Authors: Dino Ienco (EVERGREEN, UMR TETIS, INRAE), Cassio Fraga Dantas (UMR TETIS, INRAE, EVERGREEN)
Abstract: Cross-modal knowledge distillation (CMKD) refers to the scenario in which a learning framework must handle training and test data that exhibit a modality mismatch, more precisely, training and test data do not cover the same set of data modalities. Traditional approaches for CMKD are based on a teacher/student paradigm where a teacher is trained on multi-modal data with the aim to successively distill knowledge from a multi-modal teacher to a single-modal student. Despite the widespread adoption of such paradigm, recent research has highlighted its inherent limitations in the context of cross-modal knowledge transfer.Taking a step beyond the teacher/student paradigm, here we introduce a new framework for cross-modal knowledge distillation, named DisCoM-KD (Disentanglement-learning based Cross-Modal Knowledge Distillation), that explicitly models different types of per-modality information with the aim to transfer knowledge from multi-modal data to a single-modal classifier. To this end, DisCoM-KD effectively combines disentanglement representation learning with adversarial domain adaptation to simultaneously extract, foreach modality, domain-invariant, domain-informative and domain-irrelevant features according to a specific downstream task. Unlike the traditional teacher/student paradigm, our framework simultaneously learns all single-modal classifiers, eliminating the need to learn each student model separately as well as the teacher classifier. We evaluated DisCoM-KD on three standard multi-modal benchmarks and compared its behaviourwith recent SOTA knowledge distillation frameworks. The findings clearly demonstrate the effectiveness of DisCoM-KD over competitors considering mismatch scenarios involving both overlapping and non-overlapping modalities. These results offer insights to reconsider the traditional paradigm for distilling information from multi-modal data to single-modal neural networks.
Authors: Kyudan Jung, Sieun Hyeon, Kwon Jeong Youn, Nam-Joon Kim, Hyun Gon Ryu, Hyuk-Jae Lee, Jaeyoung Do
Abstract: Understanding sentences that contain mathematical expressions in text form poses significant challenges. To address this, the importance of converting these expressions into formula images has been highlighted. For instance, the expression ``x equals minus b plus or minus the square root of b squared minus four a c, all over two a'' is more readily comprehensible when displayed as an image $x = \frac{-b \pm \sqrt{b^2 - 4ac}}{2a}$. To develop a text-to-image conversion system, we can break down the process into text-to-LaTeX and LaTeX-to-image conversions, with the latter being managed with by existing various LaTeX engines. However, the former approach has been notably hindered by the severe scarcity of text-to-LaTeX paired data, presenting a significant challenge in the field.In this context, we introduce MathBridge, the first extensive dataset for translating mathematical spoken English into LaTeX, which aims to establish a robust baseline for future research in text-to-LaTeX translation. MathBridge comprises approximately 23 million LaTeX formulas paired with corresponding spoken English expressions. Through comprehensive evaluations, including fine-tuning and testing with data, we discovered that MathBridge significantly enhances pre-trained language models' capabilities for text-to-LaTeX translation. Specifically, for the T5-large model, the sacreBLEU score increased from 4.77 to 46.8, demonstrating substantial enhancement. Our findings indicate the necessity for a new metric specifically for text-to-LaTeX conversion evaluation.
Authors: Jinzhao Zhou, Justin Sia, Yiqun Duan, Yu-Cheng Chang, Yu-Kai Wang, Chin-Teng Lin
Abstract: Driving under drowsy conditions significantly escalates the risk of vehicular accidents. Although recent efforts have focused on using electroencephalography to detect drowsiness, helping prevent accidents caused by driving in such states, seamless human-machine interaction in driving scenarios requires a more versatile EEG-based system. This system should be capable of understanding a driver's intention while demonstrating resilience to artifacts induced by sudden movements. This paper pioneers a novel research direction in BCI-assisted driving, studying the neural patterns related to driving intentions and presenting a novel method for driving intention prediction. In particular, our preliminary analysis of the EEG signal using independent component analysis suggests a close relation between the intention of driving maneuvers and the neural activities in central-frontal and parietal areas. Power spectral density analysis at a group level also reveals a notable distinction among various driving intentions in the frequency domain. To exploit these brain dynamics, we propose a novel Masked EEG Modeling framework for predicting human driving intentions, including the intention for left turning, right turning, and straight proceeding. Extensive experiments, encompassing comprehensive quantitative and qualitative assessments on public dataset, demonstrate the proposed method is proficient in predicting driving intentions across various vigilance states. Specifically, our model attains an accuracy of 85.19% when predicting driving intentions for drowsy subjects, which shows its promising potential for mitigating traffic accidents related to drowsy driving. Notably, our method maintains over 75% accuracy when more than half of the channels are missing or corrupted, underscoring its adaptability in real-life driving.
Authors: Wangying Yang, Zhizhong Wu, Zitao Zheng, Bo Zhang, Shi Bo, Yuanfang Yang
Abstract: This study introduces a pioneering Dynamic Hypergraph Networks (DHCE) model designed to predict future medical diagnoses from electronic health records with enhanced accuracy. The DHCE model innovates by identifying and differentiating acute and chronic diseases within a patient's visit history, constructing dynamic hypergraphs that capture the complex, high-order interactions between diseases. It surpasses traditional recurrent neural networks and graph neural networks by effectively integrating clinical event data, reflected through medical language model-assisted encoding, into a robust patient representation. Through extensive experiments on two benchmark datasets, MIMIC-III and MIMIC-IV, the DHCE model exhibits superior performance, significantly outpacing established baseline models in the precision of sequential diagnosis prediction.
Authors: Fanghui Bi
Abstract: Dynamic Quality-of-Service (QoS) data capturing temporal variations in user-service interactions, are essential source for service selection and user behavior understanding. Approaches based on Latent Feature Analysis (LFA) have shown to be beneficial for discovering effective temporal patterns in QoS data. However, existing methods cannot well model the spatiality and temporality implied in dynamic interactions in a unified form, causing abundant accuracy loss for missing QoS estimation. To address the problem, this paper presents a novel Graph Convolutional Networks (GCNs)-based dynamic QoS estimator namely Spatiotemporal Coupling GCN (SCG) model with the three-fold ideas as below. First, SCG builds its dynamic graph convolution rules by incorporating generalized tensor product framework, for unified modeling of spatial and temporal patterns. Second, SCG combines the heterogeneous GCN layer with tensor factorization, for effective representation learning on bipartite user-service graphs. Third, it further simplifies the dynamic GCN structure to lower the training difficulties. Extensive experiments have been conducted on two large-scale widely-adopted QoS datasets describing throughput and response time. The results demonstrate that SCG realizes higher QoS estimation accuracy compared with the state-of-the-arts, illustrating it can learn powerful representations to users and cloud services.
Authors: Tianyu Liu, Qitan Lv, Jie Wang, Shuling Yang, Hanzhu Chen
Abstract: Inductive relation prediction (IRP) -- where entities can be different during training and inference -- has shown great power for completing evolving knowledge graphs. Existing works mainly focus on using graph neural networks (GNNs) to learn the representation of the subgraph induced from the target link, which can be seen as an implicit rule-mining process to measure the plausibility of the target link. However, these methods cannot differentiate the target link and other links during message passing, hence the final subgraph representation will contain irrelevant rule information to the target link, which reduces the reasoning performance and severely hinders the applications for real-world scenarios. To tackle this problem, we propose a novel \textit{single-source edge-wise} GNN model to learn the \textbf{R}ule-induc\textbf{E}d \textbf{S}ubgraph represen\textbf{T}ations (\textbf{REST}), which encodes relevant rules and eliminates irrelevant rules within the subgraph. Specifically, we propose a \textit{single-source} initialization approach to initialize edge features only for the target link, which guarantees the relevance of mined rules and target link. Then we propose several RNN-based functions for \textit{edge-wise} message passing to model the sequential property of mined rules. REST is a simple and effective approach with theoretical support to learn the \textit{rule-induced subgraph representation}. Moreover, REST does not need node labeling, which significantly accelerates the subgraph preprocessing time by up to \textbf{11.66$\times$}. Experiments on inductive relation prediction benchmarks demonstrate the effectiveness of our REST. Our code is available at https://github.com/smart-lty/REST.
Authors: Bo-Wen Zhang, Yan Yan, Lin Li, Guang Liu
Abstract: Recent advancements in Chain-of-Thoughts (CoT) and Program-of-Thoughts (PoT) methods have greatly enhanced language models' mathematical reasoning capabilities, facilitating their integration into instruction tuning datasets with LLMs. However, existing methods for large-scale dataset creation require substantial seed data and high computational costs for data synthesis, posing significant challenges for scalability. We introduce InfinityMATH, a scalable instruction tuning dataset for programmatic mathematical reasoning. The construction pipeline emphasizes decoupling numbers from mathematical problems to synthesize number-independent programs, enabling efficient and flexible scaling while minimizing dependency on specific numerical values. Fine-tuning experiments with open-source language and code models, such as Llama2 and CodeLlama, demonstrate the practical benefits of InfinityMATH. These fine-tuned models, showed significant relative improvements on both in-domain and out-of-domain benchmarks, ranging from 184.7% to 514.3% on average. Additionally, these models exhibited high robustness on the GSM8K+ and MATH+ benchmarks, which are enhanced version of test sets with simply the number variations. InfinityMATH ensures that models are more versatile and effective across a broader range of mathematical problems. The data is available at https://huggingface.co/datasets/flagopen/InfinityMATH.
URLs: https://huggingface.co/datasets/flagopen/InfinityMATH.
Authors: Cinzia Bandiziol, Stefano De Marchi
Abstract: The aim of the present work is a comparative study of different persistence kernels applied to various classification problems. After some necessary preliminaries on homology and persistence diagrams, we introduce five different kernels that are then used to compare their performances of classification on various datasets. We also provide the Python codes for the reproducibility of results.
Authors: Wenbin Hu, Huihao Jing, Qi Hu, Haoran Li, Yangqiu Song
Abstract: Textual graphs are ubiquitous in real-world applications, featuring rich text information with complex relationships, which enables advanced research across various fields. Textual graph representation learning aims to generate low-dimensional feature embeddings from textual graphs that can improve the performance of downstream tasks. A high-quality feature embedding should effectively capture both the structural and the textual information in a textual graph. However, most textual graph dataset benchmarks rely on word2vec techniques to generate feature embeddings, which inherently limits their capabilities. Recent works on textual graph representation learning can be categorized into two folds: supervised and unsupervised methods. Supervised methods finetune a language model on labeled nodes, which have limited capabilities when labeled data is scarce. Unsupervised methods, on the other hand, extract feature embeddings by developing complex training pipelines. To address these limitations, we propose a novel unified unsupervised learning autoencoder framework, named Node Level Graph AutoEncoder (NodeGAE). We employ language models as the backbone of the autoencoder, with pretraining on text reconstruction. Additionally, we add an auxiliary loss term to make the feature embeddings aware of the local graph structure. Our method maintains simplicity in the training process and demonstrates generalizability across diverse textual graphs and downstream tasks. We evaluate our method on two core graph representation learning downstream tasks: node classification and link prediction. Comprehensive experiments demonstrate that our approach substantially enhances the performance of diverse graph neural networks (GNNs) across multiple textual graph datasets.
Authors: Shuo Yang, Ying Sheng, Joseph E. Gonzalez, Ion Stoica, Lianmin Zheng
Abstract: The inference process for large language models is slow and memory-intensive, with one of the most critical bottlenecks being excessive Key-Value (KV) cache accesses. This paper introduces "Double Sparsity," a novel post-training sparse attention technique designed to alleviate this bottleneck by reducing KV cache access. Double Sparsity combines token sparsity, which focuses on utilizing only the important tokens for computing self-attention, with channel sparsity, an approach that uses important feature channels for identifying important tokens. Our key insight is that the pattern of channel sparsity is relatively static, allowing us to use offline calibration to make it efficient at runtime, thereby enabling accurate and efficient identification of important tokens. Moreover, this method can be combined with offloading to achieve significant memory usage reduction. Experimental results demonstrate that Double Sparsity can achieve \(\frac{1}{16}\) token and channel sparsity with minimal impact on accuracy across various tasks, including wiki-2 perplexity, key-value retrieval, and long context benchmarks with models including Llama-2-7B, Llama-2-70B, and Mixtral-8x7B. It brings up to a 14.1$\times$ acceleration in attention operations and a 1.9$\times$ improvement in end-to-end inference on GPUs. With offloading, it achieves a decoding speed acceleration of 16.3$\times$ compared to state-of-the-art solutions at a sequence length of 256K. Our code is publicly available at \url{https://github.com/andy-yang-1/DoubleSparse}.
Authors: Kailai Sun, Tianxiang Lan, Yang Miang Goh, Yueng-Hsiang Huang
Abstract: There is growing interest in using safety analytics and machine learning to support the prevention of workplace incidents, especially in high-risk industries like construction and trucking. Although existing safety analytics studies have made remarkable progress, they suffer from imbalanced datasets, a common problem in safety analytics, resulting in prediction inaccuracies. This can lead to management problems, e.g., incorrect resource allocation and improper interventions. To overcome the imbalanced data problem, we extend the theory of accident triangle to claim that the importance of data samples should be based on characteristics such as injury severity, accident frequency, and accident type. Thus, three oversampling methods are proposed based on assigning different weights to samples in the minority class. We find robust improvements among different machine learning algorithms. For the lack of open-source safety datasets, we are sharing three imbalanced datasets, e.g., a 9-year nationwide construction accident record dataset, and their corresponding codes.
Authors: Sayed W Qayyumi, Laureance F Park, Oliver Obst
Abstract: Training a classifier with high mean accuracy from a manifold-distributed dataset can be challenging. This problem is compounded further when there are only few labels available for training. For transfer learning to work, both the source and target datasets must have a similar manifold structure. As part of this study, we present a novel method for determining the similarity between two manifold structures. This method can be used to determine whether the target and source datasets have a similar manifold structure suitable for transfer learning. We then present a few-shot learning method to classify manifold-distributed datasets with limited labels using transfer learning. Based on the base and target datasets, a similarity comparison is made to determine if the two datasets are suitable for transfer learning. A manifold structure and label distribution are learned from the base and target datasets. When the structures are similar, the manifold structure and its relevant label information from the richly labeled source dataset is transferred to target dataset. We use the transferred information, together with the labels and unlabeled data from the target dataset, to develop a few-shot classifier that produces high mean classification accuracy on manifold-distributed datasets. In the final part of this article, we discuss the application of our manifold structure similarity measure to reinforcement learning and image recognition.
Authors: Martin K\"appel, Lars Ackermann, Stefan Jablonski, Simon H\"artl
Abstract: Predictive process monitoring aims to support the execution of a process during runtime with various predictions about the further evolution of a process instance. In the last years a plethora of deep learning architectures have been established as state-of-the-art for different prediction targets, among others the transformer architecture. The transformer architecture is equipped with a powerful attention mechanism, assigning attention scores to each input part that allows to prioritize most relevant information leading to more accurate and contextual output. However, deep learning models largely represent a black box, i.e., their reasoning or decision-making process cannot be understood in detail. This paper examines whether the attention scores of a transformer based next-activity prediction model can serve as an explanation for its decision-making. We find that attention scores in next-activity prediction models can serve as explainers and exploit this fact in two proposed graph-based explanation approaches. The gained insights could inspire future work on the improvement of predictive business process models as well as enabling a neural network based mining of process models from event logs.
Authors: Jiaying Chen, Xusheng Du, Yurong Qian, Gwanggil Jeon
Abstract: Bearing fault diagnosis technology has a wide range of practical applications in industrial production, energy and other fields. Timely and accurate detection of bearing faults plays an important role in preventing catastrophic accidents and ensuring product quality. Traditional signal analysis techniques and deep learning-based fault detection algorithms do not take into account the intricate correlation between signals, making it difficult to further improve detection accuracy. To address this problem, we introduced Graph Sampling and Aggregation (GraphSAGE) network and proposed GraphSAGE-based Bearing fault Diagnosis (GSABFD) algorithm. The original vibration signal is firstly sliced through a fixed size non-overlapping sliding window, and the sliced data is feature transformed using signal analysis methods; then correlations are constructed for the transformed vibration signal and further transformed into vertices in the graph; then the GraphSAGE network is used for training; finally the fault level of the object is calculated in the output layer of the network. The proposed algorithm is compared with five advanced algorithms in a real-world public dataset for experiments, and the results show that the GSABFD algorithm improves the AUC value by 5% compared with the next best algorithm.
Authors: Wenchao Weng, Mei Wu, Hanyu Jiang, Wanzeng Kong, Xiangjie Kong, Feng Xia
Abstract: In recent years, deep learning has increasingly gained attention in the field of traffic prediction. Existing traffic prediction models often rely on GCNs or attention mechanisms with O(N^2) complexity to dynamically extract traffic node features, which lack efficiency and are not lightweight. Additionally, these models typically only utilize historical data for prediction, without considering the impact of the target information on the prediction. To address these issues, we propose a Pattern-Matching Dynamic Memory Network (PM-DMNet). PM-DMNet employs a novel dynamic memory network to capture traffic pattern features with only O(N) complexity, significantly reducing computational overhead while achieving excellent performance. The PM-DMNet also introduces two prediction methods: Recursive Multi-step Prediction (RMP) and Parallel Multi-step Prediction (PMP), which leverage the time features of the prediction targets to assist in the forecasting process. Furthermore, a transfer attention mechanism is integrated into PMP, transforming historical data features to better align with the predicted target states, thereby capturing trend changes more accurately and reducing errors. Extensive experiments demonstrate the superiority of the proposed model over existing benchmarks. The source codes are available at: https://github.com/wengwenchao123/PM-DMNet.
Authors: Ali Mohammad-Djafari, Ning Chu, Li Wang, Caifang Cai, Liang Yu
Abstract: Neural Networks (NN) has been used in many areas with great success. When a NN's structure (Model) is given, during the training steps, the parameters of the model are determined using an appropriate criterion and an optimization algorithm (Training). Then, the trained model can be used for the prediction or inference step (Testing). As there are also many hyperparameters, related to the optimization criteria and optimization algorithms, a validation step is necessary before its final use. One of the great difficulties is the choice of the NN's structure. Even if there are many "on the shelf" networks, selecting or proposing a new appropriate network for a given data, signal or image processing, is still an open problem. In this work, we consider this problem using model based signal and image processing and inverse problems methods. We classify the methods in five classes, based on: i) Explicit analytical solutions, ii) Transform domain decomposition, iii) Operator Decomposition, iv) Optimization algorithms unfolding, and v) Physics Informed NN methods (PINN). Few examples in each category are explained.
Authors: Wenxuan Yang, Weimin Tan, Hanyu Zhang, Bo Yan
Abstract: Pre-training foundation models on large-scale datasets demonstrates exceptional performance. However, recent research questions this traditional notion, exploring whether an increase in pre-training data always leads to enhanced model performance. To address this issue, data-effective learning approaches have been introduced. However, current methods in this area lack a clear standard for sample selection. Our experiments reveal that by maximizing V-information, sample selection can be framed as an optimization problem, enabling effective improvement in model performance even with fewer samples. Under this guidance, we develop an optimal data-effective learning method (OptiDEL) to maximize V-information. The OptiDEL method generates hard samples to achieve or even exceed the performance of models trained on the full dataset while using substantially less data. We compare the OptiDEL method with state-of-the-art approaches finding that OptiDEL consistently outperforms existing approaches across different datasets, with foundation models trained on only 5% of the pre-training data surpassing the performance of those trained on the full dataset.
Authors: Giovanni Piunno, Ioannis Stefanou, Cristina Jommi
Abstract: This paper introduces a novel approach that combines Proper Orthogonal Decomposition (POD) with Thermodynamics-based Artificial Neural Networks (TANN) to capture the macroscopic behavior of complex inelastic systems and derive macroelements in geomechanics. The methodology leverages POD to extract macroscopic Internal State Variables (ISVs) from microscopic state information, thereby enriching the macroscopic state description used to train an energy potential network within the TANN framework. The thermodynamic consistency provided by TANN, combined with the hierarchical nature of POD, allows for accurate modeling of complex, non-linear material behavior and reliable macroscopic geomechanical systems responses. The effectiveness of this approach is validated through applications of increasing complexity, demonstrating its capability to handle various material behaviors and microstructural topologies. These applications include the homogenization of continuous inelastic representative unit cells (RUCs) and the derivation of a macroelement for a geotechnical system involving a monopile in a clay layer subjected to horizontal loading. The results indicate that the proposed POD-TANN methodology not only achieves high accuracy in reproducing stress-strain responses, but also significantly reduces computational costs, making it a practical tool for the multiscale modeling of heterogeneous inelastic systems, and the efficient derivation of macroelements for complex geomechanical problems.
Authors: Jonas Linkerh\"agner, Cheng Shi, Ivan Dokmani\'c
Abstract: Graph neural networks (GNNs) take as input the graph structure and the feature vectors associated with the nodes. Both contain noisy information about the labels. Here we propose joint denoising and rewiring (JDR)--an algorithm to jointly denoise the graph structure and features, which can improve the performance of any downstream algorithm. We do this by defining and maximizing the alignment between the leading eigenspaces of graph and feature matrices. To approximately solve this computationally hard problem, we propose a heuristic that efficiently handles real-world graph datasets with many classes and different levels of homophily or heterophily. We experimentally verify the effectiveness of our approach on synthetic data and real-world graph datasets. The results show that JDR consistently outperforms existing rewiring methods on node classification tasks using GNNs as downstream models.
Authors: Manav Vora, Michael N Grussing, Melkior Ornik
Abstract: Monotonic Partially Observable Markov Decision Processes (POMDPs), where the system state progressively decreases until a restorative action is performed, can be used to model sequential repair problems effectively. This paper considers the problem of solving budget-constrained multi-component monotonic POMDPs, where a finite budget limits the maximal number of restorative actions. For a large number of components, solving such a POMDP using current methods is computationally intractable due to the exponential growth in the state space with an increasing number of components. To address this challenge, we propose a two-step approach. Since the individual components of a budget-constrained multi-component monotonic POMDP are only connected via the shared budget, we first approximate the optimal budget allocation among these components using an approximation of each component POMDP's optimal value function which is obtained through a random forest model. Subsequently, we introduce an oracle-guided meta-trained Proximal Policy Optimization (PPO) algorithm to solve each of the independent budget-constrained single-component monotonic POMDPs. The oracle policy is obtained by performing value iteration on the corresponding monotonic Markov Decision Process (MDP). This two-step method provides scalability in solving truly massive multi-component monotonic POMDPs. To demonstrate the efficacy of our approach, we consider a real-world maintenance scenario that involves inspection and repair of an administrative building by a team of agents within a maintenance budget. Finally, we perform a computational complexity analysis for a varying number of components to show the scalability of the proposed approach.
Authors: Mario De Florio, Zongren Zou, Daniele E. Schiavazzi, George Em Karniadakis
Abstract: When predicting physical phenomena through simulation, quantification of the total uncertainty due to multiple sources is as crucial as making sure the underlying numerical model is accurate. Possible sources include irreducible aleatoric uncertainty due to noise in the data, epistemic uncertainty induced by insufficient data or inadequate parameterization, and model-form uncertainty related to the use of misspecified model equations. Physics-based regularization interacts in nontrivial ways with aleatoric, epistemic and model-form uncertainty and their combination, and a better understanding of this interaction is needed to improve the predictive performance of physics-informed digital twins that operate under real conditions. With a specific focus on biological and physiological models, this study investigates the decomposition of total uncertainty in the estimation of states and parameters of a differential system simulated with MC X-TFC, a new physics-informed approach for uncertainty quantification based on random projections and Monte-Carlo sampling. MC X-TFC is applied to a six-compartment stiff ODE system, the CVSim-6 model, developed in the context of human physiology. The system is analyzed by progressively removing data while estimating an increasing number of parameters and by investigating total uncertainty under model-form misspecification of non-linear resistance in the pulmonary compartment. In particular, we focus on the interaction between the formulation of the discrepancy term and quantification of model-form uncertainty, and show how additional physics can help in the estimation process. The method demonstrates robustness and efficiency in estimating unknown states and parameters, even with limited, sparse, and noisy data. It also offers great flexibility in integrating data with physics for improved estimation, even in cases of model misspecification.
Authors: Nida Zamir, I-Hong Hou
Abstract: Scheduling in multi-channel wireless communication system presents formidable challenges in effectively allocating resources. To address these challenges, we investigate the multi-resource restless matching bandit (MR-RMB) model for heterogeneous resource systems with an objective of maximizing long-term discounted total rewards while respecting resource constraints. We have also generalized to applications beyond multi-channel wireless. We discuss the Max-Weight Index Matching algorithm, which optimizes resource allocation based on learned partial indexes. We have derived the policy gradient theorem for index learning. Our main contribution is the introduction of a new Deep Index Policy (DIP), an online learning algorithm tailored for MR-RMB. DIP learns the partial index by leveraging the policy gradient theorem for restless arms with convoluted and unknown transition kernels of heterogeneous resources. We demonstrate the utility of DIP by evaluating its performance for three different MR-RMB problems. Our simulation results show that DIP indeed learns the partial indexes efficiently.
Authors: Yang Xie, Ziqi Xu, Debo Cheng, Jiuyong Li, Lin Liu, Yinghao Zhang, Zaiwen Feng
Abstract: Estimating causal effects from observational data is challenging, especially in the presence of latent confounders. Much work has been done on addressing this challenge, but most of the existing research ignores the bias introduced by the post-treatment variables. In this paper, we propose a novel method of joint Variational AutoEncoder (VAE) and identifiable Variational AutoEncoder (iVAE) for learning the representations of latent confounders and latent post-treatment variables from their proxy variables, termed CPTiVAE, to achieve unbiased causal effect estimation from observational data. We further prove the identifiability in terms of the representation of latent post-treatment variables. Extensive experiments on synthetic and semi-synthetic datasets demonstrate that the CPTiVAE outperforms the state-of-the-art methods in the presence of latent confounders and post-treatment variables. We further apply CPTiVAE to a real-world dataset to show its potential application.
Authors: Lingwei Zhu, Haseeb Shah, Han Wang, Martha White
Abstract: Policy optimization methods benefit from a simple and tractable policy functional, usually the Gaussian for continuous action spaces. In this paper, we consider a broader policy family that remains tractable: the $q$-exponential family. This family of policies is flexible, allowing the specification of both heavy-tailed policies ($q>1$) and light-tailed policies ($q<1$). This paper examines the interplay between $q$-exponential policies for several actor-critic algorithms conducted on both online and offline problems. We find that heavy-tailed policies are more effective in general and can consistently improve on Gaussian. In particular, we find the Student's t-distribution to be more stable than the Gaussian across settings and that a heavy-tailed $q$-Gaussian for Tsallis Advantage Weighted Actor-Critic consistently performs well in offline benchmark problems. Our code is available at \url{https://github.com/lingweizhu/qexp}.
Authors: Junxian Li, Di Zhang, Xunzhi Wang, Zeying Hao, Jingdi Lei, Qian Tan, Cai Zhou, Wei Liu, Weiyun Wang, Zhe Chen, Wenhai Wang, Wei Li, Shufei Zhang, Mao Su, Wanli Ouyang, Yuqiang Li, Dongzhan Zhou
Abstract: In this technical report, we propose ChemVLM, the first open-source multimodal large language model dedicated to the fields of chemistry, designed to address the incompatibility between chemical image understanding and text analysis. Built upon the VIT-MLP-LLM architecture, we leverage ChemLLM-20B as the foundational large model, endowing our model with robust capabilities in understanding and utilizing chemical text knowledge. Additionally, we employ InternVIT-6B as a powerful image encoder. We have curated high-quality data from the chemical domain, including molecules, reaction formulas, and chemistry examination data, and compiled these into a bilingual multimodal question-answering dataset. We test the performance of our model on multiple open-source benchmarks and three custom evaluation sets. Experimental results demonstrate that our model achieves excellent performance, securing state-of-the-art results in five out of six involved tasks. Our model can be found at https://huggingface.co/AI4Chem/ChemVLM-26B.
Authors: Rohit Udaiwal, Nayan Baishya, Yash Gupta, B. R. Manoj
Abstract: This work proposes a novel and efficient quadstream BiLSTM-Attention network, abbreviated as QSLA network, for robust automatic modulation classification (AMC) of wireless signals. The proposed model exploits multiple representations of the wireless signal as inputs to the network and the feature extraction process combines convolutional and BiLSTM layers for processing the spatial and temporal features of the signal, respectively. An attention layer is used after the BiLSTM layer to emphasize the important temporal features. The experimental results on the recent and realistic RML22 dataset demonstrate the superior performance of the proposed model with an accuracy up to around 99%. The model is compared with other benchmark models in the literature in terms of classification accuracy, computational complexity, memory usage, and training time to show the effectiveness of our proposed approach.
Authors: Enhao Zhang, Chaohua Li, Chuanxing Geng, Songcan Chen
Abstract: Neural Collapse (NC) presents an elegant geometric structure that enables individual activations (features), class means and classifier (weights) vectors to reach \textit{optimal} inter-class separability during the terminal phase of training on a \textit{balanced} dataset. Once shifted to imbalanced classification, such an optimal structure of NC can be readily destroyed by the notorious \textit{minority collapse}, where the classifier vectors corresponding to the minority classes are squeezed. In response, existing works endeavor to recover NC typically by optimizing classifiers. However, we discover that this squeezing phenomenon is not only confined to classifier vectors but also occurs with class means. Consequently, reconstructing NC solely at the classifier aspect may be futile, as the feature means remain compressed, leading to the violation of inherent \textit{self-duality} in NC (\textit{i.e.}, class means and classifier vectors converge mutually) and incidentally, resulting in an unsatisfactory collapse of individual activations towards the corresponding class means. To shake off these dilemmas, we present a unified \textbf{All}-around \textbf{N}eural \textbf{C}ollapse framework (AllNC), aiming to comprehensively restore NC across multiple aspects including individual activations, class means and classifier vectors. We thoroughly analyze its effectiveness and verify on multiple benchmark datasets that it achieves state-of-the-art in both balanced and imbalanced settings.
Authors: Manhyung Han
Abstract: This note provides a critical review of the mathematical concepts underlying the generalized diffusion denoising implicit model (gDDIM) and the exponential integrator (EI) scheme. We present enhanced mathematical results, including an exact expression for the reverse trajectory in the probability flow ODE and an exact expression for the covariance matrix in the gDDIM scheme. Furthermore, we offer an improved understanding of the EI scheme's efficiency in terms of the change of variables. The noising process in DDIM is analyzed from the perspective of non-equilibrium statistical physics. Additionally, we propose a new scheme for DDIM, called the principal-axis DDIM (paDDIM).
Authors: Md Fahim Anjum
Abstract: Language models have achieved remarkable success in various natural language processing tasks. However, their application to time series data, a crucial component in many domains, remains limited. This paper proposes LiPCoT (Linear Predictive Coding based Tokenizer for time series), a novel tokenizer that encodes time series data into a sequence of tokens, enabling self-supervised learning of time series using existing Language model architectures such as BERT. Unlike traditional time series tokenizers that rely heavily on CNN encoder for time series feature generation, LiPCoT employs stochastic modeling through linear predictive coding to create a latent space for time series providing a compact yet rich representation of the inherent stochastic nature of the data. Furthermore, LiPCoT is computationally efficient and can effectively handle time series data with varying sampling rates and lengths, overcoming common limitations of existing time series tokenizers. In this proof-of-concept work, we present the effectiveness of LiPCoT in classifying Parkinson's disease (PD) using an EEG dataset from 46 participants. In particular, we utilize LiPCoT to encode EEG data into a small vocabulary of tokens and then use BERT for self-supervised learning and the downstream task of PD classification. We benchmark our approach against several state-of-the-art CNN-based deep learning architectures for PD detection. Our results reveal that BERT models utilizing self-supervised learning outperformed the best-performing existing method by 7.1% in precision, 2.3% in recall, 5.5% in accuracy, 4% in AUC, and 5% in F1-score highlighting the potential for self-supervised learning even on small datasets. Our work will inform future foundational models for time series, particularly for self-supervised learning.
Authors: Minxia Chen, Ke Fu, Teng Huang, Miao Bai
Abstract: Many important managerial decisions are made based on censored observations. Making decisions without adequately handling the censoring leads to inferior outcomes. We investigate the data-driven decision-making problem with an offline dataset containing the feature data and the censored historical data of the variable of interest without the censoring indicators. Without assuming the underlying distribution, we design and leverage {\epsilon}-insensitive operational costs to deal with the unobserved censoring in an offline data-driven fashion. We demonstrate the customization of the {\epsilon}-insensitive operational costs for a newsvendor problem and use such costs to train two representative ML models, including linear regression (LR) models and neural networks (NNs). We derive tight generalization bounds for the custom LR model without regularization (LR-{\epsilon}NVC) and with regularization (LR-{\epsilon}NVC-R), and a high-probability generalization bound for the custom NN (NN-{\epsilon}NVC) trained by stochastic gradient descent. The theoretical results reveal the stability and learnability of LR-{\epsilon}NVC, LR-{\epsilon}NVC-R and NN-{\epsilon}NVC. We conduct extensive numerical experiments to compare LR-{\epsilon}NVC-R and NN-{\epsilon}NVC with two existing approaches, estimate-as-solution (EAS) and integrated estimation and optimization (IEO). The results show that LR-{\epsilon}NVC-R and NN-{\epsilon}NVC outperform both EAS and IEO, with maximum cost savings up to 14.40% and 12.21% compared to the lowest cost generated by the two existing approaches. In addition, LR-{\epsilon}NVC-R's and NN-{\epsilon}NVC's order quantities are statistically significantly closer to the optimal solutions should the underlying distribution be known.
Authors: Yue Yu, Ning Liu, Fei Lu, Tian Gao, Siavash Jafarzadeh, Stewart Silling
Abstract: Despite the recent popularity of attention-based neural architectures in core AI fields like natural language processing (NLP) and computer vision (CV), their potential in modeling complex physical systems remains under-explored. Learning problems in physical systems are often characterized as discovering operators that map between function spaces based on a few instances of function pairs. This task frequently presents a severely ill-posed PDE inverse problem. In this work, we propose a novel neural operator architecture based on the attention mechanism, which we coin Nonlocal Attention Operator (NAO), and explore its capability towards developing a foundation physical model. In particular, we show that the attention mechanism is equivalent to a double integral operator that enables nonlocal interactions among spatial tokens, with a data-dependent kernel characterizing the inverse mapping from data to the hidden parameter field of the underlying operator. As such, the attention mechanism extracts global prior information from training data generated by multiple systems, and suggests the exploratory space in the form of a nonlinear kernel map. Consequently, NAO can address ill-posedness and rank deficiency in inverse PDE problems by encoding regularization and achieving generalizability. We empirically demonstrate the advantages of NAO over baseline neural models in terms of generalizability to unseen data resolutions and system states. Our work not only suggests a novel neural operator architecture for learning interpretable foundation models of physical systems, but also offers a new perspective towards understanding the attention mechanism.
Authors: Chang Dong, Liangwei Zheng, Weitong Chen
Abstract: Kolmogorov-Arnold Networks (KAN) has recently attracted significant attention as a promising alternative to traditional Multi-Layer Perceptrons (MLP). Despite their theoretical appeal, KAN require validation on large-scale benchmark datasets. Time series data, which has become increasingly prevalent in recent years, especially univariate time series are naturally suited for validating KAN. Therefore, we conducted a fair comparison among KAN, MLP, and mixed structures. The results indicate that KAN can achieve performance comparable to, or even slightly better than, MLP across 128 time series datasets. We also performed an ablation study on KAN, revealing that the output is primarily determined by the base component instead of b-spline function. Furthermore, we assessed the robustness of these models and found that KAN and the hybrid structure MLP\_KAN exhibit significant robustness advantages, attributed to their lower Lipschitz constants. This suggests that KAN and KAN layers hold strong potential to be robust models or to improve the adversarial robustness of other models.
Authors: Mark Benjamin, Gianluca Iaccarino
Abstract: A novel strategy for generating datasets is developed within the context of drag prediction for automotive geometries using neural networks. A primary challenge in this space is constructing a training databse of sufficient size and diversity. Our method relies on a small number of starting data points, and provides a recipe to interpolate systematically between them, generating an arbitrary number of samples at the desired quality. We test this strategy using a realistic automotive geometry, and demonstrate that convolutional neural networks perform exceedingly well at predicting drag coefficients and surface pressures. Promising results are obtained in testing extrapolation performance. Our method can be applied to other problems of aerodynamic shape optimization.
Authors: Taeyoung Yun, Kanghoon Lee, Sujin Yun, Ilmyung Kim, Won-Woo Jung, Min-Cheol Kwon, Kyujin Choi, Yoohyeon Lee, Jinkyoo Park
Abstract: Complex urban road networks with high vehicle occupancy frequently face severe traffic congestion. Designing an effective strategy for managing multiple traffic lights plays a crucial role in managing congestion. However, most current traffic light management systems rely on human-crafted decisions, which may not adapt well to diverse traffic patterns. In this paper, we delve into two pivotal design components of the traffic light management system that can be dynamically adjusted to various traffic conditions: phase combination and phase time allocation. While numerous studies have sought an efficient strategy for managing traffic lights, most of these approaches consider a fixed traffic pattern and are limited to relatively small road networks. To overcome these limitations, we introduce a novel and practical framework to formulate the optimization of such design components using an offline meta black-box optimization. We then present a simple yet effective method to efficiently find a solution for the aforementioned problem. In our framework, we first collect an offline meta dataset consisting of pairs of design choices and corresponding congestion measures from various traffic patterns. After collecting the dataset, we employ the Attentive Neural Process (ANP) to predict the impact of the proposed design on congestion across various traffic patterns with well-calibrated uncertainty. Finally, Bayesian optimization, with ANP as a surrogate model, is utilized to find an optimal design for unseen traffic patterns through limited online simulations. Our experiment results show that our method outperforms state-of-the-art baselines on complex road networks in terms of the number of waiting vehicles. Surprisingly, the deployment of our method into a real-world traffic system was able to improve traffic throughput by 4.80\% compared to the original strategy.
Authors: Junyu Chen, Long Shi, Badong Chen
Abstract: Graph Neural Networks (GNNs) have exhibited remarkable efficacy in learning from multi-view graph data. In the framework of multi-view graph neural networks, a critical challenge lies in effectively combining diverse views, where each view has distinct graph structure features (GSFs). Existing approaches to this challenge primarily focus on two aspects: 1) prioritizing the most important GSFs, 2) utilizing GNNs for feature aggregation. However, prioritizing the most important GSFs can lead to limited feature diversity, and existing GNN-based aggregation strategies equally treat each view without considering view quality. To address these issues, we propose a novel Multi-View Graph Neural Network with Reliable Structural Enhancement and Aggregation (RSEA-MVGNN). Firstly, we estimate view-specific uncertainty employing subjective logic. Based on this uncertainty, we design reliable structural enhancement by feature de-correlation algorithm. This approach enables each enhancement to focus on different GSFs, thereby achieving diverse feature representation in the enhanced structure. Secondly, the model learns view-specific beliefs and uncertainty as opinions, which are utilized to evaluate view quality. Based on these opinions, the model enables high-quality views to dominate GNN aggregation, thereby facilitating representation learning. Experimental results conducted on five real-world datasets demonstrate that RSEA-MVGNN outperforms several state-of-the-art GNN-based methods.
Authors: Jingyu Peng, Qi Liu, Linan Yue, Zaixi Zhang, Kai Zhang, Yunhao Sha
Abstract: Recent advancements in Graph Neural Networks (GNNs) have spurred an upsurge of research dedicated to enhancing the explainability of GNNs, particularly in critical domains such as medicine. A promising approach is the self-explaining method, which outputs explanations along with predictions. However, existing self-explaining models require a large amount of training data, rendering them unavailable in few-shot scenarios. To address this challenge, in this paper, we propose a Meta-learned Self-Explaining GNN (MSE-GNN), a novel framework that generates explanations to support predictions in few-shot settings. MSE-GNN adopts a two-stage self-explaining structure, consisting of an explainer and a predictor. Specifically, the explainer first imitates the attention mechanism of humans to select the explanation subgraph, whereby attention is naturally paid to regions containing important characteristics. Subsequently, the predictor mimics the decision-making process, which makes predictions based on the generated explanation. Moreover, with a novel meta-training process and a designed mechanism that exploits task information, MSE-GNN can achieve remarkable performance on new few-shot tasks. Extensive experimental results on four datasets demonstrate that MSE-GNN can achieve superior performance on prediction tasks while generating high-quality explanations compared with existing methods. The code is publicly available at https://github.com/jypeng28/MSE-GNN.
Authors: Ricky Maulana Fajri, Yulong Pei, Lu Yin, Mykola Pechenizkiy
Abstract: Despite significant advancements in active learning and adversarial attacks, the intersection of these two fields remains underexplored, particularly in developing robust active learning frameworks against dynamic adversarial threats. The challenge of developing robust active learning frameworks under dynamic adversarial attacks is critical, as these attacks can lead to catastrophic forgetting within the active learning cycle. This paper introduces Robust Active Learning (RoAL), a novel approach designed to address this issue by integrating Elastic Weight Consolidation (EWC) into the active learning process. Our contributions are threefold: First, we propose a new dynamic adversarial attack that poses significant threats to active learning frameworks. Second, we introduce a novel method that combines EWC with active learning to mitigate catastrophic forgetting caused by dynamic adversarial attacks. Finally, we conduct extensive experimental evaluations to demonstrate the efficacy of our approach. The results show that RoAL not only effectively counters dynamic adversarial threats but also significantly reduces the impact of catastrophic forgetting, thereby enhancing the robustness and performance of active learning systems in adversarial environments.
Authors: Milan Pape\v{z}, Martin Rektoris, Tom\'a\v{s} Pevn\'y, V\'aclav \v{S}m\'idl
Abstract: Daily internet communication relies heavily on tree-structured graphs, embodied by popular data formats such as XML and JSON. However, many recent generative (probabilistic) models utilize neural networks to learn a probability distribution over undirected cyclic graphs. This assumption of a generic graph structure brings various computational challenges, and, more importantly, the presence of non-linearities in neural networks does not permit tractable probabilistic inference. We address these problems by proposing sum-product-set networks, an extension of probabilistic circuits from unstructured tensor data to tree-structured graph data. To this end, we use random finite sets to reflect a variable number of nodes and edges in the graph and to allow for exact and efficient inference. We demonstrate that our tractable model performs comparably to various intractable models based on neural networks.
Authors: Tobias A. Opsahl, Vegard Antun
Abstract: Most datasets used for supervised machine learning consist of a single label per data point. However, in cases where more information than just the class label is available, would it be possible to train models more efficiently? We introduce two novel model architectures, which we call hybrid concept-based models, that train using both class labels and additional information in the dataset referred to as concepts. In order to thoroughly assess their performance, we introduce ConceptShapes, an open and flexible class of datasets with concept labels. We show that the hybrid concept-based models outperform standard computer vision models and previously proposed concept-based models with respect to accuracy, especially in sparse data settings. We also introduce an algorithm for performing adversarial concept attacks, where an image is perturbed in a way that does not change a concept-based model's concept predictions, but changes the class prediction. The existence of such adversarial examples raises questions about the interpretable qualities promised by concept-based models.
Authors: Yarin Bar, Shalev Shaer, Yaniv Romano
Abstract: We present a novel approach for test-time adaptation via online self-training, consisting of two components. First, we introduce a statistical framework that detects distribution shifts in the classifier's entropy values obtained on a stream of unlabeled samples. Second, we devise an online adaptation mechanism that utilizes the evidence of distribution shifts captured by the detection tool to dynamically update the classifier's parameters. The resulting adaptation process drives the distribution of test entropy values obtained from the self-trained classifier to match those of the source domain, building invariance to distribution shifts. This approach departs from the conventional self-training method, which focuses on minimizing the classifier's entropy. Our approach combines concepts in betting martingales and online learning to form a detection tool capable of quickly reacting to distribution shifts. We then reveal a tight relation between our adaptation scheme and optimal transport, which forms the basis of our novel self-supervised loss. Experimental results demonstrate that our approach improves test-time accuracy under distribution shifts while maintaining accuracy and calibration in their absence, outperforming leading entropy minimization methods across various scenarios.
Authors: Harsh Poonia, Moritz Willig, Zhongjie Yu, Matej Ze\v{c}evi\'c, Kristian Kersting, Devendra Singh Dhami
Abstract: Causal inference in hybrid domains, characterized by a mixture of discrete and continuous variables, presents a formidable challenge. We take a step towards this direction and propose Characteristic Interventional Sum-Product Network ($\chi$SPN) that is capable of estimating interventional distributions in presence of random variables drawn from mixed distributions. $\chi$SPN uses characteristic functions in the leaves of an interventional SPN (iSPN) thereby providing a unified view for discrete and continuous random variables through the Fourier-Stieltjes transform of the probability measures. A neural network is used to estimate the parameters of the learned iSPN using the intervened data. Our experiments on 3 synthetic heterogeneous datasets suggest that $\chi$SPN can effectively capture the interventional distributions for both discrete and continuous variables while being expressive and causally adequate. We also show that $\chi$SPN generalize to multiple interventions while being trained only on a single intervention data.
Authors: Jiajun Zhou, Yijie Yang, Austin M. Mroz, Kim E. Jelfs
Abstract: Polymers play a crucial role in a wide array of applications due to their diverse and tunable properties. Establishing the relationship between polymer representations and their properties is crucial to the computational design and screening of potential polymers via machine learning. The quality of the representation significantly influences the effectiveness of these computational methods. Here, we present a self-supervised contrastive learning paradigm, PolyCL, for learning high-quality polymer representation without the need for labels. Our model combines explicit and implicit augmentation strategies for improved learning performance. The results demonstrate that our model achieves either better, or highly competitive, performances on transfer learning tasks as a feature extractor without an overcomplicated training strategy or hyperparameter optimisation. Further enhancing the efficacy of our model, we conducted extensive analyses on various augmentation combinations used in contrastive learning. This led to identifying the most effective combination to maximise PolyCL's performance.
Authors: Tsai Hor Chan, Guosheng Yin, Kyongtae Bae, Lequan Yu
Abstract: Learning electronic health records (EHRs) has received emerging attention because of its capability to facilitate accurate medical diagnosis. Since the EHRs contain enriched information specifying complex interactions between entities, modeling EHRs with graphs is shown to be effective in practice. The EHRs, however, present a great degree of heterogeneity, sparsity, and complexity, which hamper the performance of most of the models applied to them. Moreover, existing approaches modeling EHRs often focus on learning the representations for a single task, overlooking the multi-task nature of EHR analysis problems and resulting in limited generalizability across different tasks. In view of these limitations, we propose a novel framework for EHR modeling, namely MulT-EHR (Multi-Task EHR), which leverages a heterogeneous graph to mine the complex relations and model the heterogeneity in the EHRs. To mitigate the large degree of noise, we introduce a denoising module based on the causal inference framework to adjust for severe confounding effects and reduce noise in the EHR data. Additionally, since our model adopts a single graph neural network for simultaneous multi-task prediction, we design a multi-task learning module to leverage the inter-task knowledge to regularize the training process. Extensive empirical studies on MIMIC-III and MIMIC-IV datasets validate that the proposed method consistently outperforms the state-of-the-art designs in four popular EHR analysis tasks -- drug recommendation, and predictions of the length of stay, mortality, and readmission. Thorough ablation studies demonstrate the robustness of our method upon variations to key components and hyperparameters.
Authors: Thibault Simonetto, Salah Ghamizi, Maxime Cordy
Abstract: While adversarial robustness in computer vision is a mature research field, fewer researchers have tackled the evasion attacks against tabular deep learning, and even fewer investigated robustification mechanisms and reliable defenses. We hypothesize that this lag in the research on tabular adversarial attacks is in part due to the lack of standardized benchmarks. To fill this gap, we propose TabularBench, the first comprehensive benchmark of robustness of tabular deep learning classification models. We evaluated adversarial robustness with CAA, an ensemble of gradient and search attacks which was recently demonstrated as the most effective attack against a tabular model. In addition to our open benchmark (https://github.com/serval-uni-lu/tabularbench) where we welcome submissions of new models and defenses, we implement 7 robustification mechanisms inspired by state-of-the-art defenses in computer vision and propose the largest benchmark of robust tabular deep learning over 200 models across five critical scenarios in finance, healthcare and security. We curated real datasets for each use case, augmented with hundreds of thousands of realistic synthetic inputs, and trained and assessed our models with and without data augmentations. We open-source our library that provides API access to all our pre-trained robust tabular models, and the largest datasets of real and synthetic tabular inputs. Finally, we analyze the impact of various defenses on the robustness and provide actionable insights to design new defenses and robustification mechanisms.
Authors: Alessio Mora, Lorenzo Valerio, Paolo Bellavista, Andrea Passarella
Abstract: Federated Learning (FL) promises better privacy guarantees for individuals' data when machine learning models are collaboratively trained. When an FL participant exercises its right to be forgotten, i.e., to detach from the FL framework it has participated and to remove its past contributions to the global model, the FL solution should perform all the necessary steps to make it possible without sacrificing the overall performance of the global model, which is not supported in state-of-the-art related solutions nowadays. In this paper, we propose FedQUIT, a novel algorithm that uses knowledge distillation to scrub the contribution of the forgetting data from an FL global model while preserving its generalization ability. FedQUIT directly works on clients' devices and does not require sharing additional information if compared with a regular FL process, nor does it assume the availability of publicly available proxy data. Our solution is efficient, effective, and applicable in both centralized and federated settings. Our experimental results show that, on average, FedQUIT requires less than 2.5% additional communication rounds to recover generalization performances after unlearning, obtaining a sanitized global model whose predictions are comparable to those of a global model that has never seen the data to be forgotten.
Authors: Joseph Gallego-Mejia, Oscar Bustos-Brinez, Fabio A. Gonz\'alez
Abstract: This paper introduces a novel anomaly detection framework that combines the robust statistical principles of density-estimation-based anomaly detection methods with the representation-learning capabilities of deep learning models. The method originated from this framework is presented in two different versions: a shallow approach employing a density-estimation model based on adaptive Fourier features and density matrices, and a deep approach that integrates an autoencoder to learn a low-dimensional representation of the data. By estimating the density of new samples, both methods are able to find normality scores. The methods can be seamlessly integrated into an end-to-end architecture and optimized using gradient-based optimization techniques. To evaluate their performance, extensive experiments were conducted on various benchmark datasets. The results demonstrate that both versions of the method can achieve comparable or superior performance when compared to other state-of-the-art methods. Notably, the shallow approach performs better on datasets with fewer dimensions, while the autoencoder-based approach shows improved performance on datasets with higher dimensions.
Authors: Sakhinana Sagar Srinivas, Rajat Kumar Sarkar, Venkataramana Runkana
Abstract: Battery life estimation is critical for optimizing battery performance and guaranteeing minimal degradation for better efficiency and reliability of battery-powered systems. The existing methods to predict the Remaining Useful Life(RUL) of Lithium-ion Batteries (LiBs) neglect the relational dependencies of the battery parameters to model the nonlinear degradation trajectories. We present the Battery GraphNets framework that jointly learns to incorporate a discrete dependency graph structure between battery parameters to capture the complex interactions and the graph-learning algorithm to model the intrinsic battery degradation for RUL prognosis. The proposed method outperforms several popular methods by a significant margin on publicly available battery datasets and achieves SOTA performance. We report the ablation studies to support the efficacy of our approach.
Authors: \'Africa Peri\'a\~nez, Kathrin Schmitz, Lazola Makhupula, Moiz Hassan, Moeti Moleko, Ana Fern\'andez del R\'io, Ivan Nazarov, Aditya Rastogi, Dexian Tang
Abstract: By providing evidence-based clinical decision support, digital tools and electronic health records can revolutionize patient management, especially in resource-poor settings where fewer health workers are available and often need more training. When these tools are integrated with AI, they can offer personalized support and adaptive interventions, effectively connecting community health workers (CHWs) and healthcare facilities. The CHARM (Community Health Access & Resource Management) app is an AI-native mobile app for CHWs. Developed through a joint partnership of Causal Foundry (CF) and mothers2mothers (m2m), CHARM empowers CHWs, mainly local women, by streamlining case management, enhancing learning, and improving communication. This paper details CHARM's development, integration, and upcoming reinforcement learning-based adaptive interventions, all aimed at enhancing health worker engagement, efficiency, and patient outcomes, thereby enhancing CHWs' capabilities and community health.
Authors: Ana Fern\'andez del R\'io, Michael Brennan Leong, Paulo Saraiva, Ivan Nazarov, Aditya Rastogi, Moiz Hassan, Dexian Tang, \'Africa Peri\'a\~nez
Abstract: Pharmacies are critical in healthcare systems, particularly in low- and middle-income countries. Procuring pharmacists with the right behavioral interventions or nudges can enhance their skills, public health awareness, and pharmacy inventory management, ensuring access to essential medicines that ultimately benefit their patients. We introduce a reinforcement learning operational system to deliver personalized behavioral interventions through mobile health applications. We illustrate its potential by discussing a series of initial experiments run with SwipeRx, an all-in-one app for pharmacists, including B2B e-commerce, in Indonesia. The proposed method has broader applications extending beyond pharmacy operations to optimize healthcare delivery.
Authors: Xiaotang Wang, Yun Zhu, Haizhou Shi, Yongchao Liu, Chuntao Hong
Abstract: Graph Transformers (GTs) have recently achieved significant success in the graph domain by effectively capturing both long-range dependencies and graph inductive biases. However, these methods face two primary challenges: (1) multi-view chaos, which results from coupling multi-view information (positional, structural, attribute), thereby impeding flexible usage and the interpretability of the propagation process. (2) local-global chaos, which arises from coupling local message passing with global attention, leading to issues of overfitting and over-globalizing. To address these challenges, we propose a high-level decoupled perspective of GTs, breaking them down into three components and two interaction levels: positional attention, structural attention, and attribute attention, alongside local and global interaction. Based on this decoupled perspective, we design a decoupled graph triple attention network named DeGTA, which separately computes multi-view attentions and adaptively integrates multi-view local and global information. This approach offers three key advantages: enhanced interpretability, flexible design, and adaptive integration of local and global information. Through extensive experiments, DeGTA achieves state-of-the-art performance across various datasets and tasks, including node classification and graph classification. Comprehensive ablation studies demonstrate that decoupling is essential for improving performance and enhancing interpretability. Our code is available at: https://github.com/wangxiaotang0906/DeGTA
Authors: Amr Alkhatib, Henrik Bostr\"om
Abstract: Many machine learning algorithms for tabular data produce black-box models, which prevent users from understanding the rationale behind the model predictions. In their unconstrained form, graph neural networks fall into this category, and they have further limited abilities to handle heterogeneous data. To overcome these limitations, an approach is proposed, called IGNH (Interpretable Graph Neural Network for Heterogeneous tabular data), which handles both categorical and numerical features, while constraining the learning process to generate exact feature attributions together with the predictions. A large-scale empirical investigation is presented, showing that the feature attributions provided by IGNH align with Shapley values that are computed post hoc. Furthermore, the results show that IGNH outperforms two powerful machine learning algorithms for tabular data, Random Forests and TabNet, while reaching a similar level of performance as XGBoost.
Authors: Enneng Yang, Li Shen, Guibing Guo, Xingwei Wang, Xiaochun Cao, Jie Zhang, Dacheng Tao
Abstract: Model merging is an efficient empowerment technique in the machine learning community that does not require the collection of raw training data and does not require expensive computation. As model merging becomes increasingly prevalent across various fields, it is crucial to understand the available model merging techniques comprehensively. However, there is a significant gap in the literature regarding a systematic and thorough review of these techniques. This survey provides a comprehensive overview of model merging methods and theories, their applications in various domains and settings, and future research directions. Specifically, we first propose a new taxonomic approach that exhaustively discusses existing model merging methods. Secondly, we discuss the application of model merging techniques in large language models, multimodal large language models, and 10+ machine learning subfields, including continual learning, multi-task learning, few-shot learning, etc. Finally, we highlight the remaining challenges of model merging and discuss future research directions. A comprehensive list of papers about model merging is available at \url{https://github.com/EnnengYang/Awesome-Model-Merging-Methods-Theories-Applications}.
URLs: https://github.com/EnnengYang/Awesome-Model-Merging-Methods-Theories-Applications
Authors: Xia Jiang, Yijun Zhou, Chuhan Xu, Adam Brufsky, Alan Wells
Abstract: A grid search, at the cost of training and testing a large number of models, is an effective way to optimize the prediction performance of deep learning models. A challenging task concerning grid search is the time management. Without a good time management scheme, a grid search can easily be set off as a mission that will not finish in our lifetime. In this study, we introduce a heuristic three-stage mechanism for managing the running time of low-budget grid searches, and the sweet-spot grid search (SSGS) and randomized grid search (RGS) strategies for improving model prediction performance, in predicting the 5-year, 10-year, and 15-year risk of breast cancer metastasis. We develop deep feedforward neural network (DFNN) models and optimize them through grid searches. We conduct eight cycles of grid searches by applying our three-stage mechanism and SSGS and RGS strategies. We conduct various SHAP analyses including unique ones that interpret the importance of the DFNN-model hyperparameters. Our results show that grid search can greatly improve model prediction. The grid searches we conducted improved the risk prediction of 5-year, 10-year, and 15-year breast cancer metastasis by 18.6%, 16.3%, and 17.3% respectively, over the average performance of all corresponding models we trained. We not only demonstrate best model performance but also characterize grid searches from various aspects such as their capabilities of discovering decent models and the unit grid search time. The three-stage mechanism worked effectively. It made our low-budget grid searches feasible and manageable, and in the meantime helped improve model prediction performance. Our SHAP analyses identified both clinical risk factors important for the prediction of future risk of breast cancer metastasis, and DFNN-model hyperparameters important to the prediction of performance scores.
Authors: Luke Causer, Grant M. Rotskoff, Juan P. Garrahan
Abstract: Diffusion models (DMs) are a class of generative machine learning methods that sample a target distribution by transforming samples of a trivial (often Gaussian) distribution using a learned stochastic differential equation. In standard DMs, this is done by learning a ``score function'' that reverses the effect of adding diffusive noise to the distribution of interest. Here we consider the generalisation of DMs to lattice systems with discrete degrees of freedom, and where noise is added via Markov chain jump dynamics. We show how to use tensor networks (TNs) to efficiently define and sample such ``discrete diffusion models'' (DDMs) without explicitly having to solve a stochastic differential equation. We show the following: (i) by parametrising the data and evolution operators as TNs, the denoising dynamics can be represented exactly; (ii) the auto-regressive nature of TNs allows to generate samples efficiently and without bias; (iii) for sampling Boltzmann-like distributions, TNs allow to construct an efficient learning scheme that integrates well with Monte Carlo. We illustrate this approach to study the equilibrium of two models with non-trivial thermodynamics, the $d=1$ constrained Fredkin chain and the $d=2$ Ising model.
Authors: Simon Mataigne, P. -A. Absil, Nina Miolane
Abstract: We give bounds on geodesic distances on the Stiefel manifold, derived from new geometric insights. The considered geodesic distances are induced by the one-parameter family of Riemannian metrics introduced by H\"uper et al. (2021), which contains the well-known Euclidean and canonical metrics. First, we give the best Lipschitz constants between the distances induced by any two members of the family of metrics. Then, we give a lower and an upper bound on the geodesic distance by the easily computable Frobenius distance. We give explicit families of pairs of matrices that depend on the parameter of the metric and the dimensions of the manifold, where the lower and the upper bound are attained. These bounds aim at improving the theoretical guarantees and performance of minimal geodesic computation algorithms by reducing the initial velocity search space. In addition, these findings contribute to advancing the understanding of geodesic distances on the Stiefel manifold and their applications.
Authors: Atefe Hassani, Islem Rek
Abstract: A fundamental challenge in federated learning lies in mixing heterogeneous datasets and classification tasks while minimizing the high communication cost caused by clients as well as the exchange of weight updates with the server over a fixed number of rounds. This results in divergent model convergence rates and performance, which may hinder their deployment in precision medicine. In real-world scenarios, client data is collected from different hospitals with extremely varying components (e.g., imaging modality, organ type, etc). Previous studies often overlooked the convoluted heterogeneity during the training stage where the target learning tasks vary across clients as well as the dataset type and their distributions. To address such limitations, we unprecedentedly introduce UniFed, a universal federated learning paradigm that aims to classify any disease from any imaging modality. UniFed also handles the issue of varying convergence times in the client-specific optimization based on the complexity of their learning tasks. Specifically, by dynamically adjusting both local and global models, UniFed considers the varying task complexities of clients and the server, enhancing its adaptability to real-world scenarios, thereby mitigating issues related to overtraining and excessive communication. Furthermore, our framework incorporates a sequential model transfer mechanism that takes into account the diverse tasks among hospitals and a dynamic task-complexity based ordering. We demonstrate the superiority of our framework in terms of accuracy, communication cost, and convergence time over relevant benchmarks in diagnosing retina, histopathology, and liver tumour diseases under federated learning. Our UniFed code is available at https://github.com/basiralab/UniFed.
Authors: Carlo Alberto Barbano, Matteo Brunello, Benoit Dufumier, Marco Grangetto
Abstract: Deep Learning (DL) in neuroimaging has become increasingly relevant for detecting neurological conditions and neurodegenerative disorders. One of the most predominant biomarkers in neuroimaging is represented by brain age, which has been shown to be a good indicator for different conditions, such as Alzheimer's Disease. Using brain age for pretraining DL models in transfer learning settings has also recently shown promising results, especially when dealing with data scarcity of different conditions. On the other hand, anatomical information of brain MRIs (e.g. cortical thickness) can provide important information for learning good representations that can be transferred to many downstream tasks. In this work, we propose AnatCL, an anatomical foundation model for brain MRIs that i.) leverages anatomical information with a weakly contrastive learning approach and ii.) achieves state-of-the-art performances in many different downstream tasks. To validate our approach we consider 12 different downstream tasks for diagnosis classification, and prediction of 10 different clinical assessment scores.
Authors: Stefan Goetz, Andreas Schaad
Abstract: We witness an increasing usage of AI-assistants even for routine (classroom) programming tasks. However, the code generated on basis of a so called "prompt" by the programmer does not always meet accepted security standards. On the one hand, this may be due to lack of best-practice examples in the training data. On the other hand, the actual quality of the programmers prompt appears to influence whether generated code contains weaknesses or not. In this paper we analyse 4 major LLMs with respect to the security of generated code. We do this on basis of a case study for the Python and Javascript language, using the MITRE CWE catalogue as the guiding security definition. Our results show that using different prompting techniques, some LLMs initially generate 65% code which is deemed insecure by a trained security engineer. On the other hand almost all analysed LLMs will eventually generate code being close to 100% secure with increasing manual guidance of a skilled engineer.
Authors: Christoph Dehner, Guillaume Zahnd
Abstract: Clinical adoption of multispectral optoacoustic tomography necessitates improvements of the image quality available in real-time, as well as a reduction in the scanner financial cost. Deep learning approaches have recently unlocked the reconstruction of high-quality optoacoustic images in real-time. However, currently used deep neural network architectures require powerful graphics processing units to infer images at sufficiently high frame-rates, consequently greatly increasing the price tag. Herein we propose EfficientDeepMB, a relatively lightweight (17M parameters) network architecture achieving high frame-rates on medium-sized graphics cards with no noticeable downgrade in image quality. EfficientDeepMB is built upon DeepMB, a previously established deep learning framework to reconstruct high-quality images in real-time, and upon EfficientNet, a network architectures designed to operate of mobile devices. We demonstrate the performance of EfficientDeepMB in terms of reconstruction speed and accuracy using a large and diverse dataset of in vivo optoacoustic scans. EfficientDeepMB is about three to five times faster than DeepMB: deployed on a medium-sized NVIDIA RTX A2000 Ada, EfficientDeepMB reconstructs images at speeds enabling live image feedback (59Hz) while DeepMB fails to meets the real-time inference threshold (14Hz). The quantitative difference between the reconstruction accuracy of EfficientDeepMB and DeepMB is marginal (data residual norms of 0.1560 vs. 0.1487, mean absolute error of 0.642 vs. 0.745). There are no perceptible qualitative differences between images inferred with the two reconstruction methods.
Authors: Julian Suk, Dieuwertje Alblas, Barbara A. Hutten, Albert Wiegman, Christoph Brune, Pim van Ooij, Jelmer M. Wolterink
Abstract: Hemodynamic quantities are valuable biomedical risk factors for cardiovascular pathology such as atherosclerosis. Non-invasive, in-vivo measurement of these quantities can only be performed using a select number of modalities that are not widely available, such as 4D flow magnetic resonance imaging (MRI). In this work, we create a surrogate model for hemodynamic flow field estimation, powered by machine learning. We train graph neural networks that include priors about the underlying symmetries and physics, limiting the amount of data required for training. This allows us to train the model using moderately-sized, in-vivo 4D flow MRI datasets, instead of large in-silico datasets obtained by computational fluid dynamics (CFD), as is the current standard. We create an efficient, equivariant neural network by combining the popular PointNet++ architecture with group-steerable layers. To incorporate the physics-informed priors, we derive an efficient discretisation scheme for the involved differential operators. We perform extensive experiments in carotid arteries and show that our model can accurately estimate low-noise hemodynamic flow fields in the carotid artery. Moreover, we show how the learned relation between geometry and hemodynamic quantities transfers to 3D vascular models obtained using a different imaging modality than the training data. This shows that physics-informed graph neural networks can be trained using 4D flow MRI data to estimate blood flow in unseen carotid artery geometries.
Authors: Mazharul Hossain, Aaron Robinson, Lan Wang, Chrysanthe Preza
Abstract: Hyperspectral sensing is a valuable tool for detecting anomalies and distinguishing between materials in a scene. Hyperspectral anomaly detection (HS-AD) helps characterize the captured scenes and separates them into anomaly and background classes. It is vital in agriculture, environment, and military applications such as RSTA (reconnaissance, surveillance, and target acquisition) missions. We previously designed an equal voting ensemble of hyperspectral unmixing and three unsupervised HS-AD algorithms. We later utilized a supervised classifier to determine the weights of a voting ensemble, creating a hybrid of heterogeneous unsupervised HS-AD algorithms with a supervised classifier in a model stacking, which improved detection accuracy. However, supervised classification methods usually fail to detect novel or unknown patterns that substantially deviate from those seen previously. In this work, we evaluate our technique and other supervised and unsupervised methods using general hyperspectral data to provide new insights.
Authors: Nikola Surjanovic, Andrew Henrey, Thomas M. Loughin
Abstract: We demonstrate that adaptively controlling the size of individual regression trees in a random forest can improve predictive performance, contrary to the conventional wisdom that trees should be fully grown. A fast pruning algorithm, alpha-trimming, is proposed as an effective approach to pruning trees within a random forest, where more aggressive pruning is performed in regions with a low signal-to-noise ratio. The amount of overall pruning is controlled by adjusting the weight on an information criterion penalty as a tuning parameter, with the standard random forest being a special case of our alpha-trimmed random forest. A remarkable feature of alpha-trimming is that its tuning parameter can be adjusted without refitting the trees in the random forest once the trees have been fully grown once. In a benchmark suite of 46 example data sets, mean squared prediction error is often substantially lowered by using our pruning algorithm and is never substantially increased compared to a random forest with fully-grown trees at default parameter settings.
Authors: Ricardo Romero
Abstract: The intersection of artificial intelligence and bioinformatics has enabled significant advancements in drug discovery, particularly through the application of machine learning models. In this study, we present a combined approach using genetic algorithms and deep learning models to address two critical aspects of drug discovery: the generation of novel tyrosine kinase inhibitors and the prediction of their bioactivity. The generative model leverages genetic algorithms to create new small molecules with optimized ADMET (absorption, distribution, metabolism, excretion, and toxicity) and drug-likeness properties. Concurrently, a deep learning model is employed to predict the bioactivity of these generated molecules against tyrosine kinases, a key enzyme family involved in various cellular processes and cancer progression. By integrating these advanced computational methods, we demonstrate a powerful framework for accelerating the generation and identification of potential tyrosine kinase inhibitors, contributing to more efficient and effective early-stage drug discovery processes.
Authors: Abdulrahman Hamman Adama Chukkol, Senlin Luo, Kashif Sharif, Yunusa Haruna, Muhammad Muhammad Abdullahi
Abstract: Binary program vulnerability detection is critical for software security, yet existing deep learning approaches often rely on source code analysis, limiting their ability to detect unknown vulnerabilities. To address this, we propose VulCatch, a binary-level vulnerability detection framework. VulCatch introduces a Synergy Decompilation Module (SDM) and Kolmogorov-Arnold Networks (KAN) to transform raw binary code into pseudocode using CodeT5, preserving high-level semantics for deep analysis with tools like Ghidra and IDA. KAN further enhances feature transformation, enabling the detection of complex vulnerabilities. VulCatch employs word2vec, Inception Blocks, BiLSTM Attention, and Residual connections to achieve high detection accuracy (98.88%) and precision (97.92%), while minimizing false positives (1.56%) and false negatives (2.71%) across seven CVE datasets.
Authors: Rasa Khosrowshahli, Shahryar Rahnamayan, Beatrice Ombuki-Berman
Abstract: Deep learning is mainly based on utilizing gradient-based optimization for training Deep Neural Network (DNN) models. Although robust and widely used, gradient-based optimization algorithms are prone to getting stuck in local minima. In this modern deep learning era, the state-of-the-art DNN models have millions and billions of parameters, including weights and biases, making them huge-scale optimization problems in terms of search space. Tuning a huge number of parameters is a challenging task that causes vanishing/exploding gradients and overfitting; likewise, utilized loss functions do not exactly represent our targeted performance metrics. A practical solution to exploring large and complex solution space is meta-heuristic algorithms. Since DNNs exceed thousands and millions of parameters, even robust meta-heuristic algorithms, such as Differential Evolution, struggle to efficiently explore and converge in such huge-dimensional search spaces, leading to very slow convergence and high memory demand. To tackle the mentioned curse of dimensionality, the concept of blocking was recently proposed as a technique that reduces the search space dimensions by grouping them into blocks. In this study, we aim to introduce Histogram-based Blocking Differential Evolution (HBDE), a novel approach that hybridizes gradient-based and gradient-free algorithms to optimize parameters. Experimental results demonstrated that the HBDE could reduce the parameters in the ResNet-18 model from 11M to 3K during the training/optimizing phase by metaheuristics, namely, the proposed HBDE, which outperforms baseline gradient-based and parent gradient-free DE algorithms evaluated on CIFAR-10 and CIFAR-100 datasets showcasing its effectiveness with reduced computational demands for the very first time.
Authors: Pranav Putta, Edmund Mills, Naman Garg, Sumeet Motwani, Chelsea Finn, Divyansh Garg, Rafael Rafailov
Abstract: Large Language Models (LLMs) have shown remarkable capabilities in natural language tasks requiring complex reasoning, yet their application in agentic, multi-step reasoning within interactive environments remains a difficult challenge. Traditional supervised pre-training on static datasets falls short in enabling autonomous agent capabilities needed to perform complex decision-making in dynamic settings like web navigation. Previous attempts to bridge this ga-through supervised fine-tuning on curated expert demonstrations-often suffer from compounding errors and limited exploration data, resulting in sub-optimal policy outcomes. To overcome these challenges, we propose a framework that combines guided Monte Carlo Tree Search (MCTS) search with a self-critique mechanism and iterative fine-tuning on agent interactions using an off-policy variant of the Direct Preference Optimization (DPO) algorithm. Our method allows LLM agents to learn effectively from both successful and unsuccessful trajectories, thereby improving their generalization in complex, multi-step reasoning tasks. We validate our approach in the WebShop environment-a simulated e-commerce platform where it consistently outperforms behavior cloning and reinforced fine-tuning baseline, and beats average human performance when equipped with the capability to do online search. In real-world booking scenarios, our methodology boosts Llama-3 70B model's zero-shot performance from 18.6% to 81.7% success rate (a 340% relative increase) after a single day of data collection and further to 95.4% with online search. We believe this represents a substantial leap forward in the capabilities of autonomous agents, paving the way for more sophisticated and reliable decision-making in real-world settings.
Authors: Blake Castleman, Uzay Macar, Ansaf Salleb-Aouissi
Abstract: Remote education has proliferated in the twenty-first century, yielding rise to intelligent tutoring systems. In particular, research has found multi-armed bandit (MAB) intelligent tutors to have notable abilities in traversing the exploration-exploitation trade-off landscape for student problem recommendations. Prior literature, however, contains a significant lack of open-sourced MAB intelligent tutors, which impedes potential applications of these educational MAB recommendation systems. In this paper, we combine recent literature on MAB intelligent tutoring techniques into an open-sourced and simply deployable hierarchical MAB algorithm, capable of progressing students concurrently through concepts and problems, determining ideal recommended problem difficulties, and assessing latent memory decay. We evaluate our algorithm using simulated groups of 500 students, utilizing Bayesian Knowledge Tracing to estimate students' content mastery. Results suggest that our algorithm, when turned difficulty-agnostic, significantly boosts student success, and that the further addition of problem-difficulty adaptation notably improves this metric.
Authors: Patrick Kage, Jay C. Rothenberger, Pavlos Andreadis, Dimitrios I. Diochnos
Abstract: Deep neural models have achieved state of the art performance on a wide range of problems in computer science, especially in computer vision. However, deep neural networks often require large datasets of labeled samples to generalize effectively, and an important area of active research is semi-supervised learning, which attempts to instead utilize large quantities of (easily acquired) unlabeled samples. One family of methods in this space is pseudo-labeling, a class of algorithms that use model outputs to assign labels to unlabeled samples which are then used as labeled samples during training. Such assigned labels, called pseudo-labels, are most commonly associated with the field of semi-supervised learning. In this work we explore a broader interpretation of pseudo-labels within both self-supervised and unsupervised methods. By drawing the connection between these areas we identify new directions when advancements in one area would likely benefit others, such as curriculum learning and self-supervised regularization.
Authors: Jong Hyun Kim, Jongseong Jang
Abstract: The application of machine learning to transcriptomics data has led to significant advances in cancer research. However, the high dimensionality and complexity of RNA sequencing (RNA-seq) data pose significant challenges in pan-cancer studies. This study hypothesizes that gene sets derived from single-cell RNA sequencing (scRNA-seq) data will outperform those selected using bulk RNA-seq in pan-cancer downstream tasks. We analyzed scRNA-seq data from 181 tumor biopsies across 13 cancer types. High-dimensional weighted gene co-expression network analysis (hdWGCNA) was performed to identify relevant gene sets, which were further refined using XGBoost for feature selection. These gene sets were applied to downstream tasks using TCGA pan-cancer RNA-seq data and compared to six reference gene sets and oncogenes from OncoKB evaluated with deep learning models, including multilayer perceptrons (MLPs) and graph neural networks (GNNs). The XGBoost-refined hdWGCNA gene set demonstrated higher performance in most tasks, including tumor mutation burden assessment, microsatellite instability classification, mutation prediction, cancer subtyping, and grading. In particular, genes such as DPM1, BAD, and FKBP4 emerged as important pan-cancer biomarkers, with DPM1 consistently significant across tasks. This study presents a robust approach for feature selection in cancer genomics by integrating scRNA-seq data and advanced analysis techniques, offering a promising avenue for improving predictive accuracy in cancer research.
Authors: Tong Wang, K. Sudhir, Dat Hong
Abstract: Advanced Large language models (LLMs) like GPT-4 or LlaMa 3 provide superior performance in complex human-like interactions. But they are costly, or too large for edge devices such as smartphones and harder to self-host, leading to security and privacy concerns. This paper introduces a novel interpretable knowledge distillation approach to enhance the performance of smaller, more economical LLMs that firms can self-host. We study this problem in the context of building a customer service agent aimed at achieving high customer satisfaction through goal-oriented dialogues. Unlike traditional knowledge distillation, where the "student" model learns directly from the "teacher" model's responses via fine-tuning, our interpretable "strategy" teaching approach involves the teacher providing strategies to improve the student's performance in various scenarios. This method alternates between a "scenario generation" step and a "strategies for improvement" step, creating a customized library of scenarios and optimized strategies for automated prompting. The method requires only black-box access to both student and teacher models; hence it can be used without manipulating model parameters. In our customer service application, the method improves performance, and the learned strategies are transferable to other LLMs and scenarios beyond the training set. The method's interpretabilty helps safeguard against potential harms through human audit.
Authors: Ethan Kou, Noah Curran
Abstract: Robust perception is crucial in autonomous vehicle navigation and localization. Visual processing tasks, like semantic segmentation, should work in varying weather conditions and during different times of day. Semantic segmentation is where each pixel is assigned a class, which is useful for locating overall features (1). Training a segmentation model requires large amounts of data, and the labeling process for segmentation data is especially tedious. Additionally, many large datasets include only images taken in clear weather. This is a problem because training a model exclusively on clear weather data hinders performance in adverse weather conditions like fog or rain. We hypothesize that given a dataset of only clear days images, applying image augmentation (such as random rain, fog, and brightness) during training allows for domain adaptation to diverse weather conditions. We used CARLA, a 3D realistic autonomous vehicle simulator, to collect 1200 images in clear weather composed of 29 classes from 10 different towns (2). We also collected 1200 images of random weather effects. We trained encoder-decoder UNet models to perform semantic segmentation. Applying augmentations significantly improved segmentation under weathered night conditions (p < 0.001). However, models trained on weather data have significantly lower losses than those trained on augmented data in all conditions except for clear days. This shows there is room for improvement in the domain adaptation approach. Future work should test more types of augmentations and also use real-life images instead of CARLA. Ideally, the augmented model meets or exceeds the performance of the weather model.
Authors: Alireza Mousavi-Hosseini, Denny Wu, Murat A. Erdogdu
Abstract: We study the problem of learning multi-index models in high-dimensions using a two-layer neural network trained with the mean-field Langevin algorithm. Under mild distributional assumptions on the data, we characterize the effective dimension $d_{\mathrm{eff}}$ that controls both sample and computational complexity by utilizing the adaptivity of neural networks to latent low-dimensional structures. When the data exhibit such a structure, $d_{\mathrm{eff}}$ can be significantly smaller than the ambient dimension. We prove that the sample complexity grows almost linearly with $d_{\mathrm{eff}}$, bypassing the limitations of the information and generative exponents that appeared in recent analyses of gradient-based feature learning. On the other hand, the computational complexity may inevitably grow exponentially with $d_{\mathrm{eff}}$ in the worst-case scenario. Motivated by improving computational complexity, we take the first steps towards polynomial time convergence of the mean-field Langevin algorithm by investigating a setting where the weights are constrained to be on a compact manifold with positive Ricci curvature, such as the hypersphere. There, we study assumptions under which polynomial time convergence is achievable, whereas similar assumptions in the Euclidean setting lead to exponential time complexity.
Authors: Hao-Yun Hsu, Yi-Ching Cheng, Guan-Hua Huang
Abstract: In this research, we revisit the architecture of semantic segmentation and evaluate the models excelling in polyp segmentation. We introduce an integrated framework that harnesses the advantages of different models to attain an optimal outcome. More specifically, we fuse the learned features from convolutional and transformer models for prediction, and we view this approach as an ensemble technique to enhance model performance. Our experiments on polyp segmentation reveal that the proposed architecture surpasses other top models, exhibiting improved learning capacity and resilience. The code is available at https://github.com/HuangDLab/EnFormer.
Authors: Marcos Faundez-Zanuy, Anna Faura-Pujol, Hector Montalvo-Ruiz, Alexia Losada-Fors, Pablo Genovese, Pilar Sanz-Cartagena
Abstract: In this paper we analyze and compare different movement sensors: micro-chip gesture-ID, leap motion, noitom mocap, and specially developed sensor for tapping and foot motion analysis. The main goal is to evaluate the accu-racy of measurements provided by the sensors. This study presents rele-vance, for instance, in tremor/Parkinson disease analysis as well as no touch mechanisms for activation and control of devices. This scenario is especially interesting in COVID-19 scenario. Removing the need to touch a surface, the risk of contagion is reduced.
Authors: Taoran Sheng, Manfred Huber
Abstract: While the widely available embedded sensors in smartphones and other wearable devices make it easier to obtain data of human activities, recognizing different types of human activities from sensor-based data remains a difficult research topic in ubiquitous computing. One reason for this is that most of the collected data is unlabeled. However, many current human activity recognition (HAR) systems are based on supervised methods, which heavily rely on the labels of the data. We describe a weakly self-supervised approach in this paper that consists of two stages: (1) In stage one, the model learns from the nature of human activities by projecting the data into an embedding space where similar activities are grouped together; (2) In stage two, the model is fine-tuned using similarity information in a few-shot learning fashion using the similarity information of the data. This allows downstream classification or clustering tasks to benefit from the embeddings. Experiments on three benchmark datasets demonstrate the framework's effectiveness and show that our approach can help the clustering algorithm achieve comparable performance in identifying and categorizing the underlying human activities as pure supervised techniques applied directly to a corresponding fully labeled data set.
Authors: Di Chen, Jia Li, H. Michael Zhang
Abstract: Cooperation is a ubiquitous phenomenon in many natural, social, and engineered systems that contain multiple agents. Characterizing and quantifying cooperativeness of driving agents is of interest and significance for two reasons. Theoretically, it will enhance the understanding of micro-macro connections and emergence of cooperation in mixed traffic. Pragmatically, this understanding will benefit the design and operations of automated and mixed-autonomy transportation systems. However, it remains unclear how the cooperativeness can be accurately defined and quantified from empirical data, and it remains open when and to what extent collective cooperativeness exists. This paper is intended to fill the gap. We propose a unified conceptual framework to estimate collective cooperativeness of driving agents leveraging a recent behavioral equilibrium model of mixed autonomy traffic (Li et al. 2022a). This framework is interpretable, theoretically consistent, and enables quantifying collective cooperativeness of traffic agents from trajectory data. We apply the framework to multilane freeway traffic employing NGSIM I-80 trajectory data set and careful data selection. Our case study indicates the existence of collective cooperativeness between human-driven passenger cars and trucks in real-world traffic and reveals its other properties that are otherwise unknown.
Authors: Peiyuan Chen, Zecheng Zhang, Yiping Dong, Li Zhou, Han Wang
Abstract: Visual Question Answering (VQA) is a challenging task that requires systems to provide accurate answers to questions based on image content. Current VQA models struggle with complex questions due to limitations in capturing and integrating multimodal information effectively. To address these challenges, we propose the Rank VQA model, which leverages a ranking-inspired hybrid training strategy to enhance VQA performance. The Rank VQA model integrates high-quality visual features extracted using the Faster R-CNN model and rich semantic text features obtained from a pre-trained BERT model. These features are fused through a sophisticated multimodal fusion technique employing multi-head self-attention mechanisms. Additionally, a ranking learning module is incorporated to optimize the relative ranking of answers, thus improving answer accuracy. The hybrid training strategy combines classification and ranking losses, enhancing the model's generalization ability and robustness across diverse datasets. Experimental results demonstrate the effectiveness of the Rank VQA model. Our model significantly outperforms existing state-of-the-art models on standard VQA datasets, including VQA v2.0 and COCO-QA, in terms of both accuracy and Mean Reciprocal Rank (MRR). The superior performance of Rank VQA is evident in its ability to handle complex questions that require understanding nuanced details and making sophisticated inferences from the image and text. This work highlights the effectiveness of a ranking-based hybrid training strategy in improving VQA performance and lays the groundwork for further research in multimodal learning methods.
Authors: Jinghuai Zhang, Jianfeng Chi, Zheng Li, Kunlin Cai, Yang Zhang, Yuan Tian
Abstract: Fine-tuning pre-trained models for downstream tasks has led to a proliferation of open-sourced task-specific models. Recently, Model Merging (MM) has emerged as an effective approach to facilitate knowledge transfer among these independently fine-tuned models. MM directly combines multiple fine-tuned task-specific models into a merged model without additional training, and the resulting model shows enhanced capabilities in multiple tasks. Although MM provides great utility, it may come with security risks because an adversary can exploit MM to affect multiple downstream tasks. However, the security risks of MM have barely been studied. In this paper, we first find that MM, as a new learning paradigm, introduces unique challenges for existing backdoor attacks due to the merging process. To address these challenges, we introduce BadMerging, the first backdoor attack specifically designed for MM. Notably, BadMerging allows an adversary to compromise the entire merged model by contributing as few as one backdoored task-specific model. BadMerging comprises a two-stage attack mechanism and a novel feature-interpolation-based loss to enhance the robustness of embedded backdoors against the changes of different merging parameters. Considering that a merged model may incorporate tasks from different domains, BadMerging can jointly compromise the tasks provided by the adversary (on-task attack) and other contributors (off-task attack) and solve the corresponding unique challenges with novel attack designs. Extensive experiments show that BadMerging achieves remarkable attacks against various MM algorithms. Our ablation study demonstrates that the proposed attack designs can progressively contribute to the attack performance. Finally, we show that prior defense mechanisms fail to defend against our attacks, highlighting the need for more advanced defense.
Authors: Hee-Geon Kang, Sunggon Kim
Abstract: The problem of finding the expected value of a statistic of a locally stable point process in a bounded region is addressed. We propose an adaptive importance sampling for solving the problem. In our proposal, we restrict the importance point process to the family of homogeneous Poisson point processes, which enables us to generate quickly independent samples of the importance point process. The optimal intensity of the importance point process is found by applying the cross-entropy minimization method. In the proposed scheme, the expected value of the function and the optimal intensity are iteratively estimated in an adaptive manner. We show that the proposed estimator converges to the target value almost surely, and prove the asymptotic normality of it. We explain how to apply the proposed scheme to the estimation of the intensity of a stationary pairwise interaction point process. The performance of the proposed scheme is compared numerically with the Markov chain Monte Carlo simulation and the perfect sampling.
Authors: Difeng Cai, Edmond Chow, Yuanzhe Xi
Abstract: In this paper, we present a comprehensive analysis of the posterior covariance field in Gaussian processes, with applications to the posterior covariance matrix. The analysis is based on the Gaussian prior covariance but the approach also applies to other covariance kernels. Our geometric analysis reveals how the Gaussian kernel's bandwidth parameter and the spatial distribution of the observations influence the posterior covariance as well as the corresponding covariance matrix, enabling straightforward identification of areas with high or low covariance in magnitude. Drawing inspiration from the a posteriori error estimation techniques in adaptive finite element methods, we also propose several estimators to efficiently measure the absolute posterior covariance field, which can be used for efficient covariance matrix approximation and preconditioning. We conduct a wide range of experiments to illustrate our theoretical findings and their practical applications.
Authors: Juan-Pablo Ortega, Florian Rossmannek
Abstract: Several topological and analytical notions of continuity and fading memory for causal and time-invariant filters are introduced, and the relations between them are analysed. A significant generalization of the convolution theorem that establishes the equivalence between the fading memory property and the availability of convolution representations of linear filters is proved. This result extends a previous such characterization to a complete array of weighted norms in the definition of the fading memory property. Additionally, the main theorem shows that the availability of convolution representations can be characterized, at least when the codomain is finite-dimensional, not only by the fading memory property but also by the reunion of two purely topological notions that are called minimal continuity and minimal fading memory property. Finally, when the input space and the codomain of a linear functional are Hilbert spaces, it is shown that minimal continuity and the minimal fading memory property guarantee the existence of interesting embeddings of the associated reproducing kernel Hilbert spaces and approximation results of solutions of kernel regressions in the presence of finite data sets.
Authors: Tao Sun, Sander Boht\'e
Abstract: Speech enhancement (SE) improves communication in noisy environments, affecting areas such as automatic speech recognition, hearing aids, and telecommunications. With these domains typically being power-constrained and event-based while requiring low latency, neuromorphic algorithms in the form of spiking neural networks (SNNs) have great potential. Yet, current effective SNN solutions require a contextual sampling window imposing substantial latency, typically around 32ms, too long for many applications. Inspired by Dual-Path Spiking Neural Networks (DPSNNs) in classical neural networks, we develop a two-phase time-domain streaming SNN framework -- the Dual-Path Spiking Neural Network (DPSNN). In the DPSNN, the first phase uses Spiking Convolutional Neural Networks (SCNNs) to capture global contextual information, while the second phase uses Spiking Recurrent Neural Networks (SRNNs) to focus on frequency-related features. In addition, the regularizer suppresses activation to further enhance energy efficiency of our DPSNNs. Evaluating on the VCTK and Intel DNS Datasets, we demonstrate that our approach achieves the very low latency (approximately 5ms) required for applications like hearing aids, while demonstrating excellent signal-to-noise ratio (SNR), perceptual quality, and energy efficiency.
Authors: Julian Ruddick, Glenn Ceusters, Gilles Van Kriekinge, Evgenii Genov, Thierry Coosemans, Maarten Messagie
Abstract: Recent advancements in machine learning based energy management approaches, specifically reinforcement learning with a safety layer (OptLayerPolicy) and a metaheuristic algorithm generating a decision tree control policy (TreeC), have shown promise. However, their effectiveness has only been demonstrated in computer simulations. This paper presents the real-world validation of these methods, comparing against model predictive control and simple rule-based control benchmark. The experiments were conducted on the electrical installation of 4 reproductions of residential houses, which all have their own battery, photovoltaic and dynamic load system emulating a non-controllable electrical load and a controllable electric vehicle charger. The results show that the simple rules, TreeC, and model predictive control-based methods achieved similar costs, with a difference of only 0.6%. The reinforcement learning based method, still in its training phase, obtained a cost 25.5\% higher to the other methods. Additional simulations show that the costs can be further reduced by using a more representative training dataset for TreeC and addressing errors in the model predictive control implementation caused by its reliance on accurate data from various sources. The OptLayerPolicy safety layer allows safe online training of a reinforcement learning agent in the real-world, given an accurate constraint function formulation. The proposed safety layer method remains error-prone, nonetheless, it is found beneficial for all investigated methods. The TreeC method, which does require building a realistic simulation for training, exhibits the safest operational performance, exceeding the grid limit by only 27.1 Wh compared to 593.9 Wh for reinforcement learning.
Authors: Tobias A. Opsahl
Abstract: Despite recent success in natural language processing (NLP), fact verification still remains a difficult task. Due to misinformation spreading increasingly fast, attention has been directed towards automatically verifying the correctness of claims. In the domain of NLP, this is usually done by training supervised machine learning models to verify claims by utilizing evidence from trustworthy corpora. We present efficient methods for verifying claims on a dataset where the evidence is in the form of structured knowledge graphs. We use the FactKG dataset, which is constructed from the DBpedia knowledge graph extracted from Wikipedia. By simplifying the evidence retrieval process, from fine-tuned language models to simple logical retrievals, we are able to construct models that both require less computational resources and achieve better test-set accuracy.
Authors: Jean-Marie Lemercier, Eloi Moliner, Simon Welker, Vesa V\"alim\"aki, Timo Gerkmann
Abstract: This paper presents an unsupervised method for single-channel blind dereverberation and room impulse response (RIR) estimation, called BUDDy. The algorithm is rooted in Bayesian posterior sampling: it combines a likelihood model enforcing fidelity to the reverberant measurement, and an anechoic speech prior implemented by an unconditional diffusion model. We design a parametric filter representing the RIR, with exponential decay for each frequency subband. Room acoustics estimation and speech dereverberation are jointly carried out, as the filter parameters are iteratively estimated and the speech utterance refined along the reverse diffusion trajectory. In a blind scenario where the room impulse response is unknown, BUDDy successfully performs speech dereverberation in various acoustic scenarios, significantly outperforming other blind unsupervised baselines. Unlike supervised methods, which often struggle to generalize, BUDDy seamlessly adapts to different acoustic conditions. This paper extends our previous work by offering new experimental results and insights into the algorithm's performance and versatility. We first investigate the robustness of informed dereverberation methods to RIR estimation errors, to motivate the joint acoustic estimation and dereverberation paradigm. Then, we demonstrate the adaptability of our method to high-resolution singing voice dereverberation, study its performance in RIR estimation, and conduct subjective evaluation experiments to validate the perceptual quality of the results, among other contributions. Audio samples and code can be found online.
Authors: Anton Kullberg, Frida Viset, Isaac Skog, Gustaf Hendeby
Abstract: Basis Function (BF) expansions are a cornerstone of any engineer's toolbox for computational function approximation which shares connections with both neural networks and Gaussian processes. Even though BF expansions are an intuitive and straightforward model to use, they suffer from quadratic computational complexity in the number of BFs if the predictive variance is to be computed. We develop a method to automatically select the most important BFs for prediction in a sub-domain of the model domain. This significantly reduces the computational complexity of computing predictions while maintaining predictive accuracy. The proposed method is demonstrated using two numerical examples, where reductions up to 50-75% are possible without significantly reducing the predictive accuracy.
Authors: Jan Luca Scheerer, Anton Lykov, Moe Kayali, Ilias Fountalis, Dan Olteanu, Nikolaos Vasiloglou, Dan Suciu
Abstract: We demonstrate QirK, a system for answering natural language questions on Knowledge Graphs (KG). QirK can answer structurally complex questions that are still beyond the reach of emerging Large Language Models (LLMs). It does so using a unique combination of database technology, LLMs, and semantic search over vector embeddings. The glue for these components is an intermediate representation (IR). The input question is mapped to IR using LLMs, which is then repaired into a valid relational database query with the aid of a semantic search on vector embeddings. This allows a practical synthesis of LLM capabilities and KG reliability. A short video demonstrating QirK is available at https://youtu.be/6c81BLmOZ0U.
Authors: Amit Attia, Ofir Gaash, Tomer Koren
Abstract: We consider the problem of asynchronous stochastic optimization, where an optimization algorithm makes updates based on stale stochastic gradients of the objective that are subject to an arbitrary (possibly adversarial) sequence of delays. We present a procedure which, for any given $q \in (0,1]$, transforms any standard stochastic first-order method to an asynchronous method with convergence guarantee depending on the $q$-quantile delay of the sequence. This approach leads to convergence rates of the form $O(\tau_q/qT+\sigma/\sqrt{qT})$ for non-convex and $O(\tau_q^2/(q T)^2+\sigma/\sqrt{qT})$ for convex smooth problems, where $\tau_q$ is the $q$-quantile delay, generalizing and improving on existing results that depend on the average delay. We further show a method that automatically adapts to all quantiles simultaneously, without any prior knowledge of the delays, achieving convergence rates of the form $O(\inf_{q} \tau_q/qT+\sigma/\sqrt{qT})$ for non-convex and $O(\inf_{q} \tau_q^2/(q T)^2+\sigma/\sqrt{qT})$ for convex smooth problems. Our technique is based on asynchronous mini-batching with a careful batch-size selection and filtering of stale gradients.
Authors: Stas Syrota, Pablo Moreno-Mu\~noz, S{\o}ren Hauberg
Abstract: Latent space geometry provides a rigorous and empirically valuable framework for interacting with the latent variables of deep generative models. This approach reinterprets Euclidean latent spaces as Riemannian through a pull-back metric, allowing for a standard differential geometric analysis of the latent space. Unfortunately, data manifolds are generally compact and easily disconnected or filled with holes, suggesting a topological mismatch to the Euclidean latent space. The most established solution to this mismatch is to let uncertainty be a proxy for topology, but in neural network models, this is often realized through crude heuristics that lack principle and generally do not scale to high-dimensional representations. We propose using ensembles of decoders to capture model uncertainty and show how to easily compute geodesics on the associated expected manifold. Empirically, we find this simple and reliable, thereby coming one step closer to easy-to-use latent geometries.
Authors: Yuyang Yan, Sami O. Simons, Loes van Bemmel, Lauren Reinders, Frits M. E. Franssen, Visara Urovi
Abstract: Voice signals originating from the respiratory tract are utilized as valuable acoustic biomarkers for the diagnosis and assessment of respiratory diseases. Among the employed acoustic features, Mel Frequency Cepstral Coefficients (MFCC) is widely used for automatic analysis, with MFCC extraction commonly relying on default parameters. However, no comprehensive study has systematically investigated the impact of MFCC extraction parameters on respiratory disease diagnosis. In this study, we address this gap by examining the effects of key parameters, namely the number of coefficients, frame length, and hop length between frames, on respiratory condition examination. Our investigation uses four datasets: the Cambridge COVID-19 Sound database, the Coswara dataset, the Saarbrucken Voice Disorders (SVD) database, and a TACTICAS dataset. The Support Vector Machine (SVM) is employed as the classifier, given its widespread adoption and efficacy. Our findings indicate that the accuracy of MFCC decreases as hop length increases, and the optimal number of coefficients is observed to be approximately 30. The performance of MFCC varies with frame length across the datasets: for the COVID-19 datasets (Cambridge COVID-19 Sound database and Coswara dataset), performance declines with longer frame lengths, while for the SVD dataset, performance improves with increasing frame length (from 50 ms to 500 ms). Furthermore, we investigate the optimized combination of these parameters and observe substantial enhancements in accuracy. Compared to the worst combination, the SVM model achieves an accuracy of 81.1%, 80.6%, and 71.7%, with improvements of 19.6%, 16.10%, and 14.90% for the Cambridge COVID-19 Sound database, the Coswara dataset, and the SVD dataset respectively.
Authors: Chao Ni, Liyu Shen, Xiaodan Xu, Xin Yin, Shaohua Wang
Abstract: Though many deep learning-based models have made great progress in vulnerability detection, we have no good understanding of these models, which limits the further advancement of model capability, understanding of the mechanism of model detection, and efficiency and safety of practical application of models. In this paper, we extensively and comprehensively investigate two types of state-of-the-art learning-based approaches (sequence-based and graph-based) by conducting experiments on a recently built large-scale dataset. We investigate seven research questions from five dimensions, namely model capabilities, model interpretation, model stability, ease of use of model, and model economy. We experimentally demonstrate the priority of sequence-based models and the limited abilities of both LLM (ChatGPT) and graph-based models. We explore the types of vulnerability that learning-based models skilled in and reveal the instability of the models though the input is subtlely semantical-equivalently changed. We empirically explain what the models have learned. We summarize the pre-processing as well as requirements for easily using the models. Finally, we initially induce the vital information for economically and safely practical usage of these models.
Authors: Seungjun Han, Wongyung Choi
Abstract: Emergency department (ED) overcrowding and the complexity of rapid decision-making in critical care settings pose significant challenges to healthcare systems worldwide. While clinical decision support systems (CDSS) have shown promise, the integration of large language models (LLMs) offers new possibilities for enhancing triage accuracy and clinical decision-making. This study presents an LLM-driven CDSS designed to assist ED physicians and nurses in patient triage, treatment planning, and overall emergency care management. We developed a multi-agent CDSS utilizing Llama-3-70b as the base LLM, orchestrated by CrewAI and Langchain. The system comprises four AI agents emulating key ED roles: Triage Nurse, Emergency Physician, Pharmacist, and ED Coordinator. It incorporates the Korean Triage and Acuity Scale (KTAS) for triage assessment and integrates with the RxNorm API for medication management. The model was evaluated using the Asclepius dataset, with performance assessed by a clinical emergency medicine specialist. The CDSS demonstrated high accuracy in triage decision-making compared to the baseline of a single-agent system. Furthermore, the system exhibited strong performance in critical areas, including primary diagnosis, critical findings identification, disposition decision-making, treatment planning, and resource allocation. Our multi-agent CDSS demonstrates significant potential for supporting comprehensive emergency care management. By leveraging state-of-the-art AI technologies, this system offers a scalable and adaptable tool that could enhance emergency medical care delivery, potentially alleviating ED overcrowding and improving patient outcomes. This work contributes to the growing field of AI applications in emergency medicine and offers a promising direction for future research and clinical implementation.
Authors: Simon Kloker, Herbertson Bukoli, Twaha Kateete
Abstract: Introduction: Poor educational quality in Secondary Schools is still regarded as one of the major struggles in 21st century Uganda - especially in rural areas. Research identifies several problems, including low quality or absent teacher lesson planning. As the government pushes towards the implementation of a new curriculum, exiting lesson plans become obsolete and the problem is worsened. Using a Retrieval Augmented Generation approach, we developed a prototype that generates customized lesson plans based on the government-accredited textbooks. This helps teachers create lesson plans more efficiently and with better quality, ensuring they are fully aligned the new curriculum and the competence-based learning approach. Methods: The prototype was created using Cohere LLM and Sentence Embeddings, and LangChain Framework - and thereafter made available on a public website. Vector stores were trained for three new curriculum textbooks (ICT, Mathematics, History), all at Secondary 1 Level. Twenty-four lessons plans were generated following a pseudo-random generation protocol, based on the suggested periods in the textbooks. The lesson plans were analyzed regarding their technical quality by three independent raters following the Lesson Plan Analysis Protocol (LPAP) by Ndihokubwayo et al. (2022) that is specifically designed for East Africa and competence-based curriculums. Results: Evaluation of 24 lesson plans using the LPAP resulted in an average quality of between 75 and 80%, corresponding to "very good lesson plan". None of the lesson plans scored below 65%, although one lesson plan could be argued to have been missing the topic. In conclusion, the quality of the generated lesson plans is at least comparable, if not better, than those created by humans, as demonstrated in a study in Rwanda, whereby no lesson plan even reached the benchmark of 50%.
Authors: Sang-Hoon Lee, Ha-Yeong Choi, Seong-Whan Lee
Abstract: Recently, universal waveform generation tasks have been investigated conditioned on various out-of-distribution scenarios. Although GAN-based methods have shown their strength in fast waveform generation, they are vulnerable to train-inference mismatch scenarios such as two-stage text-to-speech. Meanwhile, diffusion-based models have shown their powerful generative performance in other domains; however, they stay out of the limelight due to slow inference speed in waveform generation tasks. Above all, there is no generator architecture that can explicitly disentangle the natural periodic features of high-resolution waveform signals. In this paper, we propose PeriodWave, a novel universal waveform generation model. First, we introduce a period-aware flow matching estimator that can capture the periodic features of the waveform signal when estimating the vector fields. Additionally, we utilize a multi-period estimator that avoids overlaps to capture different periodic features of waveform signals. Although increasing the number of periods can improve the performance significantly, this requires more computational costs. To reduce this issue, we also propose a single period-conditional universal estimator that can feed-forward parallel by period-wise batch inference. Additionally, we utilize discrete wavelet transform to losslessly disentangle the frequency information of waveform signals for high-frequency modeling, and introduce FreeU to reduce the high-frequency noise for waveform generation. The experimental results demonstrated that our model outperforms the previous models both in Mel-spectrogram reconstruction and text-to-speech tasks. All source code will be available at \url{https://github.com/sh-lee-prml/PeriodWave}.
Authors: Francesco Villani, Dario Lazzaro, Antonio Emanuele Cin\`a, Matteo Dell'Amico, Battista Biggio, Fabio Roli
Abstract: Data poisoning attacks on clustering algorithms have received limited attention, with existing methods struggling to scale efficiently as dataset sizes and feature counts increase. These attacks typically require re-clustering the entire dataset multiple times to generate predictions and assess the attacker's objectives, significantly hindering their scalability. This paper addresses these limitations by proposing Sonic, a novel genetic data poisoning attack that leverages incremental and scalable clustering algorithms, e.g., FISHDBC, as surrogates to accelerate poisoning attacks against graph-based and density-based clustering methods, such as HDBSCAN. We empirically demonstrate the effectiveness and efficiency of Sonic in poisoning the target clustering algorithms. We then conduct a comprehensive analysis of the factors affecting the scalability and transferability of poisoning attacks against clustering algorithms, and we conclude by examining the robustness of hyperparameters in our attack strategy Sonic.
Authors: Xin Gao, Xueyuan Li, Hao Liu, Ao Li, Zhaoyang Ma, Zirui Li
Abstract: Platooning technology is renowned for its precise vehicle control, traffic flow optimization, and energy efficiency enhancement. However, in large-scale mixed platoons, vehicle heterogeneity and unpredictable traffic conditions lead to virtual bottlenecks. These bottlenecks result in reduced traffic throughput and increased energy consumption within the platoon. To address these challenges, we introduce a decision-making strategy based on nested graph reinforcement learning. This strategy improves collaborative decision-making, ensuring energy efficiency and alleviating congestion. We propose a theory of nested traffic graph representation that maps dynamic interactions between vehicles and platoons in non-Euclidean spaces. By incorporating spatio-temporal weighted graph into a multi-head attention mechanism, we further enhance the model's capacity to process both local and global data. Additionally, we have developed a nested graph reinforcement learning framework to enhance the self-iterative learning capabilities of platooning. Using the I-24 dataset, we designed and conducted comparative algorithm experiments, generalizability testing, and permeability ablation experiments, thereby validating the proposed strategy's effectiveness. Compared to the baseline, our strategy increases throughput by 10% and decreases energy use by 9%. Specifically, increasing the penetration rate of CAVs significantly enhances traffic throughput, though it also increases energy consumption.
Authors: Jade Preston, William Basener
Abstract: Hyperspectral unmixing is the process of determining the presence of individual materials and their respective abundances from an observed pixel spectrum. Unmixing is a fundamental process in hyperspectral image analysis, and is growing in importance as increasingly large spectral libraries are created and used. Unmixing is typically done with ordinary least squares (OLS) regression. However, unmixing with large spectral libraries where the materials present in a pixel are not a priori known, solving for the coefficients in OLS requires inverting a non-invertible matrix from a large spectral library. A number of regression methods are available that can produce a numerical solution using regularization, but with considerably varied effectiveness. Also, simple methods that are unpopular in the statistics literature (i.e. step-wise regression) are used with some level of effectiveness in hyperspectral analysis. In this paper, we provide a thorough performance evaluation of the methods considered, evaluating methods based on how often they select the correct materials in the models. Investigated methods include ordinary least squares regression, non-negative least squares regression, ridge regression, lasso regression, step-wise regression and Bayesian model averaging. We evaluated these unmixing approaches using multiple criteria: incorporation of non-negative abundances, model size, accurate mineral detection and root mean squared error (RMSE). We provide a taxonomy of the regression methods, showing that most methods can be understood as Bayesian methods with specific priors. We conclude that methods that can be derived with priors that correspond to the phenomenology of hyperspectral imagery outperform those with priors that are optimal for prediction performance under the assumptions of ordinary least squares linear regression.
Authors: Guiomar Pescador-Barrios, Sarah Filippi, Mark van der Wilk
Abstract: For many machine learning methods, creating a model requires setting a parameter that controls the model's capacity before training, e.g.~number of neurons in DNNs, or inducing points in GPs. Increasing capacity improves performance until all the information from the dataset is captured. After this point, computational cost keeps increasing, without improved performance. This leads to the question ``How big is big enough?'' We investigate this problem for Gaussian processes (single-layer neural networks) in continual learning. Here, data becomes available incrementally, and the final dataset size will therefore not be known before training, preventing the use of heuristics for setting the model size. We provide a method that automatically adjusts this, while maintaining near-optimal performance, and show that a single hyperparameter setting for our method performs well across datasets with a wide range of properties.
Authors: Hui Fang, Xu Feng, Lu Qin, Zhu Sun
Abstract: The widespread use of the internet has led to an overwhelming amount of data, which has resulted in the problem of information overload. Recommender systems have emerged as a solution to this problem by providing personalized recommendations to users based on their preferences and historical data. However, as recommendation models become increasingly complex, finding the best hyperparameter combination for different models has become a challenge. The high-dimensional hyperparameter search space poses numerous challenges for researchers, and failure to disclose hyperparameter settings may impede the reproducibility of research results. In this paper, we investigate the Top-N implicit recommendation problem and focus on optimizing the benchmark recommendation algorithm commonly used in comparative experiments using hyperparameter optimization algorithms. We propose a research methodology that follows the principles of a fair comparison, employing seven types of hyperparameter search algorithms to fine-tune six common recommendation algorithms on three datasets. We have identified the most suitable hyperparameter search algorithms for various recommendation algorithms on different types of datasets as a reference for later study. This study contributes to algorithmic research in recommender systems based on hyperparameter optimization, providing a fair basis for comparison.
Authors: Bing Hu, Anita Layton, Helen Chen
Abstract: Artificial intelligence (AI) is increasingly used in every stage of drug development. One challenge facing drug discovery AI is that drug pharmacokinetic (PK) datasets are often collected independently from each other, often with limited overlap, creating data overlap sparsity. Data sparsity makes data curation difficult for researchers looking to answer research questions in poly-pharmacy, drug combination research, and high-throughput screening. We propose Imagand, a novel SMILES-to-Pharmacokinetic (S2PK) diffusion model capable of generating an array of PK target properties conditioned on SMILES inputs. We show that Imagand-generated synthetic PK data closely resembles real data univariate and bivariate distributions, and improves performance for downstream tasks. Imagand is a promising solution for data overlap sparsity and allows researchers to efficiently generate ligand PK data for drug discovery research. Code is available at \url{https://github.com/bing1100/Imagand}.
Authors: Jianye Xu, Pan Hu, Bassam Alrifaee
Abstract: This paper introduces an open-source, decentralized framework named SigmaRL, designed to enhance both sample efficiency and generalization of multi-agent Reinforcement Learning (RL) for motion planning of connected and automated vehicles. Most RL agents exhibit a limited capacity to generalize, often focusing narrowly on specific scenarios, and are usually evaluated in similar or even the same scenarios seen during training. Various methods have been proposed to address these challenges, including experience replay and regularization. However, how observation design in RL affects sample efficiency and generalization remains an under-explored area. We address this gap by proposing five strategies to design information-dense observations, focusing on general features that are applicable to most traffic scenarios. We train our RL agents using these strategies on an intersection and evaluate their generalization through numerical experiments across completely unseen traffic scenarios, including a new intersection, an on-ramp, and a roundabout. Incorporating these information-dense observations reduces training times to under one hour on a single CPU, and the evaluation results reveal that our RL agents can effectively zero-shot generalize. Code: github.com/cas-lab-munich/SigmaRL
Authors: Dong Neuck Lee, Michael R. Kosorok
Abstract: Conventional off-policy reinforcement learning (RL) focuses on maximizing the expected return of scalar rewards. Distributional RL (DRL), in contrast, studies the distribution of returns with the distributional Bellman operator in a Euclidean space, leading to highly flexible choices for utility. This paper establishes robust theoretical foundations for DRL. We prove the contraction property of the Bellman operator even when the reward space is an infinite-dimensional separable Banach space. Furthermore, we demonstrate that the behavior of high- or infinite-dimensional returns can be effectively approximated using a lower-dimensional Euclidean space. Leveraging these theoretical insights, we propose a novel DRL algorithm that tackles problems which have been previously intractable using conventional reinforcement learning approaches.
Authors: Marius Aasan, Odd Kolbj{\o}rnsen, Anne Schistad Solberg, Ad\'in Ramirez Rivera
Abstract: Vision Transformer (ViT) architectures traditionally employ a grid-based approach to tokenization independent of the semantic content of an image. We propose a modular superpixel tokenization strategy which decouples tokenization and feature extraction; a shift from contemporary approaches where these are treated as an undifferentiated whole. Using on-line content-aware tokenization and scale- and shape-invariant positional embeddings, we perform experiments and ablations that contrast our approach with patch-based tokenization and randomized partitions as baselines. We show that our method significantly improves the faithfulness of attributions, gives pixel-level granularity on zero-shot unsupervised dense prediction tasks, while maintaining predictive performance in classification tasks. Our approach provides a modular tokenization framework commensurable with standard architectures, extending the space of ViTs to a larger class of semantically-rich models.
Authors: Ronghao Lin, Ying Zeng, Sijie Mai, Haifeng Hu
Abstract: In the pathway toward Artificial General Intelligence (AGI), understanding human's affection is essential to enhance machine's cognition abilities. For achieving more sensual human-AI interaction, Multimodal Affective Computing (MAC) in human-spoken videos has attracted increasing attention. However, previous methods are mainly devoted to designing multimodal fusion algorithms, suffering from two issues: semantic imbalance caused by diverse pre-processing operations and semantic mismatch raised by inconsistent affection content contained in different modalities comparing with the multimodal ground truth. Besides, the usage of manual features extractors make they fail in building end-to-end pipeline for multiple MAC downstream tasks. To address above challenges, we propose a novel end-to-end framework named SemanticMAC to compute multimodal semantic-centric affection for human-spoken videos. We firstly employ pre-trained Transformer model in multimodal data pre-processing and design Affective Perceiver module to capture unimodal affective information. Moreover, we present a semantic-centric approach to unify multimodal representation learning in three ways, including gated feature interaction, multi-task pseudo label generation, and intra-/inter-sample contrastive learning. Finally, SemanticMAC effectively learn specific- and shared-semantic representations in the guidance of semantic-centric labels. Extensive experimental results demonstrate that our approach surpass the state-of-the-art methods on 7 public datasets in four MAC downstream tasks.
Authors: Ding Liu, Jiaqi Yao, Zekun Yao, Quan Zhang
Abstract: Tensor networks (TN) have found a wide use in machine learning, and in particular, TN and deep learning bear striking similarities. In this work, we propose the quantum-classical hybrid tensor networks (HTN) which combine tensor networks with classical neural networks in a uniform deep learning framework to overcome the limitations of regular tensor networks in machine learning. We first analyze the limitations of regular tensor networks in the applications of machine learning involving the representation power and architecture scalability. We conclude that in fact the regular tensor networks are not competent to be the basic building blocks of deep learning. Then, we discuss the performance of HTN which overcome all the deficiency of regular tensor networks for machine learning. In this sense, we are able to train HTN in the deep learning way which is the standard combination of algorithms such as Back Propagation and Stochastic Gradient Descent. We finally provide two applicable cases to show the potential applications of HTN, including quantum states classification and quantum-classical autoencoder. These cases also demonstrate the great potentiality to design various HTN in deep learning way.
Authors: Kiran Purohit, Soumi Das, Sourangshu Bhattacharya, Santu Rana
Abstract: Federated Learning systems are increasingly subjected to a multitude of model poisoning attacks from clients. Among these, edge-case attacks that target a small fraction of the input space are nearly impossible to detect using existing defenses, leading to a high attack success rate. We propose an effective defense using an external defense dataset, which provides information about the attack target. The defense dataset contains a mix of poisoned and clean examples, with only a few known to be clean. The proposed method, DataDefense, uses this dataset to learn a poisoned data detector model which marks each example in the defense dataset as poisoned or clean. It also learns a client importance model that estimates the probability of a client update being malicious. The global model is then updated as a weighted average of the client models' updates. The poisoned data detector and the client importance model parameters are updated using an alternating minimization strategy over the Federated Learning rounds. Extensive experiments on standard attack scenarios demonstrate that DataDefense can defend against model poisoning attacks where other state-of-the-art defenses fail. In particular, DataDefense is able to reduce the attack success rate by at least ~ 40% on standard attack setups and by more than 80% on some setups. Furthermore, DataDefense requires very few defense examples (as few as five) to achieve a near-optimal reduction in attack success rate.
Authors: Sami Jullien, Romain Deffayet, Jean-Michel Renders, Paul Groth, Maarten de Rijke
Abstract: Distributional reinforcement learning (RL) has proven useful in multiple benchmarks as it enables approximating the full distribution of returns and makes a better use of environment samples. The commonly used quantile regression approach to distributional RL -- based on asymmetric $L_1$ losses -- provides a flexible and effective way of learning arbitrary return distributions. In practice, it is often improved by using a more efficient, hybrid asymmetric $L_1$-$L_2$ Huber loss for quantile regression. However, by doing so, distributional estimation guarantees vanish, and we empirically observe that the estimated distribution rapidly collapses to its mean. Indeed, asymmetric $L_2$ losses, corresponding to expectile regression, cannot be readily used for distributional temporal difference learning. Motivated by the efficiency of $L_2$-based learning, we propose to jointly learn expectiles and quantiles of the return distribution in a way that allows efficient learning while keeping an estimate of the full distribution of returns. We prove that our approach approximately learns the correct return distribution, and we benchmark a practical implementation on a toy example and at scale. On the Atari benchmark, our approach matches the performance of the Huber-based IQN-1 baseline after $200$M training frames but avoids distributional collapse and keeps estimates of the full distribution of returns.
Authors: Ao Liu, Wenshan Li, Tao Li, Beibei Li, Guangquan Xu, Pan Zhou, Wengang Ma, Hanyuan Huang
Abstract: End-to-end training with global optimization have popularized graph neural networks (GNNs) for node classification, yet inadvertently introduced vulnerabilities to adversarial edge-perturbing attacks. Adversaries can exploit the inherent opened interfaces of GNNs' input and output, perturbing critical edges and thus manipulating the classification results. Current defenses, due to their persistent utilization of global-optimization-based end-to-end training schemes, inherently encapsulate the vulnerabilities of GNNs. This is specifically evidenced in their inability to defend against targeted secondary attacks. In this paper, we propose the Graph Agent Network (GAgN) to address the aforementioned vulnerabilities of GNNs. GAgN is a graph-structured agent network in which each node is designed as an 1-hop-view agent. Through the decentralized interactions between agents, they can learn to infer global perceptions to perform tasks including inferring embeddings, degrees and neighbor relationships for given nodes. This empowers nodes to filtering adversarial edges while carrying out classification tasks. Furthermore, agents' limited view prevents malicious messages from propagating globally in GAgN, thereby resisting global-optimization-based secondary attacks. We prove that single-hidden-layer multilayer perceptrons (MLPs) are theoretically sufficient to achieve these functionalities. Experimental results show that GAgN effectively implements all its intended capabilities and, compared to state-of-the-art defenses, achieves optimal classification accuracy on the perturbed datasets.
Authors: Paolo Climaco, Jochen Garcke
Abstract: For regression tasks one often leverages large datasets for training predictive machine learning models. However, using large datasets may not be feasible due to computational limitations or high data labelling costs. Therefore, suitably selecting small training sets from large pools of unlabelled data points is essential to maximize model performance while maintaining efficiency. In this work, we study Farthest Point Sampling (FPS), a data selection approach that aims to minimize the fill distance of the selected set. We derive an upper bound for the maximum expected prediction error, conditional to the location of the unlabelled data points, that linearly depends on the training set fill distance. For empirical validation, we perform experiments using two regression models on three datasets. We empirically show that selecting a training set by aiming to minimize the fill distance, thereby minimizing our derived bound, significantly reduces the maximum prediction error of various regression models, outperforming alternative sampling approaches by a large margin. Furthermore, we show that selecting training sets with the FPS can also increase model stability for the specific case of Gaussian kernel regression approaches.
Authors: Chester Holtz, Pengwen Chen, Alexander Cloninger, Chung-Kuan Cheng, Gal Mishne
Abstract: Motivated by the need to address the degeneracy of canonical Laplace learning algorithms in low label rates, we propose to reformulate graph-based semi-supervised learning as a nonconvex generalization of a \emph{Trust-Region Subproblem} (TRS). This reformulation is motivated by the well-posedness of Laplacian eigenvectors in the limit of infinite unlabeled data. To solve this problem, we first show that a first-order condition implies the solution of a manifold alignment problem and that solutions to the classical \emph{Orthogonal Procrustes} problem can be used to efficiently find good classifiers that are amenable to further refinement. To tackle refinement, we develop the framework of Sequential Subspace Optimization for graph-based SSL. Next, we address the criticality of selecting supervised samples at low-label rates. We characterize informative samples with a novel measure of centrality derived from the principal eigenvectors of a certain submatrix of the graph Laplacian. We demonstrate that our framework achieves lower classification error compared to recent state-of-the-art and classical semi-supervised learning methods at extremely low, medium, and high label rates.
Authors: Jared D. Willard, Charuleka Varadharajan, Xiaowei Jia, Vipin Kumar
Abstract: Prediction of dynamic environmental variables in unmonitored sites remains a long-standing challenge for water resources science. The majority of the world's freshwater resources have inadequate monitoring of critical environmental variables needed for management. Yet, the need to have widespread predictions of hydrological variables such as river flow and water quality has become increasingly urgent due to climate and land use change over the past decades, and their associated impacts on water resources. Modern machine learning methods increasingly outperform their process-based and empirical model counterparts for hydrologic time series prediction with their ability to extract information from large, diverse data sets. We review relevant state-of-the art applications of machine learning for streamflow, water quality, and other water resources prediction and discuss opportunities to improve the use of machine learning with emerging methods for incorporating watershed characteristics into deep learning models, transfer learning, and incorporating process knowledge into machine learning models. The analysis here suggests most prior efforts have been focused on deep learning learning frameworks built on many sites for predictions at daily time scales in the United States, but that comparisons between different classes of machine learning methods are few and inadequate. We identify several open questions for time series predictions in unmonitored sites that include incorporating dynamic inputs and site characteristics, mechanistic understanding and spatial context, and explainable AI techniques in modern machine learning frameworks.
Authors: Jae-Won Chung, Yile Gu, Insu Jang, Luoxi Meng, Nikhil Bansal, Mosharaf Chowdhury
Abstract: Training large AI models on numerous GPUs consumes a massive amount of energy, making power delivery one of the largest limiting factors in building and operating datacenters for AI workloads. However, we observe that not all energy consumed during training directly contributes to end-to-end throughput, and a significant portion can be removed without slowing down training, which we call energy bloat. In this work, we identify two independent sources of energy bloat in large model training and propose Perseus, a training system that mitigates both. To do this, Perseus obtains the "iteration time-energy" Pareto frontier of any large model training job using an efficient graph cut-based algorithm and schedules the energy consumption of computations across time to remove both types of energy bloat. Evaluation on large models including GPT-3 and Bloom shows that Perseus reduces the energy consumption of large model training by up to 30% without any throughput loss or hardware modification, enabling energy reduction -- and therefore cost savings -- otherwise unattainable before.
Authors: Huizhen Yu, Yi Wan, Richard S. Sutton
Abstract: In this paper, we study asynchronous stochastic approximation algorithms without communication delays. Our main contribution is a stability proof for these algorithms that extends a method of Borkar and Meyn by accommodating more general noise conditions. We also derive convergence results from this stability result and discuss their application in important average-reward reinforcement learning problems.
Authors: Ho Fung Tsoi, Vladimir Loncar, Sridhara Dasu, Philip Harris
Abstract: Contrary to genetic programming, the neural network approach to symbolic regression can efficiently handle high-dimensional inputs and leverage gradient methods for faster equation searching. Common ways of constraining expression complexity often involve multistage pruning with fine-tuning, which can result in significant performance loss. In this work, we propose $\tt{SymbolNet}$, a neural network approach to symbolic regression in a novel framework that allows dynamic pruning of model weights, input features, and mathematical operators in a single training process, where both training loss and expression complexity are optimized simultaneously. We introduce a sparsity regularization term for each pruning type, which can adaptively adjust its strength, leading to convergence at a target sparsity ratio. Unlike most existing symbolic regression methods that struggle with datasets containing more than $\mathcal{O}(10)$ inputs, we demonstrate the effectiveness of our model on the LHC jet tagging task (16 inputs), MNIST (784 inputs), and SVHN (3072 inputs). Our approach enables symbolic regression to achieve fast inference with nanosecond-scale latency on FPGAs for high-dimensional datasets in environments with stringent computational resource constraints, such as the high-energy physics experiments at the LHC.
Authors: Yasser H. Khalil, Amir H. Estiri, Mahdi Beitollahi, Nader Asadi, Sobhan Hemati, Xu Li, Guojun Zhang, Xi Chen
Abstract: In the realm of real-world devices, centralized servers in Federated Learning (FL) present challenges including communication bottlenecks and susceptibility to a single point of failure. Additionally, contemporary devices inherently exhibit model and data heterogeneity. Existing work lacks a Decentralized FL (DFL) framework capable of accommodating such heterogeneity without imposing architectural restrictions or assuming the availability of public data. To address these issues, we propose a Decentralized Federated Mutual Learning (DFML) framework that is serverless, supports nonrestrictive heterogeneous models, and avoids reliance on public data. DFML effectively handles model and data heterogeneity through mutual learning, which distills knowledge between clients, and cyclically varying the amount of supervision and distillation signals. Extensive experimental results demonstrate consistent effectiveness of DFML in both convergence speed and global accuracy, outperforming prevalent baselines under various conditions. For example, with the CIFAR-100 dataset and 50 clients, DFML achieves a substantial increase of +17.20% and +19.95% in global accuracy under Independent and Identically Distributed (IID) and non-IID data shifts, respectively.
Authors: Xueqing Liu, Kyra Gan, Esmaeil Keyvanshokooh, Susan Murphy
Abstract: Motivated by applications in digital health, this work studies the novel problem of online uniform allocation (OUA), where the goal is to distribute a budget uniformly across unknown decision times. In the OUA problem, the algorithm is given a budget $b$ and a time horizon $T$, and an adversary then chooses a value $\tau^* \in [b,T]$, which is revealed to the algorithm online. At each decision time $i \in [\tau^*]$, the algorithm must determine a probability that maximizes the budget spent throughout the horizon, respecting budget constraint $b$, while achieving as uniform a distribution as possible over $\tau^*$. We present the first randomized algorithm designed for this problem and subsequently extend it to incorporate learning augmentation. We provide worst-case approximation guarantees for both algorithms, and illustrate the utility of the algorithms through both synthetic experiments and a real-world case study involving the HeartSteps mobile application. Our numerical results show strong empirical average performance of our proposed randomized algorithms against previously proposed heuristic solutions.
Authors: Arian Hosseini, Xingdi Yuan, Nikolay Malkin, Aaron Courville, Alessandro Sordoni, Rishabh Agarwal
Abstract: Common self-improvement approaches for large language models (LLMs), such as STaR, iteratively fine-tune LLMs on self-generated solutions to improve their problem-solving ability. However, these approaches discard the large amounts of incorrect solutions generated during this process, potentially neglecting valuable information in such solutions. To address this shortcoming, we propose V-STaR that utilizes both the correct and incorrect solutions generated during the self-improvement process to train a verifier using DPO that judges correctness of model-generated solutions. This verifier is used at inference time to select one solution among many candidate solutions. Running V-STaR for multiple iterations results in progressively better reasoners and verifiers, delivering a 4% to 17% test accuracy improvement over existing self-improvement and verification approaches on common code generation and math reasoning benchmarks with LLaMA2 models.
Authors: Shayan Shirahmad Gale Bagi, Zahra Gharaee, Oliver Schulte, Mark Crowley
Abstract: Learning causal representations from observational and interventional data in the absence of known ground-truth graph structures necessitates implicit latent causal representation learning. Implicit learning of causal mechanisms typically involves two categories of interventional data: hard and soft interventions. In real-world scenarios, soft interventions are often more realistic than hard interventions, as the latter require fully controlled environments. Unlike hard interventions, which directly force changes in a causal variable, soft interventions exert influence indirectly by affecting the causal mechanism. However, the subtlety of soft interventions impose several challenges for learning causal models. One challenge is that soft intervention's effects are ambiguous, since parental relations remain intact. In this paper, we tackle the challenges of learning causal models using soft interventions while retaining implicit modelling. We propose ICLR-SM, which models the effects of soft interventions by employing a causal mechanism switch variable designed to toggle between different causal mechanisms. In our experiments, we consistently observe improved learning of identifiable, causal representations, compared to baseline approaches.
Authors: Hongjoon Ahn, Jinu Hyeon, Youngmin Oh, Bosun Hwang, Taesup Moon
Abstract: We argue that the negative transfer problem occurring when the new task to learn arrives is an important problem that needs not be overlooked when developing effective Continual Reinforcement Learning (CRL) algorithms. Through comprehensive experimental validation, we demonstrate that such issue frequently exists in CRL and cannot be effectively addressed by several recent work on mitigating plasticity loss of RL agents. To that end, we develop Reset & Distill (R&D), a simple yet highly effective method, to overcome the negative transfer problem in CRL. R&D combines a strategy of resetting the agent's online actor and critic networks to learn a new task and an offline learning step for distilling the knowledge from the online actor and previous expert's action probabilities. We carried out extensive experiments on long sequence of Meta World tasks and show that our method consistently outperforms recent baselines, achieving significantly higher success rates across a range of tasks. Our findings highlight the importance of considering negative transfer in CRL and emphasize the need for robust strategies like R&D to mitigate its detrimental effects.
Authors: Zhaoliang Chen, Zhihao Wu, Ylli Sadikaj, Claudia Plant, Hong-Ning Dai, Shiping Wang, Yiu-Ming Cheung, Wenzhong Guo
Abstract: Although Graph Neural Networks (GNNs) have exhibited the powerful ability to gather graph-structured information from neighborhood nodes via various message-passing mechanisms, the performance of GNNs is limited by poor generalization and fragile robustness caused by noisy and redundant graph data. As a prominent solution, Graph Augmentation Learning (GAL) has recently received increasing attention. Among prior GAL approaches, edge-dropping methods that randomly remove edges from a graph during training are effective techniques to improve the robustness of GNNs. However, randomly dropping edges often results in bypassing critical edges, consequently weakening the effectiveness of message passing. In this paper, we propose a novel adversarial edge-dropping method (ADEdgeDrop) that leverages an adversarial edge predictor guiding the removal of edges, which can be flexibly incorporated into diverse GNN backbones. Employing an adversarial training framework, the edge predictor utilizes the line graph transformed from the original graph to estimate the edges to be dropped, which improves the interpretability of the edge-dropping method. The proposed ADEdgeDrop is optimized alternately by stochastic gradient descent and projected gradient descent. Comprehensive experiments on six graph benchmark datasets demonstrate that the proposed ADEdgeDrop outperforms state-of-the-art baselines across various GNN backbones, demonstrating improved generalization and robustness.
Authors: Shashank Gupta, Olivier Jeunen, Harrie Oosterhuis, Maarten de Rijke
Abstract: The off-policy learning paradigm allows for recommender systems and general ranking applications to be framed as decision-making problems, where we aim to learn decision policies that optimize an unbiased offline estimate of an online reward metric. With unbiasedness comes potentially high variance, and prevalent methods exist to reduce estimation variance. These methods typically make use of control variates, either additive (i.e., baseline corrections or doubly robust methods) or multiplicative (i.e., self-normalisation). Our work unifies these approaches by proposing a single framework built on their equivalence in learning scenarios. The foundation of our framework is the derivation of an equivalent baseline correction for all of the existing control variates. Consequently, our framework enables us to characterize the variance-optimal unbiased estimator and provide a closed-form solution for it. This optimal estimator brings significantly improved performance in both evaluation and learning, and minimizes data requirements. Empirical observations corroborate our theoretical findings.
Authors: Jessica N. Howard, Ro Jefferson, Anindita Maiti, Zohar Ringel
Abstract: Separating relevant and irrelevant information is key to any modeling process or scientific inquiry. Theoretical physics offers a powerful tool for achieving this in the form of the renormalization group (RG). Here we demonstrate a practical approach to performing Wilsonian RG in the context of Gaussian Process (GP) Regression. We systematically integrate out the unlearnable modes of the GP kernel, thereby obtaining an RG flow of the GP in which the data sets the IR scale. In simple cases, this results in a universal flow of the ridge parameter, which becomes input-dependent in the richer scenario in which non-Gaussianities are included. In addition to being analytically tractable, this approach goes beyond structural analogies between RG and neural networks by providing a natural connection between RG flow and learnable vs. unlearnable modes. Studying such flows may improve our understanding of feature learning in deep neural networks, and enable us to identify potential universality classes in these models.
Authors: Ke Liu, Fan Hu, Hui Lin, Xi Cheng, Jianan Chen, Jilin Song, Siyuan Feng, Gaofeng Su, Chen Zhu
Abstract: This paper explores the optimization of Ground Delay Programs (GDP), a prevalent Traffic Management Initiative used in Air Traffic Management (ATM) to reconcile capacity and demand discrepancies at airports. Employing Reinforcement Learning (RL) to manage the inherent uncertainties in the national airspace system-such as weather variability, fluctuating flight demands, and airport arrival rates-we developed two RL models: Behavioral Cloning (BC) and Conservative Q-Learning (CQL). These models are designed to enhance GDP efficiency by utilizing a sophisticated reward function that integrates ground and airborne delays and terminal area congestion. We constructed a simulated single-airport environment, SAGDP_ENV, which incorporates real operational data along with predicted uncertainties to facilitate realistic decision-making scenarios. Utilizing the whole year 2019 data from Newark Liberty International Airport (EWR), our models aimed to preemptively set airport program rates. Despite thorough modeling and simulation, initial outcomes indicated that the models struggled to learn effectively, attributed potentially to oversimplified environmental assumptions. This paper discusses the challenges encountered, evaluates the models' performance against actual operational data, and outlines future directions to refine RL applications in ATM.
Authors: Sungchul Hong, Seunghwan An, Jong-June Jeon
Abstract: Recent advances in a generative neural network model extend the development of data augmentation methods. However, the augmentation methods based on the modern generative models fail to achieve notable performance for class imbalance data compared to the conventional model, Synthetic Minority Oversampling Technique (SMOTE). We investigate the problem of the generative model for imbalanced classification and introduce a framework to enhance the SMOTE algorithm using Variational Autoencoders (VAE). Our approach systematically quantifies the density of data points in a low-dimensional latent space using the VAE, simultaneously incorporating information on class labels and classification difficulty. Then, the data points potentially degrading the augmentation are systematically excluded, and the neighboring observations are directly augmented on the data space. Empirical studies on several imbalanced datasets represent that this simple process innovatively improves the conventional SMOTE algorithm over the deep learning models. Consequently, we conclude that the selection of minority data and the interpolation in the data space are beneficial for imbalanced classification problems with a relatively small number of data points.
Authors: Micha{\l} Zawalski, Gracjan G\'oral, Micha{\l} Tyrolski, Emilia Wi\'snios, Franciszek Budrowski, {\L}ukasz Kuci\'nski, Piotr Mi{\l}o\'s
Abstract: Efficiently tackling combinatorial reasoning problems, particularly the notorious NP-hard tasks, remains a significant challenge for AI research. Recent efforts have sought to enhance planning by incorporating hierarchical high-level search strategies, known as subgoal methods. While promising, their performance against traditional low-level planners is inconsistent, raising questions about their application contexts. In this study, we conduct an in-depth exploration of subgoal-planning methods for combinatorial reasoning. We identify the attributes pivotal for leveraging the advantages of high-level search: hard-to-learn value functions, complex action spaces, presence of dead ends in the environment, or using data collected from diverse experts. We propose a consistent evaluation methodology to achieve meaningful comparisons between methods and reevaluate the state-of-the-art algorithms.
Authors: Lars Veefkind, Gabriele Cesa
Abstract: Steerable convolutional neural networks (SCNNs) enhance task performance by modelling geometric symmetries through equivariance constraints on weights. Yet, unknown or varying symmetries can lead to overconstrained weights and decreased performance. To address this, this paper introduces a probabilistic method to learn the degree of equivariance in SCNNs. We parameterise the degree of equivariance as a likelihood distribution over the transformation group using Fourier coefficients, offering the option to model layer-wise and shared equivariance. These likelihood distributions are regularised to ensure an interpretable degree of equivariance across the network. Advantages include the applicability to many types of equivariant networks through the flexible framework of SCNNs and the ability to learn equivariance with respect to any subgroup of any compact group without requiring additional layers. Our experiments reveal competitive performance on datasets with mixed symmetries, with learnt likelihood distributions that are representative of the underlying degree of equivariance.
Authors: Yuval Dagan, Constantinos Daskalakis, Maxwell Fishelson, Noah Golowich, Robert Kleinberg, Princewill Okoroafor
Abstract: A set of probabilistic forecasts is calibrated if each prediction of the forecaster closely approximates the empirical distribution of outcomes on the subset of timesteps where that prediction was made. We study the fundamental problem of online calibrated forecasting of binary sequences, which was initially studied by Foster & Vohra (1998). They derived an algorithm with $O(T^{2/3})$ calibration error after $T$ time steps, and showed a lower bound of $\Omega(T^{1/2})$. These bounds remained stagnant for two decades, until Qiao & Valiant (2021) improved the lower bound to $\Omega(T^{0.528})$ by introducing a combinatorial game called sign preservation and showing that lower bounds for this game imply lower bounds for calibration. In this paper, we give the first improvement to the $O(T^{2/3})$ upper bound on calibration error of Foster & Vohra. We do this by introducing a variant of Qiao & Valiant's game that we call sign preservation with reuse (SPR). We prove that the relationship between SPR and calibrated forecasting is bidirectional: not only do lower bounds for SPR translate into lower bounds for calibration, but algorithms for SPR also translate into new algorithms for calibrated forecasting. We then give an improved \emph{upper bound} for the SPR game, which implies, via our equivalence, a forecasting algorithm with calibration error $O(T^{2/3 - \varepsilon})$ for some $\varepsilon > 0$, improving Foster & Vohra's upper bound for the first time. Using similar ideas, we then prove a slightly stronger lower bound than that of Qiao & Valiant, namely $\Omega(T^{0.54389})$. Our lower bound is obtained by an oblivious adversary, marking the first $\omega(T^{1/2})$ calibration lower bound for oblivious adversaries.
Authors: Luoxiao Yang, Yun Wang, Xinqi Fan, Israel Cohen, Jingdong Chen, Yue Zhao, Zijun Zhang
Abstract: The success of large pretrained models in natural language processing (NLP) and computer vision (CV) has opened new avenues for constructing foundation models for time series forecasting (TSF). Traditional TSF foundation models rely heavily on numerical data fitting. In contrast, the human brain is inherently skilled at processing visual information, prefer predicting future trends by observing visualized sequences. From a biomimetic perspective, utilizing models to directly process numerical sequences might not be the most effective route to achieving Artificial General Intelligence (AGI). This paper proposes ViTime, a novel Visual Intelligence-based foundation model for TSF. ViTime overcomes the limitations of numerical time series data fitting by utilizing visual data processing paradigms and employs a innovative data synthesis method during training, called Real Time Series (RealTS). Experiments on a diverse set of previously unseen forecasting datasets demonstrate that ViTime achieves state-of-the-art zero-shot performance, even surpassing the best individually trained supervised models in some situations. These findings suggest that visual intelligence can significantly enhance time series analysis and forecasting, paving the way for more advanced and versatile models in the field. The code for our framework is accessible at https://github.com/IkeYang/ViTime.
Authors: Simone Fioravanti, Steve Hanneke, Shay Moran, Hilla Schefler, Iska Tsubari
Abstract: This work continues to investigate the link between differentially private (DP) and online learning. Alon, Livni, Malliaris, and Moran (2019) showed that for binary concept classes, DP learnability of a given class implies that it has a finite Littlestone dimension (equivalently, that it is online learnable). Their proof relies on a model-theoretic result by Hodges (1997), which demonstrates that any binary concept class with a large Littlestone dimension contains a large subclass of thresholds. In a follow-up work, Jung, Kim, and Tewari (2020) extended this proof to multiclass PAC learning with a bounded number of labels. Unfortunately, Hodges's result does not apply in other natural settings such as multiclass PAC learning with an unbounded label space, and PAC learning of partial concept classes. This naturally raises the question of whether DP learnability continues to imply online learnability in more general scenarios: indeed, Alon, Hanneke, Holzman, and Moran (2021) explicitly leave it as an open question in the context of partial concept classes, and the same question is open in the general multiclass setting. In this work, we give a positive answer to these questions showing that for general classification tasks, DP learnability implies online learnability. Our proof reasons directly about Littlestone trees, without relying on thresholds. We achieve this by establishing several Ramsey-type theorems for trees, which might be of independent interest.
Authors: Zhuoyuan Wang, Albert Chern, Yorie Nakahira
Abstract: Accurate estimate of long-term risk is critical for safe decision-making, but sampling from rare risk events and long-term trajectories can be prohibitively costly. Risk gradient can be used in many first-order techniques for learning and control methods, but gradient estimate is difficult to obtain using Monte Carlo (MC) methods because the infinitesimal divisor may significantly amplify sampling noise. Motivated by this gap, we propose an efficient method to evaluate long-term risk probabilities and their gradients using short-term samples without sufficient risk events. We first derive that four types of long-term risk probability are solutions of certain partial differential equations (PDEs). Then, we propose a physics-informed learning technique that integrates data and physics information (aforementioned PDEs). The physics information helps propagate information beyond available data and obtain provable generalization beyond available data, which in turn enables long-term risk to be estimated using short-term samples of safe events. Finally, we demonstrate in simulation that the proposed technique has improved sample efficiency, generalizes well to unseen regions, and adapts to changing system parameters.
Authors: Tigran Ramazyan, Mikhail Hushchyn, Denis Derkach
Abstract: We propose a new uncertainty estimator for gradient-free optimisation of black-box simulators using deep generative surrogate models. Optimisation of these simulators is especially challenging for stochastic simulators and higher dimensions. To address these issues, we utilise a deep generative surrogate approach to model the black box response for the entire parameter space. We then leverage this knowledge to estimate the proposed uncertainty based on the Wasserstein distance - the Wasserstein uncertainty. This approach is employed in a posterior agnostic gradient-free optimisation algorithm that minimises regret over the entire parameter space. A series of tests were conducted to demonstrate that our method is more robust to the shape of both the black box function and the stochastic response of the black box than state-of-the-art methods, such as efficient global optimisation with a deep Gaussian process surrogate.
Authors: Benedikt H\"oltgen, Robert C. Williamson
Abstract: Machine Learning research, as most of Statistics, heavily relies on the concept of a data-generating probability distribution. As data points are thought to be sampled from such a distribution, we can learn from observed data about this distribution and, thus, predict future data points drawn from it (with some probability of success). Drawing on scholarship across disciplines, we here argue that this framework is not always a good model. Not only do such true probability distributions not exist; the framework can also be misleading and obscure both the choices made and the goals pursued in machine learning practice. We suggest an alternative framework that focuses on finite populations rather than abstract distributions; while classical learning theory can be left almost unchanged, it opens new opportunities, especially to model sampling. We compile these considerations into five reasons for modelling machine learning -- in some settings -- with finite distributions rather than generative distributions, both to be more faithful to practice and to provide novel theoretical insights.
Authors: Maryam Abbasihafshejani, Anindya Maiti, Murtuza Jadliwala
Abstract: Federated machine learning enables model training across multiple clients while maintaining data privacy. Vertical Federated Learning (VFL) specifically deals with instances where the clients have different feature sets of the same samples. As federated learning models aim to improve efficiency and adaptability, innovative neural network architectures like Spiking Neural Networks (SNNs) are being leveraged to enable fast and accurate processing at the edge. SNNs, known for their efficiency over Artificial Neural Networks (ANNs), have not been analyzed for their applicability in VFL, thus far. In this paper, we investigate the benefits and trade-offs of using SNN models in a vertical federated learning setting. We implement two different federated learning architectures -- with model splitting and without model splitting -- that have different privacy and performance implications. We evaluate the setup using CIFAR-10 and CIFAR-100 benchmark datasets along with SNN implementations of VGG9 and ResNET classification models. Comparative evaluations demonstrate that the accuracy of SNN models is comparable to that of traditional ANNs for VFL applications, albeit significantly more energy efficient.
Authors: Abhinav Garg, Naman Shukla, Maarten Wormer
Abstract: Time series forecasting in the air cargo industry presents unique challenges due to volatile market dynamics and the significant impact of accurate forecasts on generated revenue. This paper explores a comprehensive approach to demand forecasting at the origin-destination (O\&D) level, focusing on the development and implementation of machine learning models in decision-making for the air cargo industry. We leverage a mixture of experts framework, combining statistical and advanced deep learning models to provide reliable forecasts for cargo demand over a six-month horizon. The results demonstrate that our approach outperforms industry benchmarks, offering actionable insights for cargo capacity allocation and strategic decision-making in the air cargo industry. While this work is applied in the airline industry, the methodology is broadly applicable to any field where forecast-based decision-making in a volatile environment is crucial.
Authors: Kaier Liang, Gustavo A. Cardona, Disha Kamale, Cristian-Ioan Vasile
Abstract: This paper presents a novel framework for inferring timed temporal logic properties from data. The dataset comprises pairs of finite-time system traces and corresponding labels, denoting whether the traces demonstrate specific desired behaviors, e.g. whether the ship follows a safe route or not. Our proposed approach leverages decision-tree-based methods to infer Signal Temporal Logic classifiers using primitive formulae. We formulate the inference process as a mixed integer linear programming optimization problem, recursively generating constraints to determine both data classification and tree structure. Applying a max-flow algorithm on the resultant tree transforms the problem into a global optimization challenge, leading to improved classification rates compared to prior methodologies. Moreover, we introduce a technique to reduce the number of constraints by exploiting the symmetry inherent in STL primitives, which enhances the algorithm's time performance and interpretability. To assess our algorithm's effectiveness and classification performance, we conduct three case studies involving two-class, multi-class, and complex formula classification scenarios.
Authors: Anna Vettoruzzo, Joaquin Vanschoren, Mohamed-Rafik Bouguelia, Thorsteinn R\"ognvaldsson
Abstract: Continual learning (CL) refers to the ability to continually learn over time by accommodating new knowledge while retaining previously learned experience. While this concept is inherent in human learning, current machine learning methods are highly prone to overwrite previously learned patterns and thus forget past experience. Instead, model parameters should be updated selectively and carefully, avoiding unnecessary forgetting while optimally leveraging previously learned patterns to accelerate future learning. Since hand-crafting effective update mechanisms is difficult, we propose meta-learning a transformer-based optimizer to enhance CL. This meta-learned optimizer uses attention to learn the complex relationships between model parameters across a stream of tasks, and is designed to generate effective weight updates for the current task while preventing catastrophic forgetting on previously encountered tasks. Evaluations on benchmark datasets like SplitMNIST, RotatedMNIST, and SplitCIFAR-100 affirm the efficacy of the proposed approach in terms of both forward and backward transfer, even on small sets of labeled data, highlighting the advantages of integrating a meta-learned optimizer within the continual learning framework.
Authors: Vasudev Shyam, Jonathan Pilault, Emily Shepperd, Quentin Anthony, Beren Millidge
Abstract: Self-attention is the core mathematical operation of modern transformer architectures and is also a significant computational bottleneck due to its quadratic complexity in the sequence length. In this work, we derive the scalar energy function whose gradient computes the self-attention block, thus elucidating the theoretical underpinnings of self-attention, providing a Bayesian interpretation of the operation and linking it closely with energy-based models such as Hopfield Networks. Our formulation reveals that the reduction across the sequence axis can be efficiently computed in parallel through a tree reduction. Our algorithm, for parallelizing attention computation across multiple GPUs enables cross-device decoding to be performed asymptotically faster (up to 8x faster in our experiments) than alternative approaches such as Ring Attention, while also requiring significantly less communication volume and incurring 2x less peak memory. Our code is publicly available here: \url{https://github.com/Zyphra/tree_attention}.
Authors: Styliani Katsarou, Francesca Carminati, Martin Dlask, Marta Braojos, Lavena Patra, Richard Perkins, Carlos Garcia Ling, Maria Paskevich
Abstract: A good understanding of player preferences is crucial for increasing content relevancy, especially in mobile games. This paper illustrates the use of attentive models for producing item recommendations in a mobile game scenario. The methodology comprises a combination of supervised and unsupervised approaches to create user-level recommendations while introducing a novel scale-invariant approach to the prediction. The methodology is subsequently applied to a bundle recommendation in Candy Crush Saga. The strategy of deployment, maintenance, and monitoring of ML models that are scaled up to serve millions of users is presented, along with the best practices and design patterns adopted to minimize technical debt typical of ML systems. The recommendation approach is evaluated both offline and online, with a focus on understanding the increase in engagement, click- and take rates, novelty effects, recommendation diversity, and the impact of degenerate feedback loops. We have demonstrated that the recommendation enhances user engagement by 30% concerning click rate and by more than 40% concerning take rate. In addition, we empirically quantify the diminishing effects of recommendation accuracy on user engagement.
Authors: Dimitry Mindlin, Amelie Sophie Robrecht, Michael Morasch, Philipp Cimiano
Abstract: The field of eXplainable Artificial Intelligence (XAI) is increasingly recognizing the need to personalize and/or interactively adapt the explanation to better reflect users' explanation needs. While dialogue-based approaches to XAI have been proposed recently, the state-of-the-art in XAI is still characterized by what we call one-shot, non-personalized and one-way explanations. In contrast, dialogue-based systems that can adapt explanations through interaction with a user promise to be superior to GUI-based or dashboard explanations as they offer a more intuitive way of requesting information. In general, while interactive XAI systems are often evaluated in terms of user satisfaction, there are limited studies that access user's objective model understanding. This is in particular the case for dialogue-based XAI approaches. In this paper, we close this gap by carrying out controlled experiments within a dialogue framework in which we measure understanding of users in three phases by asking them to simulate the predictions of the model they are learning about. By this, we can quantify the level of (improved) understanding w.r.t. how the model works, comparing the state prior, and after the interaction. We further analyze the data to reveal patterns of how the interaction between groups with high vs. low understanding gain differ. Overall, our work thus contributes to our understanding about the effectiveness of XAI approaches.
Authors: A. Feder Cooper, Jonathan Frankle, Christopher De Sa
Abstract: Legal literature on machine learning (ML) tends to focus on harms, and thus tends to reason about individual model outcomes and summary error rates. This focus has masked important aspects of ML that are rooted in its reliance on randomness -- namely, stochasticity and non-determinism. While some recent work has begun to reason about the relationship between stochasticity and arbitrariness in legal contexts, the role of non-determinism more broadly remains unexamined. In this paper, we clarify the overlap and differences between these two concepts, and show that the effects of non-determinism, and consequently its implications for the law, become clearer from the perspective of reasoning about ML outputs as distributions over possible outcomes. This distributional viewpoint accounts for randomness by emphasizing the possible outcomes of ML. Importantly, this type of reasoning is not exclusive with current legal reasoning; it complements (and in fact can strengthen) analyses concerning individual, concrete outcomes for specific automated decisions. By illuminating the important role of non-determinism, we demonstrate that ML code falls outside of the cyberlaw frame of treating ``code as law,'' as this frame assumes that code is deterministic. We conclude with a brief discussion of what work ML can do to constrain the potentially harm-inducing effects of non-determinism, and we indicate where the law must do work to bridge the gap between its current individual-outcome focus and the distributional approach that we recommend.
Authors: Chaoqi Chen, Yushuang Wu, Qiyuan Dai, Hong-Yu Zhou, Mutian Xu, Sibei Yang, Xiaoguang Han, Yizhou Yu
Abstract: Graph Neural Networks (GNNs) have gained momentum in graph representation learning and boosted the state of the art in a variety of areas, such as data mining (\emph{e.g.,} social network analysis and recommender systems), computer vision (\emph{e.g.,} object detection and point cloud learning), and natural language processing (\emph{e.g.,} relation extraction and sequence learning), to name a few. With the emergence of Transformers in natural language processing and computer vision, graph Transformers embed a graph structure into the Transformer architecture to overcome the limitations of local neighborhood aggregation while avoiding strict structural inductive biases. In this paper, we present a comprehensive review of GNNs and graph Transformers in computer vision from a task-oriented perspective. Specifically, we divide their applications in computer vision into five categories according to the modality of input data, \emph{i.e.,} 2D natural images, videos, 3D data, vision + language, and medical images. In each category, we further divide the applications according to a set of vision tasks. Such a task-oriented taxonomy allows us to examine how each task is tackled by different GNN-based approaches and how well these approaches perform. Based on the necessary preliminaries, we provide the definitions and challenges of the tasks, in-depth coverage of the representative approaches, as well as discussions regarding insights, limitations, and future directions.
Authors: Xiaoyang Yu, Youfang Lin, Xiangsen Wang, Sheng Han, Kai Lv
Abstract: Previous deep multi-agent reinforcement learning (MARL) algorithms have achieved impressive results, typically in homogeneous scenarios. However, heterogeneous scenarios are also very common and usually harder to solve. In this paper, we mainly discuss cooperative heterogeneous MARL problems in Starcraft Multi-Agent Challenges (SMAC) environment. We firstly define and describe the heterogeneous problems in SMAC. In order to comprehensively reveal and study the problem, we make new maps added to the original SMAC maps. We find that baseline algorithms fail to perform well in those heterogeneous maps. To address this issue, we propose the Grouped Individual-Global-Max Consistency (GIGM) and a novel MARL algorithm, Grouped Hybrid Q Learning (GHQ). GHQ separates agents into several groups and keeps individual parameters for each group, along with a novel hybrid structure for factorization. To enhance coordination between groups, we maximize the Inter-group Mutual Information (IGMI) between groups' trajectories. Experiments on original and new heterogeneous maps show the fabulous performance of GHQ compared to other state-of-the-art algorithms.
Authors: Matthew Dicks, Andrew Paskaramoorthy, Tim Gebbie
Abstract: We consider the dynamics and the interactions of multiple reinforcement learning optimal execution trading agents interacting with a reactive Agent-Based Model (ABM) of a financial market in event time. The model represents a market ecology with 3-trophic levels represented by: optimal execution learning agents, minimally intelligent liquidity takers, and fast electronic liquidity providers. The optimal execution agent classes include buying and selling agents that can either use a combination of limit orders and market orders, or only trade using market orders. The reward function explicitly balances trade execution slippage against the penalty of not executing the order timeously. This work demonstrates how multiple competing learning agents impact a minimally intelligent market simulation as functions of the number of agents, the size of agents' initial orders, and the state spaces used for learning. We use phase space plots to examine the dynamics of the ABM, when various specifications of learning agents are included. Further, we examine whether the inclusion of optimal execution agents that can learn is able to produce dynamics with the same complexity as empirical data. We find that the inclusion of optimal execution agents changes the stylised facts produced by ABM to conform more with empirical data, and are a necessary inclusion for ABMs investigating market micro-structure. However, including execution agents to chartist-fundamentalist-noise ABMs is insufficient to recover the complexity observed in empirical data.
Authors: Fengyi Li, Youssef Marzouk
Abstract: We propose a novel diffusion map particle system (DMPS) for generative modeling, based on diffusion maps and Laplacian-adjusted Wasserstein gradient descent (LAWGD). Diffusion maps are used to approximate the generator of the corresponding Langevin diffusion process from samples, and hence to learn the underlying data-generating manifold. On the other hand, LAWGD enables efficient sampling from the target distribution given a suitable choice of kernel, which we construct here via a spectral approximation of the generator, computed with diffusion maps. Our method requires no offline training and minimal tuning, and can outperform other approaches on data sets of moderate dimension.
Authors: Colin A. Grambow, Hayley Weir, Nathaniel L. Diamant, Gabriele Scalia, Tommaso Biancalani, Kangway V. Chuang
Abstract: Macrocyclic peptides are an emerging therapeutic modality, yet computational approaches for accurately sampling their diverse 3D ensembles remain challenging due to their conformational diversity and geometric constraints. Here, we introduce RINGER, a diffusion-based transformer model using a redundant internal coordinate representation that generates three-dimensional conformational ensembles of macrocyclic peptides from their 2D representations. RINGER provides fast backbone and side-chain sampling while respecting key structural invariances of cyclic peptides. Through extensive benchmarking and analysis against gold-standard conformer ensembles of cyclic peptides generated with metadynamics, we demonstrate how RINGER generates both high-quality and diverse geometries at a fraction of the computational cost. Our work lays the foundation for improved sampling of cyclic geometries and the development of geometric learning methods for peptides.
Authors: Lin Li, Jianing Qiu, Michael Spratling
Abstract: Deep neural networks are vulnerable to adversarial examples. Adversarial training (AT) is an effective defense against adversarial examples. However, AT is prone to overfitting which degrades robustness substantially. Recently, data augmentation (DA) was shown to be effective in mitigating robust overfitting if appropriately designed and optimized for AT. This work proposes a new method to automatically learn online, instance-wise, DA policies to improve robust generalization for AT. This is the first automated DA method specific for robustness. A novel policy learning objective, consisting of Vulnerability, Affinity and Diversity, is proposed and shown to be sufficiently effective and efficient to be practical for automatic DA generation during AT. Importantly, our method dramatically reduces the cost of policy search from the 5000 hours of AutoAugment and the 412 hours of IDBH to 9 hours, making automated DA more practical to use for adversarial robustness. This allows our method to efficiently explore a large search space for a more effective DA policy and evolve the policy as training progresses. Empirically, our method is shown to outperform all competitive DA methods across various model architectures and datasets. Our DA policy reinforced vanilla AT to surpass several state-of-the-art AT methods regarding both accuracy and robustness. It can also be combined with those advanced AT methods to further boost robustness. Code and pre-trained models are available at https://github.com/TreeLLi/AROID.
Authors: Vipul Gupta, Pranav Narayanan Venkit, Shomir Wilson, Rebecca J. Passonneau
Abstract: Sociodemographic bias in language models (LMs) has the potential for harm when deployed in real-world settings. This paper presents a comprehensive survey of the past decade of research on sociodemographic bias in LMs, organized into a typology that facilitates examining the different aims: types of bias, quantifying bias, and debiasing techniques. We track the evolution of the latter two questions, then identify current trends and their limitations, as well as emerging techniques. To guide future research towards more effective and reliable solutions, and to help authors situate their work within this broad landscape, we conclude with a checklist of open questions.
Authors: Soham Jana, Kun Yang, Sanjeev Kulkarni
Abstract: We consider the problem of clustering data points coming from sub-Gaussian mixtures. Existing methods that provably achieve the optimal mislabeling error, such as the Lloyd algorithm, are usually vulnerable to outliers. In contrast, clustering methods seemingly robust to adversarial perturbations are not known to satisfy the optimal statistical guarantees. We propose a simple robust algorithm based on the coordinatewise median that obtains the optimal mislabeling rate even when we allow adversarial outliers to be present. Our algorithm achieves the optimal error rate in constant iterations when a weak initialization condition is satisfied. In the absence of outliers, in fixed dimensions, our theoretical guarantees are similar to that of the Lloyd algorithm. Extensive experiments on various simulated and public datasets are conducted to support the theoretical guarantees of our method.
Authors: Bin Chen, Xuanyu Zhang, Shuai Liu, Yongbing Zhang, Jian Zhang
Abstract: Compressed sensing (CS) is a promising tool for reducing sampling costs. Current deep neural network (NN)-based CS methods face the challenges of collecting labeled measurement-ground truth (GT) data and generalizing to real applications. This paper proposes a novel $\mathbf{S}$elf-supervised s$\mathbf{C}$alable deep CS method, comprising a deep $\mathbf{L}$earning scheme called $\mathbf{SCL}$ and a family of $\mathbf{Net}$works named $\mathbf{SCNet}$, which does not require GT and can handle arbitrary sampling ratios and matrices once trained on a partial measurement set. Our SCL contains a dual-domain loss and a four-stage recovery strategy. The former encourages a cross-consistency on two measurement parts and a sampling-reconstruction cycle-consistency regarding arbitrary ratios and matrices to maximize data/information utilization. The latter can progressively leverage common signal prior in external measurements and internal characteristics of test samples and learned NNs to improve accuracy. SCNet combines both the explicit guidance from optimization algorithms with implicit regularization from advanced NN blocks to learn a collaborative signal representation. Our theoretical analyses and experiments on simulated and real captured data, covering 1-/2-/3-D natural and scientific signals, demonstrate the effectiveness, superior performance, flexibility, and generalization ability of our method over existing self-supervised methods and its significant potential in competing against state-of-the-art supervised methods. Code is available at https://github.com/Guaishou74851/SCNet.
Authors: Kazuma Iwase, Tomoyuki Takenawa
Abstract: Recent advances in numerical simulation methods based on physical models and their combination with machine learning have improved the accuracy of weather forecasts. However, the accuracy decreases in complex terrains such as mountainous regions because these methods usually use grids of several kilometers square and simple machine learning models. While deep learning has also made significant progress in recent years, its direct application is difficult to utilize the physical knowledge used in the simulation. This paper proposes a method that uses machine learning to interpolate future weather in mountainous regions using forecast data from surrounding plains and past observed data to improve weather forecasts in mountainous regions. We focus on mountainous regions in Japan and predict temperature and precipitation mainly using LightGBM as a machine learning model. Despite the use of a small dataset, through feature engineering and model tuning, our method partially achieves improvements in the RMSE with significantly less training time.
Authors: Aashish Gottipati, Sami Khairy, Gabriel Mittag, Vishak Gopal, Ross Cutler
Abstract: In this work, we tackle the problem of bandwidth estimation (BWE) for real-time communication systems through expert personalization. While expert heuristic-based methods have been widely adopted, tailoring these methods for each and every end user environment is cumbersome due to the level of domain expertise and manual effort required to adjust the carefully tuned heuristic parameters. Thus. we propose Merlin, a data-driven solution to BWE that harnesses expert demonstrations from prior heuristic-based methods to extract an expert BWE policy. The extracted policy can then be finetuned to end user network conditions to improve user quality of experience (QoE). In real-world videoconferencing calls, Merlin matches our expert's policy with no statistically significant movements in terms of objective QoE metrics. Additionally, we show that personalizing Merlin's control policy is possible through a small number of online data-driven parameter updates.
Authors: Jan Hendrik Metzen, Piyapat Saranrittichai, Chaithanya Kumar Mummadi
Abstract: Classifiers built upon vision-language models such as CLIP have shown remarkable zero-shot performance across a broad range of image classification tasks. Prior work has studied different ways of automatically creating descriptor sets for every class based on prompt templates, ranging from manually engineered templates over templates obtained from a large language model to templates built from random words and characters. Up until now, deriving zero-shot classifiers from the respective encoded class descriptors has remained nearly unchanged, i.e., classify to the class that maximizes cosine similarity between its averaged encoded class descriptors and the image encoding. However, weighing all class descriptors equally can be suboptimal when certain descriptors match visual clues on a given image better than others. In this work, we propose AutoCLIP, a method for auto-tuning zero-shot classifiers. AutoCLIP tunes per-image weights to each prompt template at inference time, based on statistics of class descriptor-image similarities. AutoCLIP is fully unsupervised, has only a minor additional computation overhead, and can be easily implemented in few lines of code. We show that AutoCLIP outperforms baselines across a broad range of vision-language models, datasets, and prompt templates consistently and by up to 3 percent point accuracy.
Authors: Nicholas Crispino, Kyle Montgomery, Fankun Zeng, Dawn Song, Chenguang Wang
Abstract: We introduce a method to improve the zero-shot reasoning abilities of large language models on general language understanding tasks. Specifically, we build an autonomous agent to instruct the reasoning process of large language models. We show this approach further unleashes the zero-shot reasoning abilities of large language models to more tasks. We study the performance of our method on a wide set of datasets spanning generation, classification, and reasoning. We show that our method generalizes to most tasks and obtains state-of-the-art zero-shot performance on 20 of the 29 datasets that we evaluate. For instance, our method boosts the performance of state-of-the-art large language models by a large margin, including Vicuna-13b (13.3%), Llama-2-70b-chat (23.2%), and GPT-3.5 Turbo (17.0%). Compared to zero-shot chain of thought, our improvement in reasoning is striking, with an average increase of 10.5%. With our method, Llama-2-70b-chat outperforms zero-shot GPT-3.5 Turbo by 10.2%.
Authors: Yu Zhang, Yanzhen Shen, SeongKu Kang, Xiusi Chen, Bowen Jin, Jiawei Han
Abstract: With the rapid increase in paper submissions to academic conferences, the need for automated and accurate paper-reviewer matching is more critical than ever. Previous efforts in this area have considered various factors to assess the relevance of a reviewer's expertise to a paper, such as the semantic similarity, shared topics, and citation connections between the paper and the reviewer's previous works. However, most of these studies focus on only one factor, resulting in an incomplete evaluation of the paper-reviewer relevance. To address this issue, we propose a unified model for paper-reviewer matching that jointly considers semantic, topic, and citation factors. To be specific, during training, we instruction-tune a contextualized language model shared across all factors to capture their commonalities and characteristics; during inference, we chain the three factors to enable step-by-step, coarse-to-fine search for qualified reviewers given a submission. Experiments on four datasets (one of which is newly contributed by us) spanning various fields such as machine learning, computer vision, information retrieval, and data mining consistently demonstrate the effectiveness of our proposed Chain-of-Factors model in comparison with state-of-the-art paper-reviewer matching methods and scientific pre-trained language models.
Authors: Andrew Davison, S. Carlyle Morgan, Owen G. Ward
Abstract: Embedding the nodes of a large network into an Euclidean space is a common objective in modern machine learning, with a variety of tools available. These embeddings can then be used as features for tasks such as community detection/node clustering or link prediction, where they achieve state of the art performance. With the exception of spectral clustering methods, there is little theoretical understanding for commonly used approaches to learning embeddings. In this work we examine the theoretical properties of the embeddings learned by node2vec. Our main result shows that the use of $k$-means clustering on the embedding vectors produced by node2vec gives weakly consistent community recovery for the nodes in (degree corrected) stochastic block models. We also discuss the use of these embeddings for node and link prediction tasks. We demonstrate this result empirically, and examine how this relates to other embedding tools for network data.
Authors: Zhuohang Dang, Minnan Luo, Chengyou Jia, Guang Dai, Jihong Wang, Xiaojun Chang, Jingdong Wang
Abstract: Encoding only the task-related information from the raw data, \ie, disentangled representation learning, can greatly contribute to the robustness and generalizability of models. Although significant advances have been made by regularizing the information in representations with information theory, two major challenges remain: 1) the representation compression inevitably leads to performance drop; 2) the disentanglement constraints on representations are in complicated optimization. To these issues, we introduce Bayesian networks with transmitted information to formulate the interaction among input and representations during disentanglement. Building upon this framework, we propose \textbf{DisTIB} (\textbf{T}ransmitted \textbf{I}nformation \textbf{B}ottleneck for \textbf{Dis}entangled representation learning), a novel objective that navigates the balance between information compression and preservation. We employ variational inference to derive a tractable estimation for DisTIB. This estimation can be simply optimized via standard gradient descent with a reparameterization trick. Moreover, we theoretically prove that DisTIB can achieve optimal disentanglement, underscoring its superior efficacy. To solidify our claims, we conduct extensive experiments on various downstream tasks to demonstrate the appealing efficacy of DisTIB and validate our theoretical analyses.
Authors: Sihan Zeng, Sujay Bhatt, Eleonora Kreacic, Parisa Hassanzadeh, Alec Koppel, Sumitra Ganesh
Abstract: We consider the design of mechanisms that allocate limited resources among self-interested agents using neural networks. Unlike the recent works that leverage machine learning for revenue maximization in auctions, we consider welfare maximization as the key objective in the payment-free setting. Without payment exchange, it is unclear how we can align agents' incentives to achieve the desired objectives of truthfulness and social welfare simultaneously, without resorting to approximations. Our work makes novel contributions by designing an approximate mechanism that desirably trade-off social welfare with truthfulness. Specifically, (i) we contribute a new end-to-end neural network architecture, ExS-Net, that accommodates the idea of "money-burning" for mechanism design without payments; (ii)~we provide a generalization bound that guarantees the mechanism performance when trained under finite samples; and (iii) we provide an experimental demonstration of the merits of the proposed mechanism.
Authors: Daniele Regoli, Alessandro Castelnovo, Nicole Inverardi, Gabriele Nanino, Ilaria Penco
Abstract: In recent years, the increase in the usage and efficiency of Artificial Intelligence and, more in general, of Automated Decision-Making systems has brought with it an increasing and welcome awareness of the risks associated with such systems. One of such risks is that of perpetuating or even amplifying bias and unjust disparities present in the data from which many of these systems learn to adjust and optimise their decisions. This awareness has on the one hand encouraged several scientific communities to come up with more and more appropriate ways and methods to assess, quantify, and possibly mitigate such biases and disparities. On the other hand, it has prompted more and more layers of society, including policy makers, to call for fair algorithms. We believe that while many excellent and multidisciplinary research is currently being conducted, what is still fundamentally missing is the awareness that having fair algorithms is per se a nearly meaningless requirement that needs to be complemented with many additional social choices to become actionable. Namely, there is a hiatus between what the society is demanding from Automated Decision-Making systems, and what this demand actually means in real-world scenarios. In this work, we outline the key features of such a hiatus and pinpoint a set of crucial open points that we as a society must address in order to give a concrete meaning to the increasing demand of fairness in Automated Decision-Making systems.
Authors: Yiwen Zheng, Prakash Thakolkaran, Agni K. Biswal, Jake A. Smith, Ziheng Lu, Shuxin Zheng, Bichlien H. Nguyen, Siddhant Kumar, Aniruddh Vashisth
Abstract: Vitrimer is a new, exciting class of sustainable polymers with the ability to heal due to their dynamic covalent adaptive network that can go through associative rearrangement reactions. However, a limited choice of constituent molecules restricts their property space, prohibiting full realization of their potential applications. To overcome this challenge, we couple molecular dynamics (MD) simulations and a novel graph variational autoencoder (VAE) machine learning model for inverse design of vitrimer chemistries with desired glass transition temperature (Tg) and synthesize a novel vitrimer polymer. We build the first vitrimer dataset of one million chemistries and calculate Tg on 8,424 of them by high-throughput MD simulations calibrated by a Gaussian process model. The proposed novel VAE employs dual graph encoders and a latent dimension overlapping scheme which allows for individual representation of multi-component vitrimers. By constructing a continuous latent space containing necessary information of vitrimers, we demonstrate high accuracy and efficiency of our framework in discovering novel vitrimers with desirable Tg beyond the training regime. To validate the effectiveness of our framework in experiments, we generate novel vitrimer chemistries with a target Tg = 323 K. By incorporating chemical intuition, we synthesize a vitrimer with Tg of 311-317 K, and experimentally demonstrate healability and flowability. The proposed framework offers an exciting tool for polymer chemists to design and synthesize novel, sustainable vitrimer polymers for a facet of applications.
Authors: Junfei Xiao, Ziqi Zhou, Wenxuan Li, Shiyi Lan, Jieru Mei, Zhiding Yu, Alan Yuille, Yuyin Zhou, Cihang Xie
Abstract: This paper introduces ProLab, a novel approach using property-level label space for creating strong interpretable segmentation models. Instead of relying solely on category-specific annotations, ProLab uses descriptive properties grounded in common sense knowledge for supervising segmentation models. It is based on two core designs. First, we employ Large Language Models (LLMs) and carefully crafted prompts to generate descriptions of all involved categories that carry meaningful common sense knowledge and follow a structured format. Second, we introduce a description embedding model preserving semantic correlation across descriptions and then cluster them into a set of descriptive properties (e.g., 256) using K-Means. These properties are based on interpretable common sense knowledge consistent with theories of human recognition. We empirically show that our approach makes segmentation models perform stronger on five classic benchmarks (e.g., ADE20K, COCO-Stuff, Pascal Context, Cityscapes, and BDD). Our method also shows better scalability with extended training steps than category-level supervision. Our interpretable segmentation framework also emerges with the generalization ability to segment out-of-domain or unknown categories using only in-domain descriptive properties. Code is available at https://github.com/lambert-x/ProLab.
Authors: Yuyang Tao, Shufei Ge
Abstract: Motivation: The Mapper algorithm is an essential tool to explore shape of data in topology data analysis. With a dataset as an input, the Mapper algorithm outputs a graph representing the topological features of the whole dataset. This graph is often regarded as an approximation of a reeb graph of data. The classic Mapper algorithm uses fixed interval lengths and overlapping ratios, which might fail to reveal subtle features of data, especially when the underlying structure is complex. Results: In this work, we introduce a distribution guided Mapper algorithm named D-Mapper, that utilizes the property of the probability model and data intrinsic characteristics to generate density guided covers and provides enhanced topological features. Our proposed algorithm is a probabilistic model-based approach, which could serve as an alternative to non-prababilistic ones. Moreover, we introduce a metric accounting for both the quality of overlap clustering and extended persistence homology to measure the performance of Mapper type algorithm. Our numerical experiments indicate that the D-Mapper outperforms the classical Mapper algorithm in various scenarios. We also apply the D-Mapper to a SARS-COV-2 coronavirus RNA sequences dataset to explore the topological structure of different virus variants. The results indicate that the D-Mapper algorithm can reveal both vertical and horizontal evolution processes of the viruses. Availability: Our package is available at https://github.com/ShufeiGe/D-Mapper.
Authors: Chenyu Liu, Xinliang Zhou, Yihao Wu, Ruizhi Yang, Zhongruo Wang, Liming Zhai, Ziyu Jia, Yang Liu
Abstract: Compared to other modalities, EEG-based emotion recognition can intuitively respond to the emotional patterns in the human brain and, therefore, has become one of the most concerning tasks in the brain-computer interfaces field. Since dependencies within brain regions are closely related to emotion, a significant trend is to develop Graph Neural Networks (GNNs) for EEG-based emotion recognition. However, brain region dependencies in emotional EEG have physiological bases that distinguish GNNs in this field from those in other time series fields. Besides, there is neither a comprehensive review nor guidance for constructing GNNs in EEG-based emotion recognition. In the survey, our categorization reveals the commonalities and differences of existing approaches under a unified framework of graph construction. We analyze and categorize methods from three stages in the framework to provide clear guidance on constructing GNNs in EEG-based emotion recognition. In addition, we discuss several open challenges and future directions, such as Temporal full-connected graph and Graph condensation.
Authors: Joshua C. Yang, Damian Dailisan, Marcin Korecki, Carina I. Hausladen, Dirk Helbing
Abstract: This paper investigates the voting behaviors of Large Language Models (LLMs), specifically GPT-4 and LLaMA-2, their biases, and how they align with human voting patterns. Our methodology involved using a dataset from a human voting experiment to establish a baseline for human preferences and conducting a corresponding experiment with LLM agents. We observed that the choice of voting methods and the presentation order influenced LLM voting outcomes. We found that varying the persona can reduce some of these biases and enhance alignment with human choices. While the Chain-of-Thought approach did not improve prediction accuracy, it has potential for AI explainability in the voting process. We also identified a trade-off between preference diversity and alignment accuracy in LLMs, influenced by different temperature settings. Our findings indicate that LLMs may lead to less diverse collective outcomes and biased assumptions when used in voting scenarios, emphasizing the need for cautious integration of LLMs into democratic processes.
Authors: Mingjie Sun, Xinlei Chen, J. Zico Kolter, Zhuang Liu
Abstract: We observe an empirical phenomenon in Large Language Models (LLMs) -- very few activations exhibit significantly larger values than others (e.g., 100,000 times larger). We call them massive activations. First, we demonstrate the widespread existence of massive activations across various LLMs and characterize their locations. Second, we find their values largely stay constant regardless of the input, and they function as indispensable bias terms in LLMs. Third, these massive activations lead to the concentration of attention probabilities to their corresponding tokens, and further, implicit bias terms in the self-attention output. Last, we also study massive activations in Vision Transformers. Code is available at https://github.com/locuslab/massive-activations.
Authors: Emanuel Ben-Baruch, Adam Botach, Igor Kviatkovsky, Manoj Aggarwal, G\'erard Medioni
Abstract: With the increasing size of datasets used for training neural networks, data pruning becomes an attractive field of research. However, most current data pruning algorithms are limited in their ability to preserve accuracy compared to models trained on the full data, especially in high pruning regimes. In this paper we explore the application of data pruning while incorporating knowledge distillation (KD) when training on a pruned subset. That is, rather than relying solely on ground-truth labels, we also use the soft predictions from a teacher network pre-trained on the complete data. By integrating KD into training, we demonstrate significant improvement across datasets, pruning methods, and on all pruning fractions. We first establish a theoretical motivation for employing self-distillation to improve training on pruned data. Then, we empirically make a compelling and highly practical observation: using KD, simple random pruning is comparable or superior to sophisticated pruning methods across all pruning regimes. On ImageNet for example, we achieve superior accuracy despite training on a random subset of only 50% of the data. Additionally, we demonstrate a crucial connection between the pruning factor and the optimal knowledge distillation weight. This helps mitigate the impact of samples with noisy labels and low-quality images retained by typical pruning algorithms. Finally, we make an intriguing observation: when using lower pruning fractions, larger teachers lead to accuracy degradation, while surprisingly, employing teachers with a smaller capacity than the student's may improve results. Our code will be made available.
Authors: Nicolaj Schmid, Cornelius von Einem, Cesar Cadena, Roland Siegwart, Lorenz Hruby, Florian Tschopp
Abstract: Autonomous mobile robots are an increasingly integral part of modern factory and warehouse operations. Obstacle detection, avoidance and path planning are critical safety-relevant tasks, which are often solved using expensive LiDAR sensors and depth cameras. We propose to use cost-effective low-resolution ranging sensors, such as ultrasonic and infrared time-of-flight sensors by developing VIRUS-NeRF - Vision, InfraRed, and UltraSonic based Neural Radiance Fields. Building upon Instant Neural Graphics Primitives with a Multiresolution Hash Encoding (Instant-NGP), VIRUS-NeRF incorporates depth measurements from ultrasonic and infrared sensors and utilizes them to update the occupancy grid used for ray marching. Experimental evaluation in 2D demonstrates that VIRUS-NeRF achieves comparable mapping performance to LiDAR point clouds regarding coverage. Notably, in small environments, its accuracy aligns with that of LiDAR measurements, while in larger ones, it is bounded by the utilized ultrasonic sensors. An in-depth ablation study reveals that adding ultrasonic and infrared sensors is highly effective when dealing with sparse data and low view variation. Further, the proposed occupancy grid of VIRUS-NeRF improves the mapping capabilities and increases the training speed by 46% compared to Instant-NGP. Overall, VIRUS-NeRF presents a promising approach for cost-effective local mapping in mobile robotics, with potential applications in safety and navigation tasks. The code can be found at https://github.com/ethz-asl/virus nerf.
Authors: Md Salman Shamil, Dibyadip Chatterjee, Fadime Sener, Shugao Ma, Angela Yao
Abstract: 3D hand pose is an underexplored modality for action recognition. Poses are compact yet informative and can greatly benefit applications with limited compute budgets. However, poses alone offer an incomplete understanding of actions, as they cannot fully capture objects and environments with which humans interact. We propose HandFormer, a novel multimodal transformer, to efficiently model hand-object interactions. HandFormer combines 3D hand poses at a high temporal resolution for fine-grained motion modeling with sparsely sampled RGB frames for encoding scene semantics. Observing the unique characteristics of hand poses, we temporally factorize hand modeling and represent each joint by its short-term trajectories. This factorized pose representation combined with sparse RGB samples is remarkably efficient and highly accurate. Unimodal HandFormer with only hand poses outperforms existing skeleton-based methods at 5x fewer FLOPs. With RGB, we achieve new state-of-the-art performance on Assembly101 and H2O with significant improvements in egocentric action recognition.
Authors: Yucheng Shi, Qiaoyu Tan, Xuansheng Wu, Shaochen Zhong, Kaixiong Zhou, Ninghao Liu
Abstract: Large Language Models (LLMs) have shown proficiency in question-answering tasks but often struggle to integrate real-time knowledge, leading to potentially outdated or inaccurate responses. This problem becomes even more challenging when dealing with multi-hop questions, since they require LLMs to update and integrate multiple knowledge pieces relevant to the questions. To tackle the problem, we propose the Retrieval-Augmented model Editing (RAE) framework for multi-hop question answering. RAE first retrieves edited facts and then refines the language model through in-context learning. Specifically, our retrieval approach, based on mutual information maximization, leverages the reasoning abilities of LLMs to identify chain facts that traditional similarity-based searches might miss. In addition, our framework includes a pruning strategy to eliminate redundant information from the retrieved facts, which enhances the editing accuracy and mitigates the hallucination problem. Our framework is supported by theoretical justification for its fact retrieval efficacy. Finally, comprehensive evaluation across various LLMs validates RAE's ability in providing accurate answers with updated knowledge. Our code is available at: https://github.com/sycny/RAE.
Authors: Aparajithan Venkateswaran, Anirudh Sankar, Arun G. Chandrasekhar, Tyler H. McCormick
Abstract: Many statistical analyses, in both observational data and randomized control trials, ask: how does the outcome of interest vary with combinations of observable covariates? How do various drug combinations affect health outcomes, or how does technology adoption depend on incentives and demographics? Our goal is to partition this factorial space into "pools" of covariate combinations where the outcome differs across the pools (but not within a pool). Existing approaches (i) search for a single "optimal" partition under assumptions about the association between covariates or (ii) sample from the entire set of possible partitions. Both these approaches ignore the reality that, especially with correlation structure in covariates, many ways to partition the covariate space may be statistically indistinguishable, despite very different implications for policy or science. We develop an alternative perspective, called Rashomon Partition Sets (RPSs). Each item in the RPS partitions the space of covariates using a tree-like geometry. RPSs incorporate all partitions that have posterior values near the maximum a posteriori partition, even if they offer substantively different explanations, and do so using a prior that makes no assumptions about associations between covariates. This prior is the $\ell_0$ prior, which we show is minimax optimal. Given the RPS we calculate the posterior of any measurable function of the feature effects vector on outcomes, conditional on being in the RPS. We also characterize approximation error relative to the entire posterior and provide bounds on the size of the RPS. Simulations demonstrate this framework allows for robust conclusions relative to conventional regularization techniques. We apply our method to three empirical settings: price effects on charitable giving, chromosomal structure (telomere length), and the introduction of microfinance.
Authors: Brian Lester, Jaehoon Lee, Alex Alemi, Jeffrey Pennington, Adam Roberts, Jascha Sohl-Dickstein, Noah Constant
Abstract: In this paper, we explore the idea of training large language models (LLMs) over highly compressed text. While standard subword tokenizers compress text by a small factor, neural text compressors can achieve much higher rates of compression. If it were possible to train LLMs directly over neurally compressed text, this would confer advantages in training and serving efficiency, as well as easier handling of long text spans. The main obstacle to this goal is that strong compression tends to produce opaque outputs that are not well-suited for learning. In particular, we find that text na\"ively compressed via Arithmetic Coding is not readily learnable by LLMs. To overcome this, we propose Equal-Info Windows, a novel compression technique whereby text is segmented into blocks that each compress to the same bit length. Using this method, we demonstrate effective learning over neurally compressed text that improves with scale, and outperforms byte-level baselines by a wide margin on perplexity and inference speed benchmarks. While our method delivers worse perplexity than subword tokenizers for models trained with the same parameter count, it has the benefit of shorter sequence lengths. Shorter sequence lengths require fewer autoregressive generation steps, and reduce latency. Finally, we provide extensive analysis of the properties that contribute to learnability, and offer concrete suggestions for how to further improve the performance of high-compression tokenizers.
Authors: Hyeonggeun Yun
Abstract: In computer vision, explainable AI (xAI) methods seek to mitigate the 'black-box' problem by making the decision-making process of deep learning models more interpretable and transparent. Traditional xAI methods concentrate on visualizing input features that influence model predictions, providing insights primarily suited for experts. In this work, we present an interaction-based xAI method that enhances user comprehension of image classification models through their interaction. Thus, we developed a web-based prototype allowing users to modify images via painting and erasing, thereby observing changes in classification results. Our approach enables users to discern critical features influencing the model's decision-making process, aligning their mental models with the model's logic. Experiments conducted with five images demonstrate the potential of the method to reveal feature importance through user interaction. Our work contributes a novel perspective to xAI by centering on end-user engagement and understanding, paving the way for more intuitive and accessible explainability in AI systems.
Authors: Nina Moutonnet, Steven White, Benjamin P Campbell, Saeid Sanei, Toshihisa Tanaka, Hong Ji, Danilo Mandic, Gregory Scott
Abstract: Machine learning algorithms for seizure detection have shown considerable diagnostic potential, with recent reported accuracies reaching 100%. Yet, only few published algorithms have fully addressed the requirements for successful clinical translation. This is, for example, because the properties of training data may limit the generalisability of algorithms, algorithm performance may vary depending on which electroencephalogram (EEG) acquisition hardware was used, or run-time processing costs may be prohibitive to real-time clinical use cases. To address these issues in a critical manner, we systematically review machine learning algorithms for seizure detection with a focus on clinical translatability, assessed by criteria including generalisability, run-time costs, explainability, and clinically-relevant performance metrics. For non-specialists, the domain-specific knowledge necessary to contextualise model development and evaluation is provided. It is our hope that such critical evaluation of machine learning algorithms with respect to their potential real-world effectiveness can help accelerate clinical translation and identify gaps in the current seizure detection literature.
Authors: Tian Xie, Xueru Zhang
Abstract: This paper studies algorithmic decision-making in the presence of strategic individual behaviors, where an ML model is used to make decisions about human agents and the latter can adapt their behavior strategically to improve their future data. Existing results on strategic learning have largely focused on the linear setting where agents with linear labeling functions best respond to a (noisy) linear decision policy. Instead, this work focuses on general non-linear settings where agents respond to the decision policy with only "local information" of the policy. Moreover, we simultaneously consider the objectives of maximizing decision-maker welfare (model prediction accuracy), social welfare (agent improvement caused by strategic behaviors), and agent welfare (the extent that ML underestimates the agents). We first generalize the agent best response model in previous works to the non-linear setting, then reveal the compatibility of welfare objectives. We show the three welfare can attain the optimum simultaneously only under restrictive conditions which are challenging to achieve in non-linear settings. The theoretical results imply that existing works solely maximizing the welfare of a subset of parties inevitably diminish the welfare of the others. We thus claim the necessity of balancing the welfare of each party in non-linear settings and propose an irreducible optimization algorithm suitable for general strategic learning. Experiments on synthetic and real data validate the proposed algorithm.
Authors: Dinuka Sandun Udayantha, Kavindu Weerasinghe, Nima Wickramasinghe, Akila Abeyratne, Kithmin Wickremasinghe, Jithangi Wanigasinghe, Anjula De Silva, Chamira U. S. Edussooriya
Abstract: The neonatal period is the most vulnerable time for the development of seizures. Seizures in the immature brain lead to detrimental consequences, therefore require early diagnosis. The gold-standard for neonatal seizure detection currently relies on continuous video-EEG monitoring; which involves recording multi-channel electroencephalogram (EEG) alongside real-time video monitoring within a neonatal intensive care unit (NICU). However, video-EEG monitoring technology requires clinical expertise and is often limited to technologically advanced and resourceful settings. Cost-effective new techniques could help the medical fraternity make an accurate diagnosis and advocate treatment without delay. In this work, a novel explainable deep learning model to automate the neonatal seizure detection process with a reduced EEG montage is proposed, which employs convolutional nets, graph attention layers, and fully connected layers. Beyond its ability to detect seizures in real-time with a reduced montage, this model offers the unique advantage of real-time interpretability. By evaluating the performance on the Zenodo dataset with 10-fold cross-validation, the presented model achieves an absolute improvement of 8.31% and 42.86% in area under curve (AUC) and recall, respectively.
Authors: Zixiang Wang, Hao Yan, Yining Wang, Zhengjia Xu, Zhuoyue Wang, Zhizhong Wu
Abstract: Reinforcement learning continuously optimizes decision-making based on real-time feedback reward signals through continuous interaction with the environment, demonstrating strong adaptive and self-learning capabilities. In recent years, it has become one of the key methods to achieve autonomous navigation of robots. In this work, an autonomous robot navigation method based on reinforcement learning is introduced. We use the Deep Q Network (DQN) and Proximal Policy Optimization (PPO) models to optimize the path planning and decision-making process through the continuous interaction between the robot and the environment, and the reward signals with real-time feedback. By combining the Q-value function with the deep neural network, deep Q network can handle high-dimensional state space, so as to realize path planning in complex environments. Proximal policy optimization is a strategy gradient-based method, which enables robots to explore and utilize environmental information more efficiently by optimizing policy functions. These methods not only improve the robot's navigation ability in the unknown environment, but also enhance its adaptive and self-learning capabilities. Through multiple training and simulation experiments, we have verified the effectiveness and robustness of these models in various complex scenarios.
Authors: Stefanos Pertigkiozoglou, Evangelos Chatzipantazis, Kostas Daniilidis
Abstract: The goal of this paper is to address the problem of global point cloud registration (PCR) i.e., finding the optimal alignment between point clouds irrespective of the initial poses of the scans. This problem is notoriously challenging for classical optimization methods due to computational constraints. First, we show that state-of-the-art deep learning methods suffer from huge performance degradation when the point clouds are arbitrarily placed in space. We propose that equivariant deep learning should be utilized for solving this task and we characterize the specific type of bi-equivariance of PCR. Then, we design BiEquiformer a novel and scalable bi-equivariant pipeline i.e. equivariant to the independent transformations of the input point clouds. While a naive approach would process the point clouds independently we design expressive bi-equivariant layers that fuse the information from both point clouds. This allows us to extract high-quality superpoint correspondences and in turn, robust point-cloud registration. Extensive comparisons against state-of-the-art methods show that our method achieves comparable performance in the canonical setting and superior performance in the robust setting in both the 3DMatch and the challenging low-overlap 3DLoMatch dataset.
Authors: Desta Haileselassie Hagos, Rick Battle, Danda B. Rawat
Abstract: The emergence of Generative Artificial Intelligence (AI) and Large Language Models (LLMs) has marked a new era of Natural Language Processing (NLP), introducing unprecedented capabilities that are revolutionizing various domains. This paper explores the current state of these cutting-edge technologies, demonstrating their remarkable advancements and wide-ranging applications. Our paper contributes to providing a holistic perspective on the technical foundations, practical applications, and emerging challenges within the evolving landscape of Generative AI and LLMs. We believe that understanding the generative capabilities of AI systems and the specific context of LLMs is crucial for researchers, practitioners, and policymakers to collaboratively shape the responsible and ethical integration of these technologies into various domains. Furthermore, we identify and address main research gaps, providing valuable insights to guide future research endeavors within the AI research community.
Authors: Bailu Ding, Jiaqi Zhai
Abstract: Retrieval plays a fundamental role in recommendation systems, search, and natural language processing by efficiently finding relevant items from a large corpus given a query. Dot products have been widely used as the similarity function in such retrieval tasks, thanks to Maximum Inner Product Search (MIPS) that enabled efficient retrieval based on dot products. However, state-of-the-art retrieval algorithms have migrated to learned similarities. Such algorithms vary in form; the queries can be represented with multiple embeddings, complex neural networks can be deployed, the item ids can be decoded directly from queries using beam search, and multiple approaches can be combined in hybrid solutions. Unfortunately, we lack efficient solutions for retrieval in these state-of-the-art setups. Our work investigates techniques for approximate nearest neighbor search with learned similarity functions. We first prove that Mixture-of-Logits (MoL) is a universal approximator, and can express all learned similarity functions. We next propose techniques to retrieve the approximate top K results using MoL with a tight bound. We finally compare our techniques with existing approaches, showing that MoL sets new state-of-the-art results on recommendation retrieval tasks, and our approximate top-k retrieval with learned similarities outperforms baselines by up to two orders of magnitude in latency, while achieving > .99 recall rate of exact algorithms.
Authors: Emanuele Frascaroli, Aniello Panariello, Pietro Buzzega, Lorenzo Bonicelli, Angelo Porrello, Simone Calderara
Abstract: With the emergence of Transformers and Vision-Language Models (VLMs) such as CLIP, fine-tuning large pre-trained models has recently become a prevalent strategy in Continual Learning. This has led to the development of numerous prompting strategies to adapt transformer-based models without incurring catastrophic forgetting. However, these strategies often compromise the original zero-shot capabilities of the pre-trained CLIP model and struggle to adapt to domains that significantly deviate from the pre-training data. In this work, we propose Continual Generative training for Incremental prompt-Learning, a simple and novel approach to mitigate forgetting while adapting CLIP. Briefly, we employ Variational Autoencoders (VAEs) to learn class-conditioned distributions within the embedding space of the visual encoder. We then exploit these distributions to sample new synthetic visual embeddings and train the corresponding class-specific textual prompts during subsequent tasks. Through extensive experiments on different domains, we show that such a generative replay approach can adapt to new tasks while improving zero-shot capabilities, evaluated using a novel metric tailored for CL scenarios. Notably, further analysis reveals that our approach can bridge the gap with joint prompt tuning. The codebase is available at https://github.com/aimagelab/mammoth.
Authors: Benedikt H\"oltgen, Robert C. Williamson
Abstract: The most common approach to causal modelling is the potential outcomes framework due to Neyman and Rubin. In this framework, outcomes of counterfactual treatments are assumed to be well-defined. This metaphysical assumption is often thought to be problematic yet indispensable. The conventional approach relies not only on counterfactuals but also on abstract notions of distributions and assumptions of independence that are not directly testable. In this paper, we construe causal inference as treatment-wise predictions for finite populations where all assumptions are testable; this means that one can not only test predictions themselves (without any fundamental problem) but also investigate sources of error when they fail. The new framework highlights the model-dependence of causal claims as well as the difference between statistical and scientific inference.
Authors: Tiago Monteiro
Abstract: In quantitative finance, machine learning methods are essential for alpha generation. This study introduces a new approach that combines Hidden Markov Models (HMM) and neural networks, integrated with Black-Litterman portfolio optimization. During the COVID period (2019-2022), this dual-model approach achieved a 83% return with a Sharpe ratio of 0.77. It incorporates two risk models to enhance risk management, showing efficiency during volatile periods. The methodology was implemented on the QuantConnect platform, which was chosen for its robust framework and experimental reproducibility. The system, which predicts future price movements, includes a three-year warm-up to ensure proper algorithm function. It targets highly liquid, large-cap energy stocks to ensure stable and predictable performance while also considering broker payments. The dual-model alpha system utilizes log returns to select the optimal state based on the historical performance. It combines state predictions with neural network outputs, which are based on historical data, to generate trading signals. This study examined the architecture of the trading system, data pre-processing, training, and performance. The full code and backtesting data are available under the QuantConnect terms.
Authors: Sixiao Zhang, Cheng Long, Wei Yuan, Hongxu Chen, Hongzhi Yin
Abstract: Recommender systems embody significant commercial value and represent crucial intellectual property. However, the integrity of these systems is constantly challenged by malicious actors seeking to steal their underlying models. Safeguarding against such threats is paramount to upholding the rights and interests of the model owner. While model watermarking has emerged as a potent defense mechanism in various domains, its direct application to recommender systems remains unexplored and non-trivial. In this paper, we address this gap by introducing Autoregressive Out-of-distribution Watermarking (AOW), a novel technique tailored specifically for recommender systems. Our approach entails selecting an initial item and querying it through the oracle model, followed by the selection of subsequent items with small prediction scores. This iterative process generates a watermark sequence autoregressively, which is then ingrained into the model's memory through training. To assess the efficacy of the watermark, the model is tasked with predicting the subsequent item given a truncated watermark sequence. Through extensive experimentation and analysis, we demonstrate the superior performance and robust properties of AOW. Notably, our watermarking technique exhibits high-confidence extraction capabilities and maintains effectiveness even in the face of distillation and fine-tuning processes.
Authors: Sz-Ting Tzeng, Nirav Ajmeri, Munindar P. Singh
Abstract: We propose Exanna, a framework to realize agents that incorporate values in decision making. An Exannaagent considers the values of itself and others when providing rationales for its actions and evaluating the rationales provided by others. Via multiagent simulation, we demonstrate that considering values in decision making and producing rationales, especially for norm-deviating actions, leads to (1) higher conflict resolution, (2) better social experience, (3) higher privacy, and (4) higher flexibility.
Authors: Danil Gusak, Gleb Mezentsev, Ivan Oseledets, Evgeny Frolov
Abstract: Scalability is a major challenge in modern recommender systems. In sequential recommendations, full Cross-Entropy (CE) loss achieves state-of-the-art recommendation quality but consumes excessive GPU memory with large item catalogs, limiting its practicality. Using a GPU-efficient locality-sensitive hashing-like algorithm for approximating large tensor of logits, this paper introduces a novel RECE (REduced Cross-Entropy) loss. RECE significantly reduces memory consumption while allowing one to enjoy the state-of-the-art performance of full CE loss. Experimental results on various datasets show that RECE cuts training peak memory usage by up to 12 times compared to existing methods while retaining or exceeding performance metrics of CE loss. The approach also opens up new possibilities for large-scale applications in other domains.
Authors: Xueyan Li, Xinyan Chen, Yazhe Niu, Shuai Hu, Yu Liu
Abstract: In the field of psychology, traditional assessment methods, such as standardized scales, are frequently critiqued for their static nature, lack of personalization, and reduced participant engagement, while comprehensive counseling evaluations are often inaccessible. The complexity of quantifying psychological traits further limits these methods. Despite advances with large language models (LLMs), many still depend on single-round Question-and-Answer interactions. To bridge this gap, we introduce PsyDI, a personalized and progressively in-depth chatbot designed for psychological measurements, exemplified by its application in the Myers-Briggs Type Indicator (MBTI) framework. PsyDI leverages user-related multi-modal information and engages in customized, multi-turn interactions to provide personalized, easily accessible measurements, while ensuring precise MBTI type determination. To address the challenge of unquantifiable psychological traits, we introduce a novel training paradigm that involves learning the ranking of proxy variables associated with these traits, culminating in a robust score model for MBTI measurements. The score model enables PsyDI to conduct comprehensive and precise measurements through multi-turn interactions within a unified estimation context. Through various experiments, we validate the efficacy of both the score model and the PsyDI pipeline, demonstrating its potential to serve as a general framework for psychological measurements. Furthermore, the online deployment of PsyDI has garnered substantial user engagement, with over 3,000 visits, resulting in the collection of numerous multi-turn dialogues annotated with MBTI types, which facilitates further research.
Authors: Thao Nguyen, Jeffrey Li, Sewoong Oh, Ludwig Schmidt, Jason Weston, Luke Zettlemoyer, Xian Li
Abstract: We propose a new method, instruction back-and-forth translation, to construct high-quality synthetic data grounded in world knowledge for aligning large language models (LLMs). Given documents from a web corpus, we generate and curate synthetic instructions using the backtranslation approach proposed by Li et al.(2023a), and rewrite the responses to improve their quality further based on the initial documents. Fine-tuning with the resulting (backtranslated instruction, rewritten response) pairs yields higher win rates on AlpacaEval than using other common instruction datasets such as Humpback, ShareGPT, Open Orca, Alpaca-GPT4 and Self-instruct. We also demonstrate that rewriting the responses with an LLM outperforms direct distillation, and the two generated text distributions exhibit significant distinction in embedding space. Further analysis shows that our backtranslated instructions are of higher quality than other sources of synthetic instructions, while our responses are more diverse and complex than those obtained from distillation. Overall we find that instruction back-and-forth translation combines the best of both worlds -- making use of the information diversity and quantity found on the web, while ensuring the quality of the responses which is necessary for effective alignment.
Authors: Vasiliy Alekseev, Ilya Lukashevich, Ilia Zharikov, Ilya Vasiliev
Abstract: Deep neural network models have a complex architecture and are overparameterized. The number of parameters is more than the whole dataset, which is highly resource-consuming. This complicates their application and limits its usage on different devices. Reduction in the number of network parameters helps to reduce the size of the model, but at the same time, thoughtlessly applied, can lead to a deterioration in the quality of the network. One way to reduce the number of model parameters is matrix decomposition, where a matrix is represented as a product of smaller matrices. In this paper, we propose a new way of applying the matrix decomposition with respect to the weights of convolutional layers. The essence of the method is to train not all convolutions, but only the subset of convolutions (basis convolutions), and represent the rest as linear combinations of the basis ones. Experiments on models from the ResNet family and the CIFAR-10 dataset demonstrate that basis convolutions can not only reduce the size of the model but also accelerate the forward and backward passes of the network. Another contribution of this work is that we propose a fast method for selecting a subset of network layers in which the use of matrix decomposition does not degrade the quality of the final model.
Authors: Haoyu Qin, Yungang Chen, Qianchuan Jiang, Pengchao Sun, Xiancai Ye, Chao Lin
Abstract: Deep Learning based Weather Prediction (DLWP) models have been improving rapidly over the last few years, surpassing state of the art numerical weather forecasts by significant margins. While much of the optimization effort is focused on training curriculum to extend forecast range in the global context, two aspects remains less explored: limited area modeling and better backbones for weather forecasting. We show in this paper that MetMamba, a DLWP model built on a state-of-the-art state-space model, Mamba, offers notable performance gains and unique advantages over other popular backbones using traditional attention mechanisms and neural operators. We also demonstrate the feasibility of deep learning based limited area modeling via coupled training with a global host model.
Authors: Nayely V\'elez-Cruz, Manfred D. Laubichler
Abstract: The ubiquity of multiscale interactions in complex systems is well-recognized, with development and heredity serving as a prime example of how processes at different temporal scales influence one another. This work introduces a novel multiscale state-space model to explore the dynamic interplay between systems interacting across different time scales, with feedback between each scale. We propose a Bayesian learning framework to estimate unknown states by learning the unknown process noise covariances within this multiscale model. We develop a Particle Gibbs with Ancestor Sampling (PGAS) algorithm for inference and demonstrate through simulations the efficacy of our approach.
Authors: Muhammad Tayyab Khan, Wenhe Feng, Lequn Chen, Ye Han Ng, Nicholas Yew Jin Tan, Seung Ki Moon
Abstract: The integration of Computer-Aided Design (CAD), Computer-Aided Process Planning (CAPP), and Computer-Aided Manufacturing (CAM) plays a crucial role in modern manufacturing, facilitating seamless transitions from digital designs to physical products. However, a significant challenge within this integration is the Automatic Feature Recognition (AFR) of CAD models, especially in the context of hybrid manufacturing that combines subtractive and additive manufacturing processes. Traditional AFR methods, focused mainly on the identification of subtractive (machined) features including holes, fillets, chamfers, pockets, and slots, fail to recognize features pertinent to additive manufacturing. Furthermore, the traditional methods fall short in accurately extracting geometric dimensions and orientations, which are also key factors for effective manufacturing process planning. This paper presents a novel approach for creating a synthetic CAD dataset that encompasses features relevant to both additive and subtractive machining through Python Open Cascade. The Hierarchical Graph Convolutional Neural Network (HGCNN) model is implemented to accurately identify the composite additive-subtractive features within the synthetic CAD dataset. The key novelty and contribution of the proposed methodology lie in its ability to recognize a wide range of manufacturing features, and precisely extracting their dimensions, orientations, and stock sizes. The proposed model demonstrates remarkable feature recognition accuracy exceeding 97% and a dimension extraction accuracy of 100% for identified features. Therefore, the proposed methodology enhances the integration of CAD, CAPP, and CAM within hybrid manufacturing by providing precise feature recognition and dimension extraction. It facilitates improved manufacturing process planning, by enabling more informed decision-making.