Anindya Maiti, Bimal Viswanath, Murtuza Jadliwala
Abstract: The reliance of popular programming languages such as Python and JavaScript on centralized package repositories and open-source software, combined with the emergence of code-generating Large Language Models (LLMs), has created a new type of threat to the software supply chain: package hallucinations. These hallucinations, which arise from fact-conflicting errors when generating code using LLMs, represent a novel form of package confusion attack that poses a critical threat to the integrity of the software supply chain. This paper conducts a rigorous and comprehensive evaluation of package hallucinations across different programming languages, settings, and parameters, exploring how a diverse set of models and configurations affect the likelihood of generating erroneous package recommendations and identifying the root causes of this phenomenon. Using 16 popular LLMs for code generation and two unique prompt datasets, we generate 576,000 code samples in two programming languages that we analyze for package hallucinations. Our findings reveal that that the average percentage of hallucinated packages is at least 5.2% for commercial models and 21.7% for open-source models, including a staggering 205,474 unique examples of hallucinated package names, further underscoring the severity and pervasiveness of this threat. To overcome this problem, we implement several hallucination mitigation strategies and show that they are able to significantly reduce the number of package hallucinations while maintaining code quality. Our experiments and findings highlight package hallucinations as a persistent and systemic phenomenon while using state-of-the-art LLMs for code generation, and a significant challenge which deserves the research community's urgent attention.
Authors: Pedro Cisneros-Velarde
Abstract: We study the evolution of opinions inside a population of interacting large language models (LLMs). Every LLM needs to decide how much funding to allocate to an item with three initial possibilities: full, partial, or no funding. We identify biases that drive the exchange of opinions based on the LLM's tendency to find consensus with the other LLM's opinion, display caution when specifying funding, and consider ethical concerns in its opinion. We find these biases are affected by the perceived absence of compelling reasons for opinion change, the perceived willingness to engage in discussion, and the distribution of allocation values. Moreover, tensions among biases can lead to the survival of funding for items with negative connotations. We also find that the final distribution of full, partial, and no funding opinions is more diverse when an LLM freely forms its opinion after an interaction than when its opinion is a multiple-choice selection among the three allocation options. In the latter case, consensus is mostly attained. When agents are aware of past opinions, they seek to maintain consistency with them, changing the opinion dynamics. Our study is performed using Llama 3 and Mistral LLMs.
Authors: Junying Chen, Chi Gui, Ruyi Ouyang, Anningzhe Gao, Shunian Chen, Guiming Hardy Chen, Xidong Wang, Ruifei Zhang, Zhenyang Cai, Ke Ji, Guangjun Yu, Xiang Wan, Benyou Wang
Abstract: The rapid development of multimodal large language models (MLLMs), such as GPT-4V, has led to significant advancements. However, these models still face challenges in medical multimodal capabilities due to limitations in the quantity and quality of medical vision-text data, stemming from data privacy concerns and high annotation costs. While pioneering approaches utilize PubMed's large-scale, de-identified medical image-text pairs to address these limitations, they still fall short due to inherent data noise. To tackle this, we refined medical image-text pairs from PubMed and employed MLLMs (GPT-4V) in an 'unblinded' capacity to denoise and reformat the data, resulting in the creation of the PubMedVision dataset with 1.3 million medical VQA samples. Our validation demonstrates that: (1) PubMedVision can significantly enhance the medical multimodal capabilities of current MLLMs, showing significant improvement in benchmarks including the MMMU Health & Medicine track; (2) manual checks by medical experts and empirical results validate the superior data quality of our dataset compared to other data construction methods. Using PubMedVision, we train a 34B medical MLLM HuatuoGPT-Vision, which shows superior performance in medical multimodal scenarios among open-source MLLMs.
Authors: Matteo Belenchia, Flavio Corradini, Michela Quadrini, Michele Loreti
Abstract: Graph neural networks form a class of deep learning architectures specifically designed to work with graph-structured data. As such, they share the inherent limitations and problems of deep learning, especially regarding the issues of explainability and trustworthiness. We propose $\mu\mathcal{G}$, an original domain-specific language for the specification of graph neural networks that aims to overcome these issues. The language's syntax is introduced, and its meaning is rigorously defined by a denotational semantics. An equivalent characterization in the form of an operational semantics is also provided and, together with a type system, is used to prove the type soundness of $\mu\mathcal{G}$. We show how $\mu\mathcal{G}$ programs can be represented in a more user-friendly graphical visualization, and provide examples of its generality by showing how it can be used to define some of the most popular graph neural network models, or to develop any custom graph processing application.
Authors: Naoya Sogi, Takashi Shibata, Makoto Terao
Abstract: The pre-trained vision and language (V\&L) models have substantially improved the performance of cross-modal image-text retrieval. In general, however, V\&L models have limited retrieval performance for small objects because of the rough alignment between words and the small objects in the image. In contrast, it is known that human cognition is object-centric, and we pay more attention to important objects, even if they are small. To bridge this gap between the human cognition and the V\&L model's capability, we propose a cross-modal image-text retrieval framework based on ``object-aware query perturbation.'' The proposed method generates a key feature subspace of the detected objects and perturbs the corresponding queries using this subspace to improve the object awareness in the image. In our proposed method, object-aware cross-modal image-text retrieval is possible while keeping the rich expressive power and retrieval performance of existing V\&L models without additional fine-tuning. Comprehensive experiments on four public datasets show that our method outperforms conventional algorithms. Our code is publicly available at \url{https://github.com/NEC-N-SOGI/query-perturbation}.
Authors: Zhanpeng Chen, Chengjin Xu, Yiyan Qi, Jian Guo
Abstract: Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in processing and generating content across multiple data modalities. However, a significant drawback of MLLMs is their reliance on static training data, leading to outdated information and limited contextual awareness. This static nature hampers their ability to provide accurate and up-to-date responses, particularly in dynamic or rapidly evolving contexts. Though integrating Multimodal Retrieval-augmented Generation (Multimodal RAG) offers a promising solution, the system would inevitably encounter the multi-granularity noisy correspondence (MNC) problem, which hinders accurate retrieval and generation. In this work, we propose RagVL, a novel framework with knowledge-enhanced reranking and noise-injected training, to address these limitations. We instruction-tune the MLLM with a simple yet effective instruction template to induce its ranking ability and serve it as a reranker to precisely filter the top-k retrieved images. For generation, we inject visual noise during training at the data and token levels to enhance the generator's robustness. Extensive experiments on the subsets of two datasets that require retrieving and reasoning over images to answer a given query verify the effectiveness of our method. Code and models are available at https://github.com/IDEA-FinAI/RagVL.
Authors: Tom Z. Jiahao, Ryan Adolf, Cynthia Sung, M. Ani Hsieh
Abstract: Soft robots have many advantages over rigid robots thanks to their compliant and passive nature. However, it is generally challenging to model the dynamics of soft robots due to their high spatial dimensionality, making it difficult to use model-based methods to accurately control soft robots. It often requires direct numerical simulation of partial differential equations to simulate soft robots. This not only requires an accurate numerical model, but also makes soft robot modeling slow and expensive. Deep learning algorithms have shown promises in data-driven modeling of soft robots. However, these algorithms usually require a large amount of data, which are difficult to obtain in either simulation or real-world experiments of soft robots. In this work, we propose KNODE-Cosserat, a framework that combines first-principle physics models and neural ordinary differential equations. We leverage the best from both worlds -- the generalization ability of physics-based models and the fast speed of deep learning methods. We validate our framework in both simulation and real-world experiments. In both cases, we show that the robot model significantly improves over the baseline models under different metrics.
Authors: Joseph Cho, Samuel Schmidgall, Cyril Zakka, Mrudang Mathur, Dhamanpreet Kaur, Rohan Shad, William Hiesinger
Abstract: Diffusion-based video generation models have made significant strides, producing outputs with improved visual fidelity, temporal coherence, and user control. These advancements hold great promise for improving surgical education by enabling more realistic, diverse, and interactive simulation environments. In this study, we introduce SurGen, a text-guided diffusion model tailored for surgical video synthesis. SurGen produces videos with the highest resolution and longest duration among existing surgical video generation models. We validate the visual and temporal quality of the outputs using standard image and video generation metrics. Additionally, we assess their alignment to the corresponding text prompts through a deep learning classifier trained on surgical data. Our results demonstrate the potential of diffusion models to serve as valuable educational tools for surgical trainees.
Authors: Ziyang Yu, Wenbing Huang, Yang Liu
Abstract: Molecular Dynamics (MD) is crucial in various fields such as materials science, chemistry, and pharmacology to name a few. Conventional MD software struggles with the balance between time cost and prediction accuracy, which restricts its wider application. Recently, data-driven approaches based on deep generative models have been devised for time-coarsened dynamics, which aim at learning dynamics of diverse molecular systems over a long timestep, enjoying both universality and efficiency. Nevertheless, most current methods are designed solely to learn from the data distribution regardless of the underlying Boltzmann distribution, and the physics priors such as energies and forces are constantly overlooked. In this work, we propose a conditional generative model called Force-guided Bridge Matching (FBM), which learns full-atom time-coarsened dynamics and targets the Boltzmann-constrained distribution. With the guidance of our delicately-designed intermediate force field, FBM leverages favourable physics priors into the generation process, giving rise to enhanced simulations. Experiments on two datasets consisting of peptides verify our superiority in terms of comprehensive metrics and demonstrate transferability to unseen systems.
Authors: Anton Andreychuk, Konstantin Yakovlev, Aleksandr Panov, Alexey Skrynnik
Abstract: Multi-agent pathfinding (MAPF) is a challenging computational problem that typically requires to find collision-free paths for multiple agents in a shared environment. Solving MAPF optimally is NP-hard, yet efficient solutions are critical for numerous applications, including automated warehouses and transportation systems. Recently, learning-based approaches to MAPF have gained attention, particularly those leveraging deep reinforcement learning. Following current trends in machine learning, we have created a foundation model for the MAPF problems called MAPF-GPT. Using imitation learning, we have trained a policy on a set of pre-collected sub-optimal expert trajectories that can generate actions in conditions of partial observability without additional heuristics, reward functions, or communication with other agents. The resulting MAPF-GPT model demonstrates zero-shot learning abilities when solving the MAPF problem instances that were not present in the training dataset. We show that MAPF-GPT notably outperforms the current best-performing learnable-MAPF solvers on a diverse range of problem instances and is efficient in terms of computation (in the inference mode).
Authors: Fatma Yasmine Loumachi, Mohamed Chahine Ghanem
Abstract: Timeline Analysis (TA) plays a crucial role in Timeline Forensics (TF) within the field of Digital Forensics (DF). It focuses on examining and analyzing time-based digital artefacts, such as timestamps derived from event logs, file metadata, and other relevant data, to correlate events linked to cyber incidents and reconstruct their chronological sequence. Traditional tools often struggle to efficiently handle the large volume and variety of data generated during DF investigations and Incident Response (IR) processes. This paper introduces a novel framework, GenDFIR, which combines Rule-Based Artificial Intelligence (R-BAI) algorithms with Large Language Models (LLMs) to enhance and automate the TA process. The proposed approach consists of two key stages: (1) R-BAI is used to identify and select anomalous digital artefacts based on predefined rules. (2) The selected artefacts are then transformed into embeddings for processing by an LLM with the assistance of a Retrieval-Augmented Generation (RAG) agent. The LLM uses its capabilities to perform automated TA on the artefacts and predict potential incident outcomes. To validate the framework, we evaluated its performance, efficiency, and reliability. Several metrics were applied to simulated cyber incident scenarios, which were presented as forensic case documents. Our findings demonstrate the significant potential of integrating R-BAI and LLMs for TA. This innovative approach underscores the power of Generative AI (GenAI), particularly LLMs, and opens up new possibilities for advanced threat detection and incident reconstruction, marking a significant advancement in the field.
Authors: Peng Zhu, Yuante Li, Yifan Hu, Qinyuan Liu, Dawei Cheng, Yuqi Liang
Abstract: Stock price prediction is a challenging problem in the field of finance and receives widespread attention. In recent years, with the rapid development of technologies such as deep learning and graph neural networks, more research methods have begun to focus on exploring the interrelationships between stocks. However, existing methods mostly focus on the short-term dynamic relationships of stocks and directly integrating relationship information with temporal information. They often overlook the complex nonlinear dynamic characteristics and potential higher-order interaction relationships among stocks in the stock market. Therefore, we propose a stock price trend prediction model named LSR-IGRU in this paper, which is based on long short-term stock relationships and an improved GRU input. Firstly, we construct a long short-term relationship matrix between stocks, where secondary industry information is employed for the first time to capture long-term relationships of stocks, and overnight price information is utilized to establish short-term relationships. Next, we improve the inputs of the GRU model at each step, enabling the model to more effectively integrate temporal information and long short-term relationship information, thereby significantly improving the accuracy of predicting stock trend changes. Finally, through extensive experiments on multiple datasets from stock markets in China and the United States, we validate the superiority of the proposed LSR-IGRU model over the current state-of-the-art baseline models. We also apply the proposed model to the algorithmic trading system of a financial company, achieving significantly higher cumulative portfolio returns compared to other baseline methods. Our sources are released at https://github.com/ZP1481616577/Baselines_LSR-IGRU.
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: Chi Chiu So, Siu Pang Yung
Abstract: Finding solutions to partial differential equations (PDEs) is an important and essential component in many scientific and engineering discoveries. One of the common approaches empowered by deep learning is Physics-informed Neural Networks (PINNs). Recently, a new type of fundamental neural network model, Kolmogorov-Arnold Networks (KANs), has been proposed as a substitute of Multilayer Perceptions (MLPs), and possesses trainable activation functions. To enhance KANs in fitting accuracy, a modification of KANs, so called ReLU-KANs, using "square of ReLU" as the basis of its activation functions, has been suggested. In this work, we propose another basis of activation functions, namely, Higherorder-ReLU (HR), which is simpler than the basis of activation functions used in KANs, namely, Bsplines; allows efficient KAN matrix operations; and possesses smooth and non-zero higher-order derivatives, essential to physicsinformed neural networks. We name such KANs with Higher-order-ReLU (HR) as their activations, HRKANs. Our detailed experiments on two famous and representative PDEs, namely, the linear Poisson equation and nonlinear Burgers' equation with viscosity, reveal that our proposed Higher-order-ReLU-KANs (HRKANs) achieve the highest fitting accuracy and training robustness and lowest training time significantly among KANs, ReLU-KANs and HRKANs. The codes to replicate our experiments are available at https://github.com/kelvinhkcs/HRKAN.
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: Yannis Bendi-Ouis, Dan Dutarte, Xavier Hinaut
Abstract: Since the release of ChatGPT in November 2022, large language models (LLMs) have seen considerable success, including in the open-source community, with many open-weight models available. However, the requirements to deploy such a service are often unknown and difficult to evaluate in advance. To facilitate this process, we conducted numerous tests at the Centre Inria de l'Universit\'e de Bordeaux. In this article, we propose a comparison of the performance of several models of different sizes (mainly Mistral and LLaMa) depending on the available GPUs, using vLLM, a Python library designed to optimize the inference of these models. Our results provide valuable information for private and public groups wishing to deploy LLMs, allowing them to evaluate the performance of different models based on their available hardware. This study thus contributes to facilitating the adoption and use of these large language models in various application domains.
Authors: Peter M\"uhlbacher, Nikos I. Bosse, Lawrence Phillips
Abstract: We present initial results of a forthcoming benchmark for evaluating LLM agents on white-collar tasks of economic value. We evaluate agents on real-world "messy" open-web research tasks of the type that are routine in finance and consulting. In doing so, we lay the groundwork for an LLM agent evaluation suite where good performance directly corresponds to a large economic and societal impact. We built and tested several agent architectures with o1-preview, GPT-4o, Claude-3.5 Sonnet, Llama 3.1 (405b), and GPT-4o-mini. On average, LLM agents powered by Claude-3.5 Sonnet and o1-preview substantially outperformed agents using GPT-4o, with agents based on Llama 3.1 (405b) and GPT-4o-mini lagging noticeably behind. Across LLMs, a ReAct architecture with the ability to delegate subtasks to subagents performed best. In addition to quantitative evaluations, we qualitatively assessed the performance of the LLM agents by inspecting their traces and reflecting on their observations. Our evaluation represents the first in-depth assessment of agents' abilities to conduct challenging, economically valuable analyst-style research on the real open web.
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 (M$^2$PT) approach for efficient instruction tuning of MLLMs. M$^2$PT 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: 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: 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.