Authors: Siddhant Kharbanda, Devaansh Gupta, Erik Schultheis, Atmadeep Banerjee, Cho-Jui Hsieh, Rohit Babbar
Abstract: Extreme Multi-label Text Classification (XMC) involves learning a classifier that can assign an input with a subset of most relevant labels from millions of label choices. Recent works in this domain have increasingly focused on a symmetric problem setting where both input instances and label features are short-text in nature. Short-text XMC with label features has found numerous applications in areas such as query-to-ad-phrase matching in search ads, title-based product recommendation, prediction of related searches. In this paper, we propose Gandalf, a novel approach which makes use of a label co-occurrence graph to leverage label features as additional data points to supplement the training distribution. By exploiting the characteristics of the short-text XMC problem, it leverages the label features to construct valid training instances, and uses the label graph for generating the corresponding soft-label targets, hence effectively capturing the label-label correlations. Surprisingly, models trained on these new training instances, although being less than half of the original dataset, can outperform models trained on the original dataset, particularly on the PSP@k metric for tail labels. With this insight, we aim to train existing XMC algorithms on both, the original and new training instances, leading to an average 5% relative improvements for 6 state-of-the-art algorithms across 4 benchmark datasets consisting of up to 1.3M labels. Gandalf can be applied in a plug-and-play manner to various methods and thus forwards the state-of-the-art in the domain, without incurring any additional computational overheads.
Authors: Chris Junchi Li
Abstract: Federated learning (FL) for minimax optimization has emerged as a powerful paradigm for training models across distributed nodes/clients while preserving data privacy and model robustness on data heterogeneity. In this work, we delve into the decentralized implementation of federated minimax optimization by proposing \texttt{K-GT-Minimax}, a novel decentralized minimax optimization algorithm that combines local updates and gradient tracking techniques. Our analysis showcases the algorithm's communication efficiency and convergence rate for nonconvex-strongly-concave (NC-SC) minimax optimization, demonstrating a superior convergence rate compared to existing methods. \texttt{K-GT-Minimax}'s ability to handle data heterogeneity and ensure robustness underscores its significance in advancing federated learning research and applications.
Authors: Joseph Janssen, Ardalan Tootchi, Ali A. Ameli
Abstract: Fine-resolution spatial patterns of water table depth (WTD) can inform the dynamics of groundwater-dependent systems, including ecological, hydrological, and anthropogenic systems. Generally, a large-scale (e.g., continental or global) spatial map of static WTD can be simulated using either physically-based (PB) or machine learning-based (ML) models. We construct three fine-resolution (500 m) ML simulations of WTD, using the XGBoost algorithm and more than 20 million real and proxy observations of WTD, across the United States and Canada. The three ML models were constrained using known physical relations between WTD's drivers and WTD and were trained by sequentially adding real and proxy observations of WTD. We interpret the black box of our physically constrained ML models and compare it against available literature in groundwater hydrology. Through an extensive (pixel-by-pixel) evaluation, we demonstrate that our models can more accurately predict unseen real and proxy observations of WTD across most of North America's ecoregions compared to three available PB simulations of WTD. However, we still argue that large-scale WTD estimation is far from being a solved problem. We reason that due to biased and untrustworthy observational data, the misspecification of physically-based equations, and the over-flexibility of machine learning models, our community's confidence in ML or PB simulations of WTD is far too high and verifiably accurate simulations of WTD do not yet exist in the literature, particularly in arid high-elevation landscapes. Ultimately, we thoroughly discuss future directions that may help hydrogeologists decide how to proceed with WTD estimations, with a particular focus on the application of machine learning.
Authors: Alexander W. Rogers, Amanda Lane, Cesar Mendoza, Simon Watson, Adam Kowalski, Philip Martin, Dongda Zhang
Abstract: New products must be formulated rapidly to succeed in the global formulated product market; however, key product indicators (KPIs) can be complex, poorly understood functions of the chemical composition and processing history. Consequently, scale-up must currently undergo expensive trial-and-error campaigns. To accelerate process flow diagram (PFD) optimisation and knowledge discovery, this work proposed a novel digital framework to automatically quantify process mechanisms by integrating symbolic regression (SR) within model-based design of experiments (MBDoE). Each iteration, SR proposed a Pareto front of interpretable mechanistic expressions, and then MBDoE designed a new experiment to discriminate between them while balancing PFD optimisation. To investigate the framework's performance, a new process model capable of simulating general formulated product synthesis was constructed to generate in-silico data for different case studies. The framework could effectively discover ground-truth process mechanisms within a few iterations, indicating its great potential for use within the general chemical industry for digital manufacturing and product innovation.
Authors: Makbule Gulcin Ozsoy
Abstract: Recommender systems guide users through vast amounts of information by suggesting items based on their predicted preferences. Collaborative filtering-based deep learning techniques have regained popularity due to their straightforward nature, relying only on user-item interactions. Typically, these systems consist of three main components: an interaction module, a loss function, and a negative sampling strategy. Initially, researchers focused on enhancing performance by developing complex interaction modules. However, there has been a recent shift toward refining loss functions and negative sampling strategies. This shift has led to an increased interest in contrastive learning, which pulls similar pairs closer while pushing dissimilar ones apart. Contrastive learning involves key practices such as heavy data augmentation, large batch sizes, and hard-negative sampling, but these also bring challenges like high memory demands and under-utilization of some negative samples. The proposed Multi-Margin Loss (MML) addresses these challenges by introducing multiple margins and varying weights for negative samples. This allows MML to efficiently utilize not only the hardest negatives but also other non-trivial negatives, offering a simpler yet effective loss function that outperforms more complex methods, especially when resources are limited. Experiments on two well-known datasets demonstrated that MML achieved up to a 20% performance improvement compared to a baseline contrastive loss function when fewer number of negative samples are used.
Authors: Sanath Kumar Krishnamurthy, Susan Athey, Emma Brunskill
Abstract: We formulate the problem of constructing multiple simultaneously valid confidence intervals (CIs) as estimating a high probability upper bound on the maximum error for a class/set of estimate-estimand-error tuples, and refer to this as the error estimation problem. For a single such tuple, data-driven confidence intervals can often be used to bound the error in our estimate. However, for a class of estimate-estimand-error tuples, nontrivial high probability upper bounds on the maximum error often require class complexity as input -- limiting the practicality of such methods and often resulting in loose bounds. Rather than deriving theoretical class complexity-based bounds, we propose a completely data-driven approach to estimate an upper bound on the maximum error. The simple and general nature of our solution to this fundamental challenge lends itself to several applications including: multiple CI construction, multiple hypothesis testing, estimating excess risk bounds (a fundamental measure of uncertainty in machine learning) for any training/fine-tuning algorithm, and enabling the development of a contextual bandit pipeline that can leverage any reward model estimation procedure as input (without additional mathematical analysis).
Authors: Albert Bou, Morgan Thomas, Sebastian Dittert, Carles Navarro Ram\'irez, Maciej Majewski, Ye Wang, Shivam Patel, Gary Tresadern, Mazen Ahmad, Vincent Moens, Woody Sherman, Simone Sciabola, Gianni De Fabritiis
Abstract: In recent years, reinforcement learning (RL) has emerged as a valuable tool in drug design, offering the potential to propose and optimize molecules with desired properties. However, striking a balance between capability, flexibility, and reliability remains challenging due to the complexity of advanced RL algorithms and the significant reliance on specialized code. In this work, we introduce ACEGEN, a comprehensive and streamlined toolkit tailored for generative drug design, built using TorchRL, a modern decision-making library that offers efficient and thoroughly tested reusable components. ACEGEN provides a robust, flexible, and efficient platform for molecular design. We validate its effectiveness by benchmarking it across various algorithms and conducting multiple drug discovery case studies. ACEGEN is accessible at https://github.com/acellera/acegen-open.
Authors: Andrei Lixandru
Abstract: Proximal Policy Optimization with Adaptive Exploration (axPPO) is introduced as a novel learning algorithm. This paper investigates the exploration-exploitation tradeoff within the context of reinforcement learning and aims to contribute new insights into reinforcement learning algorithm design. The proposed adaptive exploration framework dynamically adjusts the exploration magnitude during training based on the recent performance of the agent. Our proposed method outperforms standard PPO algorithms in learning efficiency, particularly when significant exploratory behavior is needed at the beginning of the learning process.
Authors: Hanlin Zhu, Baihe Huang, Shaolun Zhang, Michael Jordan, Jiantao Jiao, Yuandong Tian, Stuart Russell
Abstract: Auto-regressive large language models (LLMs) show impressive capacities to solve many complex reasoning tasks while struggling with some simple logical reasoning tasks such as inverse search: when trained on ''A is B'', LLM fails to directly conclude ''B is A'' during inference, which is known as the ''reversal curse'' (Berglund et al., 2023). In this paper, we theoretically analyze the reversal curse via the training dynamics of (stochastic) gradient descent for two auto-regressive models: (1) a bilinear model that can be viewed as a simplification of a one-layer transformer; (2) one-layer transformers using the framework of Tian et al. (2023a). Our analysis reveals a core reason why the reversal curse happens: the (effective) weights of both auto-regressive models show asymmetry, i.e., the increase of weights from a token $A$ to token $B$ during training does not necessarily cause the increase of the weights from $B$ to $A$. Moreover, our analysis can be naturally applied to other logical reasoning tasks such as chain-of-thought (COT) (Wei et al., 2022b). We show the necessity of COT, i.e., a model trained on ''$A \to B$'' and ''$B \to C$'' fails to directly conclude ''$A \to C$'' without COT (also empirically observed by Allen-Zhu and Li (2023)), for one-layer transformers via training dynamics, which provides a new perspective different from previous work (Feng et al., 2024) that focuses on expressivity. Finally, we also conduct experiments to validate our theory on multi-layer transformers under different settings.
Authors: Saurabh Varshneya, Antoine Ledent, Philipp Liznerski, Andriy Balinskyy, Purvanshi Mehta, Waleed Mustafa, Marius Kloft
Abstract: Conventional machine learning methods are predominantly designed to predict outcomes based on a single data type. However, practical applications may encompass data of diverse types, such as text, images, and audio. We introduce interpretable tensor fusion (InTense), a multimodal learning method for training neural networks to simultaneously learn multimodal data representations and their interpretable fusion. InTense can separately capture both linear combinations and multiplicative interactions of diverse data types, thereby disentangling higher-order interactions from the individual effects of each modality. InTense provides interpretability out of the box by assigning relevance scores to modalities and their associations. The approach is theoretically grounded and yields meaningful relevance scores on multiple synthetic and real-world datasets. Experiments on six real-world datasets show that InTense outperforms existing state-of-the-art multimodal interpretable approaches in terms of accuracy and interpretability.
Authors: Ruiyang Qin, Zheyu Yan, Dewen Zeng, Zhenge Jia, Dancheng Liu, Jianbo Liu, Zhi Zheng, Ningyuan Cao, Kai Ni, Jinjun Xiong, Yiyu Shi
Abstract: Large Language Models (LLMs) deployed on edge devices learn through fine-tuning and updating a certain portion of their parameters. Although such learning methods can be optimized to reduce resource utilization, the overall required resources remain a heavy burden on edge devices. Instead, Retrieval-Augmented Generation (RAG), a resource-efficient LLM learning method, can improve the quality of the LLM-generated content without updating model parameters. However, the RAG-based LLM may involve repetitive searches on the profile data in every user-LLM interaction. This search can lead to significant latency along with the accumulation of user data. Conventional efforts to decrease latency result in restricting the size of saved user data, thus reducing the scalability of RAG as user data continuously grows. It remains an open question: how to free RAG from the constraints of latency and scalability on edge devices? In this paper, we propose a novel framework to accelerate RAG via Computing-in-Memory (CiM) architectures. It accelerates matrix multiplications by performing in-situ computation inside the memory while avoiding the expensive data transfer between the computing unit and memory. Our framework, Robust CiM-backed RAG (RoCR), utilizing a novel contrastive learning-based training method and noise-aware training, can enable RAG to efficiently search profile data with CiM. To the best of our knowledge, this is the first work utilizing CiM to accelerate RAG.
Authors: Kai-Chia Mo, Shai Shalev-Shwartz, Nis{\ae}l Sh\'artov
Abstract: We describe a novel subgradient following apparatus for calculating the optimum of convex problems with variational penalties. In this setting, we receive a sequence $y_i,\ldots,y_n$ and seek a smooth sequence $x_1,\ldots,x_n$. The smooth sequence attains the minimum Bregman divergence to an input sequence with additive variational penalties in the general form of $\sum_i g_i(x_{i+1}-x_i)$. We derive, as special cases of our apparatus, known algorithms for the fused lasso and isotonic regression. Our approach also facilitates new variational penalties such as non-smooth barrier functions. We next derive and analyze multivariate problems in which $\mathbf{x}_i,\mathbf{y}_i\in\mathbb{R}^d$ and variational penalties that depend on $\|\mathbf{x}_{i+1}-\mathbf{x}_i\|$. The norms we consider are $\ell_2$ and $\ell_\infty$ which promote group sparsity. Last but not least, we derive a lattice-based subgradient following for variational penalties characterized through the output of arbitrary convolutional filters. This paradigm yields efficient solvers for problems in which sparse high-order discrete derivatives such as acceleration and jerk are desirable.
Authors: Yongze Wang, Haimin Zhang, Qiang Wu, Min Xu
Abstract: Graph neural networks (GNNs) have shown great success in learning from graph-based data. The key mechanism of current GNNs is message passing, where a node's feature is updated based on the information passing from its local neighbourhood. A limitation of this mechanism is that node features become increasingly dominated by the information aggregated from the neighbourhood as we use more rounds of message passing. Consequently, as the GNN layers become deeper, adjacent node features tends to be similar, making it more difficult for GNNs to distinguish adjacent nodes, thereby, limiting the performance of GNNs. In this paper, we propose conditional local feature encoding (CLFE) to help prevent the problem of node features being dominated by the information from local neighbourhood. The idea of our method is to extract the node hidden state embedding from message passing process and concatenate it with the nodes feature from previous stage, then we utilise linear transformation to form a CLFE based on the concatenated vector. The CLFE will form the layer output to better preserve node-specific information, thus help to improve the performance of GNN models. To verify the feasibility of our method, we conducted extensive experiments on seven benchmark datasets for four graph domain tasks: super-pixel graph classification, node classification, link prediction, and graph regression. The experimental results consistently demonstrate that our method improves model performance across a variety of baseline GNN models for all four tasks.
Authors: Pengyu Zhang, Yingjie Liu, Yingbo Zhou, Xiao Du, Xian Wei, Ting Wang, Mingsong Chen
Abstract: Although Federated Learning (FL) enables collaborative learning in Artificial Intelligence of Things (AIoT) design, it fails to work on low-memory AIoT devices due to its heavy memory usage. To address this problem, various federated pruning methods are proposed to reduce memory usage during inference. However, few of them can substantially mitigate the memory burdens during pruning and training. As an alternative, zeroth-order or backpropagation-free (BP-Free) methods can partially alleviate the memory consumption, but they suffer from scaling up and large computation overheads, since the gradient estimation error and floating point operations (FLOPs) increase as the dimensionality of the model parameters grows. In this paper, we propose a federated foresight pruning method based on Neural Tangent Kernel (NTK), which can seamlessly integrate with federated BP-Free training frameworks. We present an approximation to the computation of federated NTK by using the local NTK matrices. Moreover, we demonstrate that the data-free property of our method can substantially reduce the approximation error in extreme data heterogeneity scenarios. Since our approach improves the performance of the vanilla BP-Free method with fewer FLOPs and truly alleviates memory pressure during training and inference, it makes FL more friendly to low-memory devices. Comprehensive experimental results obtained from simulation- and real test-bed-based platforms show that our federated foresight-pruning method not only preserves the ability of the dense model with a memory reduction up to 9x but also boosts the performance of the vanilla BP-Free method with dramatically fewer FLOPs.
Authors: Ryo Ishiyama, Takahiro Shirakawa, Seiichi Uchida, Shinnosuke Matsuo
Abstract: We propose Test-Time Augmentation (TTA) as an effective technique for addressing combinatorial optimization problems, including the Traveling Salesperson Problem. In general, deep learning models possessing the property of invariance, where the output is uniquely determined regardless of the node indices, have been proposed to learn graph structures efficiently. In contrast, we interpret the permutation of node indices, which exchanges the elements of the distance matrix, as a TTA scheme. The results demonstrate that our method is capable of obtaining shorter solutions than the latest models. Furthermore, we show that the probability of finding a solution closer to an exact solution increases depending on the augmentation size.
Authors: Wei Ju, Zhengyang Mao, Siyu Yi, Yifang Qin, Yiyang Gu, Zhiping Xiao, Yifan Wang, Xiao Luo, Ming Zhang
Abstract: In this paper, we study semi-supervised graph classification, which aims at accurately predicting the categories of graphs in scenarios with limited labeled graphs and abundant unlabeled graphs. Despite the promising capability of graph neural networks (GNNs), they typically require a large number of costly labeled graphs, while a wealth of unlabeled graphs fail to be effectively utilized. Moreover, GNNs are inherently limited to encoding local neighborhood information using message-passing mechanisms, thus lacking the ability to model higher-order dependencies among nodes. To tackle these challenges, we propose a Hypergraph-Enhanced DuAL framework named HEAL for semi-supervised graph classification, which captures graph semantics from the perspective of the hypergraph and the line graph, respectively. Specifically, to better explore the higher-order relationships among nodes, we design a hypergraph structure learning to adaptively learn complex node dependencies beyond pairwise relations. Meanwhile, based on the learned hypergraph, we introduce a line graph to capture the interaction between hyperedges, thereby better mining the underlying semantic structures. Finally, we develop a relational consistency learning to facilitate knowledge transfer between the two branches and provide better mutual guidance. Extensive experiments on real-world graph datasets verify the effectiveness of the proposed method against existing state-of-the-art methods.
Authors: Wei Deng, Weijian Luo, Yixin Tan, Marin Bilo\v{s}, Yu Chen, Yuriy Nevmyvaka, Ricky T. Q. Chen
Abstract: Schr\"odinger bridge (SB) has emerged as the go-to method for optimizing transportation plans in diffusion models. However, SB requires estimating the intractable forward score functions, inevitably resulting in the costly implicit training loss based on simulated trajectories. To improve the scalability while preserving efficient transportation plans, we leverage variational inference to linearize the forward score functions (variational scores) of SB and restore simulation-free properties in training backward scores. We propose the variational Schr\"odinger diffusion model (VSDM), where the forward process is a multivariate diffusion and the variational scores are adaptively optimized for efficient transport. Theoretically, we use stochastic approximation to prove the convergence of the variational scores and show the convergence of the adaptively generated samples based on the optimal variational scores. Empirically, we test the algorithm in simulated examples and observe that VSDM is efficient in generations of anisotropic shapes and yields straighter sample trajectories compared to the single-variate diffusion. We also verify the scalability of the algorithm in real-world data and achieve competitive unconditional generation performance in CIFAR10 and conditional generation in time series modeling. Notably, VSDM no longer depends on warm-up initializations and has become tuning-friendly in training large-scale experiments.
Authors: Huy Quang Ung, Hao Niu, Minh-Son Dao, Shinya Wada, Atsunori Minamikawa
Abstract: Traffic predictions play a crucial role in intelligent transportation systems. The rapid development of IoT devices allows us to collect different kinds of data with high correlations to traffic predictions, fostering the development of efficient multi-modal traffic prediction models. Until now, there are few studies focusing on utilizing advantages of multi-modal data for traffic predictions. In this paper, we introduce a novel temporal attentive cross-modality transformer model for long-term traffic predictions, namely xMTrans, with capability of exploring the temporal correlations between the data of two modalities: one target modality (for prediction, e.g., traffic congestion) and one support modality (e.g., people flow). We conducted extensive experiments to evaluate our proposed model on traffic congestion and taxi demand predictions using real-world datasets. The results showed the superiority of xMTrans against recent state-of-the-art methods on long-term traffic predictions. In addition, we also conducted a comprehensive ablation study to further analyze the effectiveness of each module in xMTrans.
Authors: Mandani Ntekouli, Gerasimos Spanakis, Lourens Waldorp, Anne Roefs
Abstract: In the field of psychopathology, Ecological Momentary Assessment (EMA) studies offer rich individual data on psychopathology-relevant variables (e.g., affect, behavior, etc) in real-time. EMA data is collected dynamically, represented as complex multivariate time series (MTS). Such information is crucial for a better understanding of mental disorders at the individual- and group-level. More specifically, clustering individuals in EMA data facilitates uncovering and studying the commonalities as well as variations of groups in the population. Nevertheless, since clustering is an unsupervised task and true EMA grouping is not commonly available, the evaluation of clustering is quite challenging. An important aspect of evaluation is clustering explainability. Thus, this paper proposes an attention-based interpretable framework to identify the important time-points and variables that play primary roles in distinguishing between clusters. A key part of this study is to examine ways to analyze, summarize, and interpret the attention weights as well as evaluate the patterns underlying the important segments of the data that differentiate across clusters. To evaluate the proposed approach, an EMA dataset of 187 individuals grouped in 3 clusters is used for analyzing the derived attention-based importance attributes. More specifically, this analysis provides the distinct characteristics at the cluster-, feature- and individual level. Such clustering explanations could be beneficial for generalizing existing concepts of mental disorders, discovering new insights, and even enhancing our knowledge at an individual level.
Authors: John-Joseph Brady, Yuhui Luo, Wenwu Wang, Victor Elvira, Yunpeng Li
Abstract: Differentiable particle filters are an emerging class of models that combine sequential Monte Carlo techniques with the flexibility of neural networks to perform state space inference. This paper concerns the case where the system may switch between a finite set of state-space models, i.e. regimes. No prior approaches effectively learn both the individual regimes and the switching process simultaneously. In this paper, we propose the neural network based regime learning differentiable particle filter (RLPF) to address this problem. We further design a training procedure for the RLPF and other related algorithms. We demonstrate competitive performance compared to the previous state-of-the-art algorithms on a pair of numerical experiments.
Authors: Jiarong Yang, Yuan Liu
Abstract: Split Federated Learning (SFL) is a distributed machine learning framework which strategically divides the learning process between a server and clients and collaboratively trains a shared model by aggregating local models updated based on data from distributed clients. However, data heterogeneity and partial client participation result in label distribution skew, which severely degrades the learning performance. To address this issue, we propose SFL with Concatenated Activations and Logit Adjustments (SCALA). Specifically, the activations from the client-side models are concatenated as the input of the server-side model so as to centrally adjust label distribution across different clients, and logit adjustments of loss functions on both server-side and client-side models are performed to deal with the label distribution variation across different subsets of participating clients. Theoretical analysis and experimental results verify the superiority of the proposed SCALA on public datasets.
Authors: Rongrong Ma, Guansong Pang, Ling Chen
Abstract: One main challenge in imbalanced graph classification is to learn expressive representations of the graphs in under-represented (minority) classes. Existing generic imbalanced learning methods, such as oversampling and imbalanced learning loss functions, can be adopted for enabling graph representation learning models to cope with this challenge. However, these methods often directly operate on the graph representations, ignoring rich discriminative information within the graphs and their interactions. To tackle this issue, we introduce a novel multi-scale oversampling graph neural network (MOSGNN) that learns expressive minority graph representations based on intra- and inter-graph semantics resulting from oversampled graphs at multiple scales - subgraph, graph, and pairwise graphs. It achieves this by jointly optimizing subgraph-level, graph-level, and pairwise-graph learning tasks to learn the discriminative information embedded within and between the minority graphs. Extensive experiments on 16 imbalanced graph datasets show that MOSGNN i) significantly outperforms five state-of-the-art models, and ii) offers a generic framework, in which different advanced imbalanced learning loss functions can be easily plugged in and obtain significantly improved classification performance.
Authors: Kazuma Shimizu, Junya Honda, Shinji Ito, Shinji Nakadai
Abstract: This paper discusses the revenue management (RM) problem to maximize revenue by pricing items or services. One challenge in this problem is that the demand distribution is unknown and varies over time in real applications such as airline and retail industries. In particular, the time-varying demand has not been well studied under scenarios of unknown demand due to the difficulty of jointly managing the remaining inventory and estimating the demand. To tackle this challenge, we first introduce an episodic generalization of the RM problem motivated by typical application scenarios. We then propose a computationally efficient algorithm based on posterior sampling, which effectively optimizes prices by solving linear programming. We derive a Bayesian regret upper bound of this algorithm for general models where demand parameters can be correlated between time periods, while also deriving a regret lower bound for generic algorithms. Our empirical study shows that the proposed algorithm performs better than other benchmark algorithms and comparably to the optimal policy in hindsight. We also propose a heuristic modification of the proposed algorithm, which further efficiently learns the pricing policy in the experiments.
Authors: Alan A. Lahoud, Erik Schaffernicht, Johannes A. Stork
Abstract: Learning latent costs of transitions on graphs from trajectories demonstrations under various contextual features is challenging but useful for path planning. Yet, existing methods either oversimplify cost assumptions or scale poorly with the number of observed trajectories. This paper introduces DataSP, a differentiable all-to-all shortest path algorithm to facilitate learning latent costs from trajectories. It allows to learn from a large number of trajectories in each learning step without additional computation. Complex latent cost functions from contextual features can be represented in the algorithm through a neural network approximation. We further propose a method to sample paths from DataSP in order to reconstruct/mimic observed paths' distributions. We prove that the inferred distribution follows the maximum entropy principle. We show that DataSP outperforms state-of-the-art differentiable combinatorial solver and classical machine learning approaches in predicting paths on graphs.
Authors: Valentina Zaccaria, Davide Sartor, Simone Del Favero, Gian Antonio Susto
Abstract: This letter presents a novel approach in the field of Active Fault Detection (AFD), by explicitly separating the task into two parts: Passive Fault Detection (PFD) and control input design. This formulation is very general, and most existing AFD literature can be viewed through this lens. By recognizing this separation, PFD methods can be leveraged to provide components that make efficient use of the available information, while the control input is designed in order to optimize the gathering of information. The core contribution of this work is FIERL, a general simulation-based approach for the design of such control strategies, using Constrained Reinforcement Learning (CRL) to optimize the performance of arbitrary passive detectors. The control policy is learned without the need of knowing the passive detector inner workings, making FIERL broadly applicable. However, it is especially useful when paired with the design of an efficient passive component. Unlike most AFD approaches, FIERL can handle fairly complex scenarios such as continuous sets of fault modes. The effectiveness of FIERL is tested on a benchmark problem for actuator fault diagnosis, where FIERL is shown to be fairly robust, being able to generalize to fault dynamics not seen in training.
Authors: Kristupas Bajarunas, Marcia L. Baptista, Kai Goebel, Manuel A. Chao
Abstract: Accurately estimating a Health Index (HI) from condition monitoring data (CM) is essential for reliable and interpretable prognostics and health management (PHM) in complex systems. In most scenarios, complex systems operate under varying operating conditions and can exhibit different fault modes, making unsupervised inference of an HI from CM data a significant challenge. Hybrid models combining prior knowledge about degradation with deep learning models have been proposed to overcome this challenge. However, previously suggested hybrid models for HI estimation usually rely heavily on system-specific information, limiting their transferability to other systems. In this work, we propose an unsupervised hybrid method for HI estimation that integrates general knowledge about degradation into the convolutional autoencoder's model architecture and learning algorithm, enhancing its applicability across various systems. The effectiveness of the proposed method is demonstrated in two case studies from different domains: turbofan engines and lithium batteries. The results show that the proposed method outperforms other competitive alternatives, including residual-based methods, in terms of HI quality and their utility for Remaining Useful Life (RUL) predictions. The case studies also highlight the comparable performance of our proposed method with a supervised model trained with HI labels.
Authors: Redemptor Jr Laceda Taloma, Patrizio Pisani, Danilo Comminiello
Abstract: Time series clustering is fundamental in data analysis for discovering temporal patterns. Despite recent advancements, learning cluster-friendly representations is still challenging, particularly with long and complex time series. Deep temporal clustering methods have been trying to integrate the canonical k-means into end-to-end training of neural networks but fall back on surrogate losses due to the non-differentiability of the hard cluster assignment, yielding sub-optimal solutions. In addition, the autoregressive strategy used in the state-of-the-art RNNs is subject to error accumulation and slow training, while recent research findings have revealed that Transformers are less effective due to time points lacking semantic meaning, to the permutation invariance of attention that discards the chronological order and high computation cost. In light of these observations, we present LoSTer which is a novel dense autoencoder architecture for the long-sequence time series clustering problem (LSTC) capable of optimizing the k-means objective via the Gumbel-softmax reparameterization trick and designed specifically for accurate and fast clustering of long time series. Extensive experiments on numerous benchmark datasets and two real-world applications prove the effectiveness of LoSTer over state-of-the-art RNNs and Transformer-based deep clustering methods.
Authors: Zine el abidine Kherroubi
Abstract: Current autonomous driving systems heavily rely on V2X communication data to enhance situational awareness and the cooperation between vehicles. However, a major challenge when using V2X data is that it may not be available periodically because of unpredictable delays and data loss during wireless transmission between road stations and the receiver vehicle. This issue should be considered when designing control strategies for connected and autonomous vehicles. Therefore, this paper proposes a novel 'Blind Actor-Critic' algorithm that guarantees robust driving performance in V2X environment with delayed and/or lost data. The novel algorithm incorporates three key mechanisms: a virtual fixed sampling period, a combination of Temporal-Difference and Monte Carlo learning, and a numerical approximation of immediate reward values. To address the temporal aperiodicity problem of V2X data, we first illustrate this challenge. Then, we provide a detailed explanation of the Blind Actor-Critic algorithm where we highlight the proposed components to compensate for the temporal aperiodicity problem of V2X data. We evaluate the performance of our algorithm in a simulation environment and compare it to benchmark approaches. The results demonstrate that training metrics are improved compared to conventional actor-critic algorithms. Additionally, testing results show that our approach provides robust control, even under low V2X network reliability levels.
Authors: Xuyang Zhong, Yixiao Huang, Chen Liu
Abstract: This work studies sparse adversarial perturbations bounded by $l_0$ norm. We propose a white-box PGD-like attack method named sparse-PGD to effectively and efficiently generate such perturbations. Furthermore, we combine sparse-PGD with a black-box attack to comprehensively and more reliably evaluate the models' robustness against $l_0$ bounded adversarial perturbations. Moreover, the efficiency of sparse-PGD enables us to conduct adversarial training to build robust models against sparse perturbations. Extensive experiments demonstrate that our proposed attack algorithm exhibits strong performance in different scenarios. More importantly, compared with other robust models, our adversarially trained model demonstrates state-of-the-art robustness against various sparse attacks. Codes are available at https://github.com/CityU-MLO/sPGD.
Authors: Jarek Duda
Abstract: Popular artificial neural networks (ANN) optimize parameters for unidirectional value propagation, assuming some guessed parametrization type like Multi-Layer Perceptron (MLP) or Kolmogorov-Arnold Network (KAN). In contrast, for biological neurons e.g. "it is not uncommon for axonal propagation of action potentials to happen in both directions" \cite{axon} - suggesting they are optimized to continuously operate in multidirectional way. Additionally, statistical dependencies a single neuron could model is not just (expected) value dependence, but entire joint distributions including also higher moments. Such agnostic joint distribution neuron would allow for multidirectional propagation (of distributions or values) e.g. $\rho(x|y,z)$ or $\rho(y,z|x)$ by substituting to $\rho(x,y,z)$ and normalizing. There will be discussed Hierarchical Correlation Reconstruction (HCR) for such neuron model: assuming $\rho(x,y,z)=\sum_{ijk} a_{ijk} f_i(x) f_j(y) f_k(z)$ type parametrization of joint distribution with polynomial basis $f_i$, which allows for flexible, inexpensive processing including nonlinearities, direct model estimation and update, trained through standard backpropagation or novel ways for such structure up to tensor decomposition. Using only pairwise (input-output) dependencies, its expected value prediction becomes KAN-like with trained activation functions as polynomials, can be extended by adding higher order dependencies through included products - in conscious interpretable way, allowing for multidirectional propagation of both values and probability densities.
Authors: Hengyue Liang, Le Peng, Ju Sun
Abstract: In selective classification (SC), a classifier abstains from making predictions that are likely to be wrong to avoid excessive errors. To deploy imperfect classifiers -- imperfect either due to intrinsic statistical noise of data or for robustness issue of the classifier or beyond -- in high-stakes scenarios, SC appears to be an attractive and necessary path to follow. Despite decades of research in SC, most previous SC methods still focus on the ideal statistical setting only, i.e., the data distribution at deployment is the same as that of training, although practical data can come from the wild. To bridge this gap, in this paper, we propose an SC framework that takes into account distribution shifts, termed generalized selective classification, that covers label-shifted (or out-of-distribution) and covariate-shifted samples, in addition to typical in-distribution samples, the first of its kind in the SC literature. We focus on non-training-based confidence-score functions for generalized SC on deep learning (DL) classifiers and propose two novel margin-based score functions. Through extensive analysis and experiments, we show that our proposed score functions are more effective and reliable than the existing ones for generalized SC on a variety of classification tasks and DL classifiers.
Authors: Matt Schoenbauer, Daniele Moro, Lukasz Lew, Andrew Howard
Abstract: Quantization-aware training comes with a fundamental challenge: the derivative of quantization functions such as rounding are zero almost everywhere and nonexistent elsewhere. Various differentiable approximations of quantization functions have been proposed to address this issue. In this paper, we prove that when the learning rate is sufficiently small, a large class of weight gradient estimators is equivalent with the straight through estimator (STE). Specifically, after swapping in the STE and adjusting both the weight initialization and the learning rate in SGD, the model will train in almost exactly the same way as it did with the original gradient estimator. Moreover, we show that for adaptive learning rate algorithms like Adam, the same result can be seen without any modifications to the weight initialization and learning rate. We experimentally show that these results hold for both a small convolutional model trained on the MNIST dataset and for a ResNet50 model trained on ImageNet.
Authors: Jiuxiang Gu, Yingyu Liang, Heshan Liu, Zhenmei Shi, Zhao Song, Junze Yin
Abstract: Large Language Models (LLMs) have profoundly changed the world. Their self-attention mechanism is the key to the success of transformers in LLMs. However, the quadratic computational cost $O(n^2)$ to the length $n$ input sequence is the notorious obstacle for further improvement and scalability in the longer context. In this work, we leverage the convolution-like structure of attention matrices to develop an efficient approximation method for attention computation using convolution matrices. We propose a $\mathsf{conv}$ basis system, "similar" to the rank basis, and show that any lower triangular (attention) matrix can always be decomposed as a sum of $k$ structured convolution matrices in this basis system. We then design an algorithm to quickly decompose the attention matrix into $k$ convolution matrices. Thanks to Fast Fourier Transforms (FFT), the attention {\it inference} can be computed in $O(knd \log n)$ time, where $d$ is the hidden dimension. In practice, we have $ d \ll n$, i.e., $d=3,072$ and $n=1,000,000$ for Gemma. Thus, when $kd = n^{o(1)}$, our algorithm achieve almost linear time, i.e., $n^{1+o(1)}$. Furthermore, the attention {\it training forward} and {\it backward gradient} can be computed in $n^{1+o(1)}$ as well. Our approach can avoid explicitly computing the $n \times n$ attention matrix, which may largely alleviate the quadratic computational complexity. Furthermore, our algorithm works on any input matrices. This work provides a new paradigm for accelerating attention computation in transformers to enable their application to longer contexts.
Authors: Renjie Liu, Yichuan Wang, Xiao Yan, Zhenkun Cai, Minjie Wang, Haitian Jiang, Bo Tang, Jinyang Li
Abstract: Graph neural networks (GNNs) are machine learning models specialized for graph data and widely used in many applications. To train GNNs on large graphs that exceed CPU memory, several systems store data on disk and conduct out-of-core processing. However, these systems suffer from either read amplification when reading node features that are usually smaller than a disk page or degraded model accuracy by treating the graph as disconnected partitions. To close this gap, we build a system called DiskGNN, which achieves high I/O efficiency and thus fast training without hurting model accuracy. The key technique used by DiskGNN is offline sampling, which helps decouple graph sampling from model computation. In particular, by conducting graph sampling beforehand, DiskGNN acquires the node features that will be accessed by model computation, and such information is utilized to pack the target node features contiguously on disk to avoid read amplification. Besides, \name{} also adopts designs including four-level feature store to fully utilize the memory hierarchy to cache node features and reduce disk access, batched packing to accelerate the feature packing process, and pipelined training to overlap disk access with other operations. We compare DiskGNN with Ginex and MariusGNN, which are state-of-the-art systems for out-of-core GNN training. The results show that DiskGNN can speed up the baselines by over 8x while matching their best model accuracy.
Authors: Lucas K. Johnson (State University of New York College of Environmental Science and Forestry), Michael J. Mahoney (State University of New York College of Environmental Science and Forestry), Grant Domke (USDA Forest Service), Colin M. Beier (State University of New York College of Environmental Science and Forestry)
Abstract: The United States national forest inventory (NFI) serves as the foundation for forest aboveground biomass (AGB) and carbon accounting across the nation. These data enable design-based estimates of forest carbon stocks and stock-changes at state and regional levels, but also serve as inputs to model-based approaches for characterizing forest carbon stocks and stock-changes at finer resolutions. Although NFI tree and plot-level data are often treated as truth in these models, they are in fact estimates based on regional species-group models known collectively as the Component Ratio Method (CRM). In late 2023 the Forest Inventory and Analysis (FIA) program introduced a new National Scale Volume and Biomass Estimators (NSVB) system to replace CRM nationwide and offer more precise and accurate representations of forest AGB and carbon. Given the prevalence of model-based AGB studies relying on FIA, there is concern about the transferability of methods from CRM to NSVB models, as well as the comparability of existing CRM AGB products (e.g. maps) to new and forthcoming NSVB AGB products. To begin addressing these concerns we compared previously published CRM AGB maps to new maps produced using identical methods with NSVB AGB reference data. Our results suggest that models relying on passive satellite imagery (e.g. Landsat) provide acceptable estimates of point-in-time NSVB AGB and carbon stocks, but fail to accurately quantify growth in mature closed-canopy forests. We highlight that existing estimates, models, and maps based on FIA reference data are no longer compatible with NSVB, and recommend new methods as well as updated models and maps for accommodating this step-change. Our collective ability to adopt NSVB in our modeling and mapping workflows will help us provide the most accurate spatial forest carbon data possible in order to better inform local management and decision making.
Authors: Qiqi Zhou, Yichen Zhu
Abstract: This paper investigates the Neural Tangent Kernel (NTK) to search vision transformers without training. In contrast with the previous observation that NTK-based metrics can effectively predict CNNs performance at initialization, we empirically show their inefficacy in the ViT search space. We hypothesize that the fundamental feature learning preference within ViT contributes to the ineffectiveness of applying NTK to NAS for ViT. We both theoretically and empirically validate that NTK essentially estimates the ability of neural networks that learn low-frequency signals, completely ignoring the impact of high-frequency signals in feature learning. To address this limitation, we propose a new method called ViNTK that generalizes the standard NTK to the high-frequency domain by integrating the Fourier features from inputs. Experiments with multiple ViT search spaces on image classification and semantic segmentation tasks show that our method can significantly speed up search costs over prior state-of-the-art NAS for ViT while maintaining similar performance on searched architectures.
Authors: Freddie Grabovski, Lior Yasur, Yaniv Hacmon, Lior Nisimov, Stav Nimrod
Abstract: This study explores the generation of synthesized fingerprint images using Denoising Diffusion Probabilistic Models (DDPMs). The significant obstacles in collecting real biometric data, such as privacy concerns and the demand for diverse datasets, underscore the imperative for synthetic biometric alternatives that are both realistic and varied. Despite the strides made with Generative Adversarial Networks (GANs) in producing realistic fingerprint images, their limitations prompt us to propose DDPMs as a promising alternative. DDPMs are capable of generating images with increasing clarity and realism while maintaining diversity. Our results reveal that DiffFinger not only competes with authentic training set data in quality but also provides a richer set of biometric data, reflecting true-to-life variability. These findings mark a promising stride in biometric synthesis, showcasing the potential of DDPMs to advance the landscape of fingerprint identification and authentication systems.
Authors: Aryan Bhambu, Arabin Kumar Dey
Abstract: This research paper introduces innovative approaches for multivariate time series forecasting based on different variations of the combined regression strategy. We use specific data preprocessing techniques which makes a radical change in the behaviour of prediction. We compare the performance of the model based on two types of hyper-parameter tuning Bayesian optimisation (BO) and Usual Grid search. Our proposed methodologies outperform all state-of-the-art comparative models. We illustrate the methodologies through eight time series datasets from three categories: cryptocurrency, stock index, and short-term load forecasting.
Authors: Jiang Zhang, Yahya H Ezzeldin, Ahmed Roushdy Elkordy, Konstantinos Psounis, Salman Avestimehr
Abstract: Federated Learning (FL) with Secure Aggregation (SA) has gained significant attention as a privacy preserving framework for training machine learning models while preventing the server from learning information about users' data from their individual encrypted model updates. Recent research has extended privacy guarantees of FL with SA by bounding the information leakage through the aggregate model over multiple training rounds thanks to leveraging the "noise" from other users' updates. However, the privacy metric used in that work (mutual information) measures the on-average privacy leakage, without providing any privacy guarantees for worse-case scenarios. To address this, in this work we study the conditions under which FL with SA can provide worst-case differential privacy guarantees. Specifically, we formally identify the necessary condition that SA can provide DP without addition noise. We then prove that when the randomness inside the aggregated model update is Gaussian with non-singular covariance matrix, SA can provide differential privacy guarantees with the level of privacy $\epsilon$ bounded by the reciprocal of the minimum eigenvalue of the covariance matrix. However, we further demonstrate that in practice, these conditions are almost unlikely to hold and hence additional noise added in model updates is still required in order for SA in FL to achieve DP. Lastly, we discuss the potential solution of leveraging inherent randomness inside aggregated model update to reduce the amount of addition noise required for DP guarantee.
Authors: Nikolija Bojkovic, Po-Ling Loh
Abstract: The need to analyze sensitive data, such as medical records or financial data, has created a critical research challenge in recent years. In this paper, we adopt the framework of differential privacy, and explore mechanisms for generating an entire dataset which accurately captures characteristics of the original data. We build upon the work of Boedihardjo et al, which laid the foundations for a new optimization-based algorithm for generating private synthetic data. Importantly, we adapt their algorithm by replacing a uniform sampling step with a private distribution estimator; this allows us to obtain better computational guarantees for discrete distributions, and develop a novel algorithm suitable for continuous distributions. We also explore applications of our work to several statistical tasks.
Authors: Felipe Moreno-Vera
Abstract: The increasing sophistication of cyber threats necessitates proactive measures to identify vulnerabilities and potential exploits. Underground hacking forums serve as breeding grounds for the exchange of hacking techniques and discussions related to exploitation. In this research, we propose an innovative approach using topic modeling to analyze and uncover key themes in vulnerabilities discussed within these forums. The objective of our study is to develop a machine learning-based model that can automatically detect and classify vulnerability-related discussions in underground hacking forums. By monitoring and analyzing the content of these forums, we aim to identify emerging vulnerabilities, exploit techniques, and potential threat actors. To achieve this, we collect a large-scale dataset consisting of posts and threads from multiple underground forums. We preprocess and clean the data to ensure accuracy and reliability. Leveraging topic modeling techniques, specifically Latent Dirichlet Allocation (LDA), we uncover latent topics and their associated keywords within the dataset. This enables us to identify recurring themes and prevalent discussions related to vulnerabilities, exploits, and potential targets.
Authors: Arpit Aggarwal
Abstract: There are several improvements proposed over the baseline Absolute Positional Encoding (APE) method used in original transformer. In this study, we aim to investigate the implications of inadequately representing positional encoding in higher dimensions on crucial aspects of the attention mechanism, the model's capacity to learn relative positional information, and the convergence of models, all stemming from the choice of sinusoidal basis functions. Through a combination of theoretical insights and empirical analyses, we elucidate how these challenges extend beyond APEs and may adversely affect the performance of Relative Positional Encoding (RPE) methods, such as Rotatory Positional Encoding (RoPE). Subsequently, we introduce an innovative solution termed Orthogonal Polynomial Based Positional Encoding (PoPE) to address some of the limitations associated with existing methods. The PoPE method encodes positional information by leveraging Orthogonal Legendre polynomials. Legendre polynomials as basis functions offers several desirable properties for positional encoding, including improved correlation structure, non-periodicity, orthogonality, and distinct functional forms among polynomials of varying orders. Our experimental findings demonstrate that transformer models incorporating PoPE outperform baseline transformer models on the $Multi30k$ English-to-German translation task, thus establishing a new performance benchmark. Furthermore, PoPE-based transformers exhibit significantly accelerated convergence rates. Additionally, we will present novel theoretical perspectives on position encoding based on the superior performance of PoPE.
Authors: Fakrul Islam Tushar, Avivah Wang, Lavsen Dahal, Michael R. Harowicz, Kyle J. Lafata, Tina D. Tailor, Joseph Y. Lo
Abstract: BACKGROUND: Lung cancer's high mortality rate can be mitigated by early detection, which is increasingly reliant on artificial intelligence (AI) for diagnostic imaging. However, the performance of AI models is contingent upon the datasets used for their training and validation. METHODS: This study developed and validated the DLCSD-mD and LUNA16-mD models utilizing the Duke Lung Cancer Screening Dataset (DLCSD), encompassing over 2,000 CT scans with more than 3,000 annotations. These models were rigorously evaluated against the internal DLCSD and external LUNA16 and NLST datasets, aiming to establish a benchmark for imaging-based performance. The assessment focused on creating a standardized evaluation framework to facilitate consistent comparison with widely utilized datasets, ensuring a comprehensive validation of the model's efficacy. Diagnostic accuracy was assessed using free-response receiver operating characteristic (FROC) and area under the curve (AUC) analyses. RESULTS: On the internal DLCSD set, the DLCSD-mD model achieved an AUC of 0.93 (95% CI:0.91-0.94), demonstrating high accuracy. Its performance was sustained on the external datasets, with AUCs of 0.97 (95% CI: 0.96-0.98) on LUNA16 and 0.75 (95% CI: 0.73-0.76) on NLST. Similarly, the LUNA16-mD model recorded an AUC of 0.96 (95% CI: 0.95-0.97) on its native dataset and showed transferable diagnostic performance with AUCs of 0.91 (95% CI: 0.89-0.93) on DLCSD and 0.71 (95% CI: 0.70-0.72) on NLST. CONCLUSION: The DLCSD-mD model exhibits reliable performance across different datasets, establishing the DLCSD as a robust benchmark for lung cancer detection and diagnosis. Through the provision of our models and code to the public domain, we aim to accelerate the development of AI-based diagnostic tools and encourage reproducibility and collaborative advancements within the medical machine-learning (ML) field.
Authors: Won-Gi Paeng, Daesuk Kwon
Abstract: This short note is written for rapid communication of long context training and to share the idea of how to train it with low memory usage. In the note, we generalize the attention algorithm and neural network of Generative Pre-Trained Transformers and reinterpret it in Path integral formalism. First, the role of the transformer is understood as the time evolution of the token state and second, it is suggested that the all key-token states in the same time as the query-token can attend to the attention with the query token states. As a result of the repetitive time evolution, it is discussed that the token states in the past sequence meats the token states in the present sequence so that the attention between separated sequences becomes possible for maintaining infinite contextual information just by using low memory for limited size of sequence. For the experiment, the $12$ input token window size was taken and one GPU with $24$GB memory was used for the pre-training. It was confirmed that more than $150$ length context is preserved. The sampling result of the training, the code and the other details will be included in the revised version of this note later.
Authors: Charles Gaydon, Michel Daab, Floryne Roche
Abstract: Mapping agencies are increasingly adopting Aerial Lidar Scanning (ALS) as a new tool to monitor territory and support public policies. Processing ALS data at scale requires efficient point classification methods that perform well over highly diverse territories. To evaluate them, researchers need large annotated Lidar datasets, however, current Lidar benchmark datasets have restricted scope and often cover a single urban area. To bridge this data gap, we present the FRench ALS Clouds from TArgeted Landscapes (FRACTAL) dataset: an ultra-large-scale aerial Lidar dataset made of 100,000 dense point clouds with high-quality labels for 7 semantic classes and spanning 250 km$^2$. FRACTAL is built upon France's nationwide open Lidar data. It achieves spatial and semantic diversity via a sampling scheme that explicitly concentrates rare classes and challenging landscapes from five French regions. It should support the development of 3D deep learning approaches for large-scale land monitoring. We describe the nature of the source data, the sampling workflow, the content of the resulting dataset, and provide an initial evaluation of segmentation performance using a performant 3D neural architecture.
Authors: Hritik Bansal, Yonatan Bitton, Michal Yarom, Idan Szpektor, Aditya Grover, Kai-Wei Chang
Abstract: Recent advances in diffusion-based generative modeling have led to the development of text-to-video (T2V) models that can generate high-quality videos conditioned on a text prompt. Most of these T2V models often produce single-scene video clips that depict an entity performing a particular action (e.g., `a red panda climbing a tree'). However, it is pertinent to generate multi-scene videos since they are ubiquitous in the real-world (e.g., `a red panda climbing a tree' followed by `the red panda sleeps on the top of the tree'). To generate multi-scene videos from the pretrained T2V model, we introduce Time-Aligned Captions (TALC) framework. Specifically, we enhance the text-conditioning mechanism in the T2V architecture to recognize the temporal alignment between the video scenes and scene descriptions. For instance, we condition the visual features of the earlier and later scenes of the generated video with the representations of the first scene description (e.g., `a red panda climbing a tree') and second scene description (e.g., `the red panda sleeps on the top of the tree'), respectively. As a result, we show that the T2V model can generate multi-scene videos that adhere to the multi-scene text descriptions and be visually consistent (e.g., entity and background). Further, we finetune the pretrained T2V model with multi-scene video-text data using the TALC framework. We show that the TALC-finetuned model outperforms the baseline methods by 15.5 points in the overall score, which averages visual consistency and text adherence using human evaluation. The project website is https://talc-mst2v.github.io/.
Authors: Emre Can Acikgoz, Mete Erdogan, Deniz Yuret
Abstract: Large Language Models (LLMs) are becoming crucial across various fields, emphasizing the urgency for high-quality models in underrepresented languages. This study explores the unique challenges faced by low-resource languages, such as data scarcity, model selection, evaluation, and computational limitations, with a special focus on Turkish. We conduct an in-depth analysis to evaluate the impact of training strategies, model choices, and data availability on the performance of LLMs designed for underrepresented languages. Our approach includes two methodologies: (i) adapting existing LLMs originally pretrained in English to understand Turkish, and (ii) developing a model from the ground up using Turkish pretraining data, both supplemented with supervised fine-tuning on a novel Turkish instruction-tuning dataset aimed at enhancing reasoning capabilities. The relative performance of these methods is evaluated through the creation of a new leaderboard for Turkish LLMs, featuring benchmarks that assess different reasoning and knowledge skills. Furthermore, we conducted experiments on data and model scaling, both during pretraining and fine-tuning, simultaneously emphasizing the capacity for knowledge transfer across languages and addressing the challenges of catastrophic forgetting encountered during fine-tuning on a different language. Our goal is to offer a detailed guide for advancing the LLM framework in low-resource linguistic contexts, thereby making natural language processing (NLP) benefits more globally accessible.
Authors: Jonathan Oliver, Raghav Batta, Adam Bates, Muhammad Adil Inam, Shelly Mehta, Shugao Xia
Abstract: "Alert fatigue" is one of the biggest challenges faced by the Security Operations Center (SOC) today, with analysts spending more than half of their time reviewing false alerts. Endpoint detection products raise alerts by pattern matching on event telemetry against behavioral rules that describe potentially malicious behavior, but can suffer from high false positives that distract from actual attacks. While alert triage techniques based on data provenance may show promise, these techniques can take over a minute to inspect a single alert, while EDR customers may face tens of millions of alerts per day; the current reality is that these approaches aren't nearly scalable enough for production environments. We present Carbon Filter, a statistical learning based system that dramatically reduces the number of alerts analysts need to manually review. Our approach is based on the observation that false alert triggers can be efficiently identified and separated from suspicious behaviors by examining the process initiation context (e.g., the command line) that launched the responsible process. Through the use of fast-search algorithms for training and inference, our approach scales to millions of alerts per day. Through batching queries to the model, we observe a theoretical maximum throughput of 20 million alerts per hour. Based on the analysis of tens of million alerts from customer deployments, our solution resulted in a 6-fold improvement in the Signal-to-Noise ratio without compromising on alert triage performance.
Authors: Kyle Stachowicz, Sergey Levine
Abstract: Reinforcement learning provides an appealing framework for robotic control due to its ability to learn expressive policies purely through real-world interaction. However, this requires addressing real-world constraints and avoiding catastrophic failures during training, which might severely impede both learning progress and the performance of the final policy. In many robotics settings, this amounts to avoiding certain "unsafe" states. The high-speed off-road driving task represents a particularly challenging instantiation of this problem: a high-return policy should drive as aggressively and as quickly as possible, which often requires getting close to the edge of the set of "safe" states, and therefore places a particular burden on the method to avoid frequent failures. To both learn highly performant policies and avoid excessive failures, we propose a reinforcement learning framework that combines risk-sensitive control with an adaptive action space curriculum. Furthermore, we show that our risk-sensitive objective automatically avoids out-of-distribution states when equipped with an estimator for epistemic uncertainty. We implement our algorithm on a small-scale rally car and show that it is capable of learning high-speed policies for a real-world off-road driving task. We show that our method greatly reduces the number of safety violations during the training process, and actually leads to higher-performance policies in both driving and non-driving simulation environments with similar challenges.
Authors: Yihong Gu, Cong Fang, Peter B\"uhlmann, Jianqing Fan
Abstract: Statistics suffers from a fundamental problem, "the curse of endogeneity" -- the regression function, or more broadly the prediction risk minimizer with infinite data, may not be the target we wish to pursue. This is because when complex data are collected from multiple sources, the biases deviated from the interested (causal) association inherited in individuals or sub-populations are not expected to be canceled. Traditional remedies are of hindsight and restrictive in being tailored to prior knowledge like untestable cause-effect structures, resulting in methods that risk model misspecification and lack scalable applicability. This paper seeks to offer a purely data-driven and universally applicable method that only uses the heterogeneity of the biases in the data rather than following pre-offered commandments. Such an idea is formulated as a nonparametric invariance pursuit problem, whose goal is to unveil the invariant conditional expectation $m^\star(x)\equiv \mathbb{E}[Y^{(e)}|X_{S^\star}^{(e)}=x_{S^\star}]$ with unknown important variable set $S^\star$ across heterogeneous environments $e\in \mathcal{E}$. Under the structural causal model framework, $m^\star$ can be interpreted as certain data-driven causality in general. The paper contributes to proposing a novel framework, called Focused Adversarial Invariance Regularization (FAIR), formulated as a single minimax optimization program that can solve the general invariance pursuit problem. As illustrated by the unified non-asymptotic analysis, our adversarial estimation framework can attain provable sample-efficient estimation akin to standard regression under a minimal identification condition for various tasks and models. As an application, the FAIR-NN estimator realized by two Neural Network classes is highlighted as the first approach to attain statistically efficient estimation in general nonparametric invariance learning.
Authors: Cong Cao, Ramit Debnath, R. Michael Alvarez
Abstract: Policymakers frequently analyze air quality and climate change in isolation, disregarding their interactions. This study explores the influence of specific climate factors on air quality by contrasting a regression model with K-Means Clustering, Hierarchical Clustering, and Random Forest techniques. We employ Physics-based Deep Learning (PBDL) and Long Short-Term Memory (LSTM) to examine the air pollution predictions. Our analysis utilizes ten years (2009-2018) of daily traffic, weather, and air pollution data from three major cities in Norway. Findings from feature selection reveal a correlation between rising heating degree days and heightened air pollution levels, suggesting increased heating activities in Norway are a contributing factor to worsening air quality. PBDL demonstrates superior accuracy in air pollution predictions compared to LSTM. This paper contributes to the growing literature on PBDL methods for more accurate air pollution predictions using environmental variables, aiding policymakers in formulating effective data-driven climate policies.
Authors: Seoyoung Hong, Jeongwhan Choi, Yeon-Chang Lee, Srijan Kumar, Noseong Park
Abstract: Collaborative filtering (CF) methods for recommendation systems have been extensively researched, ranging from matrix factorization and autoencoder-based to graph filtering-based methods. Recently, lightweight methods that require almost no training have been recently proposed to reduce overall computation. However, existing methods still have room to improve the trade-offs among accuracy, efficiency, and robustness. In particular, there are no well-designed closed-form studies for \emph{balanced} CF in terms of the aforementioned trade-offs. In this paper, we design SVD-AE, a simple yet effective singular vector decomposition (SVD)-based linear autoencoder, whose closed-form solution can be defined based on SVD for CF. SVD-AE does not require iterative training processes as its closed-form solution can be calculated at once. Furthermore, given the noisy nature of the rating matrix, we explore the robustness against such noisy interactions of existing CF methods and our SVD-AE. As a result, we demonstrate that our simple design choice based on truncated SVD can be used to strengthen the noise robustness of the recommendation while improving efficiency. Code is available at https://github.com/seoyoungh/svd-ae.
Authors: Chu Fei Luo, Ahmad Ghawanmeh, Xiaodan Zhu, Faiza Khan Khattak
Abstract: Modern large language models (LLMs) have a significant amount of world knowledge, which enables strong performance in commonsense reasoning and knowledge-intensive tasks when harnessed properly. The language model can also learn social biases, which has a significant potential for societal harm. There have been many mitigation strategies proposed for LLM safety, but it is unclear how effective they are for eliminating social biases. In this work, we propose a new methodology for attacking language models with knowledge graph augmented generation. We refactor natural language stereotypes into a knowledge graph, and use adversarial attacking strategies to induce biased responses from several open- and closed-source language models. We find our method increases bias in all models, even those trained with safety guardrails. This demonstrates the need for further research in AI safety, and further work in this new adversarial space.
Authors: Yihan Mei, Xinyu Wang, Dell Zhang, Xiaoling Wang
Abstract: In today's interconnected world, achieving reliable out-of-distribution (OOD) detection poses a significant challenge for machine learning models. While numerous studies have introduced improved approaches for multi-class OOD detection tasks, the investigation into multi-label OOD detection tasks has been notably limited. We introduce Spectral Normalized Joint Energy (SNoJoE), a method that consolidates label-specific information across multiple labels through the theoretically justified concept of an energy-based function. Throughout the training process, we employ spectral normalization to manage the model's feature space, thereby enhancing model efficacy and generalization, in addition to bolstering robustness. Our findings indicate that the application of spectral normalization to joint energy scores notably amplifies the model's capability for OOD detection. We perform OOD detection experiments utilizing PASCAL-VOC as the in-distribution dataset and ImageNet-22K or Texture as the out-of-distribution datasets. Our experimental results reveal that, in comparison to prior top performances, SNoJoE achieves 11% and 54% relative reductions in FPR95 on the respective OOD datasets, thereby defining the new state of the art in this field of study.
Authors: Amrita Bhattacharjee, Raha Moraffah, Joshua Garland, Huan Liu
Abstract: Counterfactual examples are frequently used for model development and evaluation in many natural language processing (NLP) tasks. Although methods for automated counterfactual generation have been explored, such methods depend on models such as pre-trained language models that are then fine-tuned on auxiliary, often task-specific datasets. Collecting and annotating such datasets for counterfactual generation is labor intensive and therefore, infeasible in practice. Therefore, in this work, we focus on a novel problem setting: \textit{zero-shot counterfactual generation}. To this end, we propose a structured way to utilize large language models (LLMs) as general purpose counterfactual example generators. We hypothesize that the instruction-following and textual understanding capabilities of recent LLMs can be effectively leveraged for generating high quality counterfactuals in a zero-shot manner, without requiring any training or fine-tuning. Through comprehensive experiments on various downstream tasks in natural language processing (NLP), we demonstrate the efficacy of LLMs as zero-shot counterfactual generators in evaluating and explaining black-box NLP models.
Authors: Irene Alisjahbana (Mullet), Jiawei Li (Mullet), Ben (Mullet), Strong, Yue Zhang
Abstract: Satellite imagery has played an increasingly important role in post-disaster building damage assessment. Unfortunately, current methods still rely on manual visual interpretation, which is often time-consuming and can cause very low accuracy. To address the limitations of manual interpretation, there has been a significant increase in efforts to automate the process. We present a solution that performs the two most important tasks in building damage assessment, segmentation and classification, through deep-learning models. We show our results submitted as part of the xView2 Challenge, a competition to design better models for identifying buildings and their damage level after exposure to multiple kinds of natural disasters. Our best model couples a building identification semantic segmentation convolutional neural network (CNN) to a building damage classification CNN, with a combined F1 score of 0.66, surpassing the xView2 challenge baseline F1 score of 0.28. We find that though our model was able to identify buildings with relatively high accuracy, building damage classification across various disaster types is a difficult task due to the visual similarity between different damage levels and different damage distribution between disaster types, highlighting the fact that it may be important to have a probabilistic prior estimate regarding disaster damage in order to obtain accurate predictions.
Authors: Takumi Okuo, Kazuya Nishimura, Hiroaki Ito, Kazuhiro Terada, Akihiko Yoshizawa, Ryoma Bise
Abstract: The PD-L1 rate, the number of PD-L1 positive tumor cells over the total number of all tumor cells, is an important metric for immunotherapy. This metric is recorded as diagnostic information with pathological images. In this paper, we propose a proportion estimation method with a small amount of cell-level annotation and proportion annotation, which can be easily collected. Since the PD-L1 rate is calculated from only `tumor cells' and not using `non-tumor cells', we first detect tumor cells with a detection model. Then, we estimate the PD-L1 proportion by introducing a masking technique to `learning from label proportion.' In addition, we propose a weighted focal proportion loss to address data imbalance problems. Experiments using clinical data demonstrate the effectiveness of our method. Our method achieved the best performance in comparisons.
Authors: Shuo Shao, Yiming Li, Hongwei Yao, Yiling He, Zhan Qin, Kui Ren
Abstract: Ownership verification is currently the most critical and widely adopted post-hoc method to safeguard model copyright. In general, model owners exploit it to identify whether a given suspicious third-party model is stolen from them by examining whether it has particular properties `inherited' from their released models. Currently, backdoor-based model watermarks are the primary and cutting-edge methods to implant such properties in the released models. However, backdoor-based methods have two fatal drawbacks, including harmfulness and ambiguity. The former indicates that they introduce maliciously controllable misclassification behaviors ($i.e.$, backdoor) to the watermarked released models. The latter denotes that malicious users can easily pass the verification by finding other misclassified samples, leading to ownership ambiguity. In this paper, we argue that both limitations stem from the `zero-bit' nature of existing watermarking schemes, where they exploit the status ($i.e.$, misclassified) of predictions for verification. Motivated by this understanding, we design a new watermarking paradigm, $i.e.$, Explanation as a Watermark (EaaW), that implants verification behaviors into the explanation of feature attribution instead of model predictions. Specifically, EaaW embeds a `multi-bit' watermark into the feature attribution explanation of specific trigger samples without changing the original prediction. We correspondingly design the watermark embedding and extraction algorithms inspired by explainable artificial intelligence. In particular, our approach can be used for different tasks ($e.g.$, image classification and text generation). Extensive experiments verify the effectiveness and harmlessness of our EaaW and its resistance to potential attacks.
Authors: Vicky Vikrant, Narodia Parth P, Kamalika Bhattacharjee
Abstract: In this paper, a decimal first degree cellular automata (FDCA) based clustering algorithm is proposed where clusters are created based on reachability. Cyclic spaces are created and configurations which are in the same cycle are treated as the same cluster. Here, real-life data objects are encoded into decimal strings using G\"odel number based encoding. The benefits of the scheme is, it reduces the encoded string length while maintaining the features properties. Candidate CA rules are identified based on some theoretical criteria such as self-replication and information flow. An iterative algorithm is developed to generate the desired number of clusters over three stages. The results of the clustering are evaluated based on benchmark clustering metrics such as Silhouette score, Davis Bouldin, Calinski Harabasz and Dunn Index. In comparison with the existing state-of-the-art clustering algorithms, our proposed algorithm gives better performance.
Authors: Zehan Wang, Ziang Zhang, Xize Cheng, Rongjie Huang, Luping Liu, Zhenhui Ye, Haifeng Huang, Yang Zhao, Tao Jin, Peng Gao, Zhou Zhao
Abstract: Unified multi-model representation spaces are the foundation of multimodal understanding and generation. However, the billions of model parameters and catastrophic forgetting problems make it challenging to further enhance pre-trained unified spaces. In this work, we propose Molecule-Space, an idea that treats multimodal representation spaces as "molecules", and augments pre-trained unified space by integrating knowledge from extra expert spaces via "molecules space reactions". Specifically, we introduce two kinds of basic space reactions: 1) Space Displacement Reaction and 2) Space Combination Reaction. Based on these defined basic reactions, we design Complex Sequential & Parallel Reactions to effectively integrate multiple spaces simultaneously. Benefiting from the modularization concept, we further propose a coarse-to-fine customized inference strategy to flexibly adjust the enhanced unified space for different purposes. Experimentally, we fuse the audio-image-text space of ImageBind with the image-text and audio-text expert spaces. The resulting space outperforms ImageBind on 5 downstream tasks across 9 datasets. Moreover, via customized inference, it even surpasses the used image-text and audio-text expert spaces.
Authors: Jerret Ross, Brian Belgodere, Samuel C. Hoffman, Vijil Chenthamarakshan, Youssef Mroueh, Payel Das
Abstract: Transformer-based models trained on large and general purpose datasets consisting of molecular strings have recently emerged as a powerful tool for successfully modeling various structure-property relations. Inspired by this success, we extend the paradigm of training chemical language transformers on large-scale chemical datasets to generative tasks in this work. Specifically, we propose GP-MoLFormer, an autoregressive molecular string generator that is trained on more than 1.1B chemical SMILES. GP-MoLFormer uses a 46.8M parameter transformer decoder model with linear attention and rotary positional encodings as the base architecture. We explore the utility of GP-MoLFormer in generating novel, valid, and unique SMILES. Impressively, we find GP-MoLFormer is able to generate a significant fraction of novel, valid, and unique SMILES even when the number of generated molecules is in the 10 billion range and the reference set is over a billion. We also find strong memorization of training data in GP-MoLFormer generations, which has so far remained unexplored for chemical language models. Our analyses reveal that training data memorization and novelty in generations are impacted by the quality of the training data; duplication bias in training data can enhance memorization at the cost of lowering novelty. We evaluate GP-MoLFormer's utility and compare it with that of existing baselines on three different tasks: de novo generation, scaffold-constrained molecular decoration, and unconstrained property-guided optimization. While the first two are handled with no additional training, we propose a parameter-efficient fine-tuning method for the last task, which uses property-ordered molecular pairs as input. We call this new approach pair-tuning. Our results show GP-MoLFormer performs better or comparable with baselines across all three tasks, demonstrating its general utility.
Authors: Motonobu Kanagawa
Abstract: We describe a fast computation method for leave-one-out cross-validation (LOOCV) for $k$-nearest neighbours ($k$-NN) regression. We show that, under a tie-breaking condition for nearest neighbours, the LOOCV estimate of the mean square error for $k$-NN regression is identical to the mean square error of $(k+1)$-NN regression evaluated on the training data, multiplied by the scaling factor $(k+1)^2/k^2$. Therefore, to compute the LOOCV score, one only needs to fit $(k+1)$-NN regression only once, and does not need to repeat training-validation of $k$-NN regression for the number of training data. Numerical experiments confirm the validity of the fast computation method.
Authors: Tugba Torun, Eren Yenigul, Ameer Taweel, Didem Unat
Abstract: Sparse tensor operations are gaining attention in emerging applications such as social networks, deep learning, diagnosis, crime, and review analysis. However, a major obstacle for research in sparse tensor operations is the deficiency of a broad-scale sparse tensor dataset. Another challenge in sparse tensor operations is examining the sparse tensor features, which are not only important for revealing its nonzero pattern but also have a significant impact on determining the best-suited storage format, the decomposition algorithm, and the reordering methods. However, due to the large sizes of real tensors, even extracting these features becomes costly without caution. To address these gaps in the literature, we have developed a smart sparse tensor generator that mimics the substantial features of real sparse tensors. Moreover, we propose various methods for efficiently extracting an extensive set of features for sparse tensors. The effectiveness of our generator is validated through the quality of features and the performance of decomposition in the generated tensors. Both the sparse tensor feature extractor and the tensor generator are open source with all the artifacts available at https://github.com/sparcityeu/feaTen and https://github.com/sparcityeu/genTen, respectively.
URLs: https://github.com/sparcityeu/feaTen, https://github.com/sparcityeu/genTen,
Authors: Aimira Baitieva, David Hurych, Victor Besnier, Olivier Bernard
Abstract: Automating visual inspection in industrial production lines is essential for increasing product quality across various industries. Anomaly detection (AD) methods serve as robust tools for this purpose. However, existing public datasets primarily consist of images without anomalies, limiting the practical application of AD methods in production settings. To address this challenge, we present (1) the Valeo Anomaly Dataset (VAD), a novel real-world industrial dataset comprising 5000 images, including 2000 instances of challenging real defects across more than 20 subclasses. Acknowledging that traditional AD methods struggle with this dataset, we introduce (2) Segmentation-based Anomaly Detector (SegAD). First, SegAD leverages anomaly maps as well as segmentation maps to compute local statistics. Next, SegAD uses these statistics and an optional supervised classifier score as input features for a Boosted Random Forest (BRF) classifier, yielding the final anomaly score. Our SegAD achieves state-of-the-art performance on both VAD (+2.1% AUROC) and the VisA dataset (+0.4% AUROC). The code and the models are publicly available.
Authors: Felix Haag, Carlo Stingl, Katrin Zerfass, Konstantin Hopf, Thorsten Staake
Abstract: Information systems (IS) are frequently designed to leverage the negative effect of anchoring bias to influence individuals' decision-making (e.g., by manipulating purchase decisions). Recent advances in Artificial Intelligence (AI) and the explanations of its decisions through explainable AI (XAI) have opened new opportunities for mitigating biased decisions. So far, the potential of these technological advances to overcome anchoring bias remains widely unclear. To this end, we conducted two online experiments with a total of N=390 participants in the context of purchase decisions to examine the impact of AI and XAI-based decision support on anchoring bias. Our results show that AI alone and its combination with XAI help to mitigate the negative effect of anchoring bias. Ultimately, our findings have implications for the design of AI and XAI-based decision support and IS to overcome cognitive biases.
Authors: Kexin Rong, Paul Liu, Sarah Ashok Sonje, Moses Charikar
Abstract: Many data analytics systems store and process large datasets in partitions containing millions of rows. By mapping rows to partitions in an optimized way, it is possible to improve query performance by skipping over large numbers of irrelevant partitions during query processing. This mapping is referred to as a data layout. Recent works have shown that customizing the data layout to the anticipated query workload greatly improves query performance, but the performance benefits may disappear if the workload changes. Reorganizing data layouts to accommodate workload drift can resolve this issue, but reorganization costs could exceed query savings if not done carefully. In this paper, we present an algorithmic framework OReO that makes online reorganization decisions to balance the benefits of improved query performance with the costs of reorganization. Our framework extends results from Metrical Task Systems to provide a tight bound on the worst-case performance guarantee for online reorganization, without prior knowledge of the query workload. Through evaluation on real-world datasets and query workloads, our experiments demonstrate that online reorganization with OReO can lead to an up to 32% improvement in combined query and reorganization time compared to using a single, optimized data layout for the entire workload.
Authors: Audrey Poinsot, Alessandro Leite, Nicolas Chesneau, Mich\`ele S\'ebag, Marc Schoenauer
Abstract: This paper provides a comprehensive review of deep structural causal models (DSCMs), particularly focusing on their ability to answer counterfactual queries using observational data within known causal structures. It delves into the characteristics of DSCMs by analyzing the hypotheses, guarantees, and applications inherent to the underlying deep learning components and structural causal models, fostering a finer understanding of their capabilities and limitations in addressing different counterfactual queries. Furthermore, it highlights the challenges and open questions in the field of deep structural causal modeling. It sets the stages for researchers to identify future work directions and for practitioners to get an overview in order to find out the most appropriate methods for their needs.
Authors: Dhruv V. Patel, Jonghyun Lee, Matthew W. Farthing, Peter K. Kitanidis, Eric F. Darve
Abstract: Numerous applications in biology, statistics, science, and engineering require generating samples from high-dimensional probability distributions. In recent years, the Hamiltonian Monte Carlo (HMC) method has emerged as a state-of-the-art Markov chain Monte Carlo technique, exploiting the shape of such high-dimensional target distributions to efficiently generate samples. Despite its impressive empirical success and increasing popularity, its wide-scale adoption remains limited due to the high computational cost of gradient calculation. Moreover, applying this method is impossible when the gradient of the posterior cannot be computed (for example, with black-box simulators). To overcome these challenges, we propose a novel two-stage Hamiltonian Monte Carlo algorithm with a surrogate model. In this multi-fidelity algorithm, the acceptance probability is computed in the first stage via a standard HMC proposal using an inexpensive differentiable surrogate model, and if the proposal is accepted, the posterior is evaluated in the second stage using the high-fidelity (HF) numerical solver. Splitting the standard HMC algorithm into these two stages allows for approximating the gradient of the posterior efficiently, while producing accurate posterior samples by using HF numerical solvers in the second stage. We demonstrate the effectiveness of this algorithm for a range of problems, including linear and nonlinear Bayesian inverse problems with in-silico data and experimental data. The proposed algorithm is shown to seamlessly integrate with various low-fidelity and HF models, priors, and datasets. Remarkably, our proposed method outperforms the traditional HMC algorithm in both computational and statistical efficiency by several orders of magnitude, all while retaining or improving the accuracy in computed posterior statistics.
Authors: Karim Hamade, Reid McIlroy-Young, Siddhartha Sen, Jon Kleinberg, Ashton Anderson
Abstract: Powerful artificial intelligence systems are often used in settings where they must interact with agents that are computationally much weaker, for example when they work alongside humans or operate in complex environments where some tasks are handled by algorithms, heuristics, or other entities of varying computational power. For AI agents to successfully interact in these settings, however, achieving superhuman performance alone is not sufficient; they also need to account for suboptimal actions or idiosyncratic style from their less-skilled counterparts. We propose a formal evaluation framework for assessing the compatibility of near-optimal AI with interaction partners who may have much lower levels of skill; we use popular collaborative chess variants as model systems to study and develop AI agents that can successfully interact with lower-skill entities. Traditional chess engines designed to output near-optimal moves prove to be inadequate partners when paired with engines of various lower skill levels in this domain, as they are not designed to consider the presence of other agents. We contribute three methodologies to explicitly create skill-compatible AI agents in complex decision-making settings, and two chess game frameworks designed to foster collaboration between powerful AI agents and less-skilled partners. On these frameworks, our agents outperform state-of-the-art chess AI (based on AlphaZero) despite being weaker in conventional chess, demonstrating that skill-compatibility is a tangible trait that is qualitatively and measurably distinct from raw performance. Our evaluations further explore and clarify the mechanisms by which our agents achieve skill-compatibility.
Authors: William Kengne, Modou Wade
Abstract: Recent developments on deep learning established some theoretical properties of deep neural networks estimators. However, most of the existing works on this topic are restricted to bounded loss functions or (sub)-Gaussian or bounded input. This paper considers robust deep learning from weakly dependent observations, with unbounded loss function and unbounded input/output. It is only assumed that the output variable has a finite $r$ order moment, with $r >1$. Non asymptotic bounds for the expected excess risk of the deep neural network estimator are established under strong mixing, and $\psi$-weak dependence assumptions on the observations. We derive a relationship between these bounds and $r$, and when the data have moments of any order (that is $r=\infty$), the convergence rate is close to some well-known results. When the target predictor belongs to the class of H\"older smooth functions with sufficiently large smoothness index, the rate of the expected excess risk for exponentially strongly mixing data is close to or as same as those for obtained with i.i.d. samples. Application to robust nonparametric regression and robust nonparametric autoregression are considered. The simulation study for models with heavy-tailed errors shows that, robust estimators with absolute loss and Huber loss function outperform the least squares method.
Authors: Ming Kuo, Shouvon Sarker, Lijun Qian, Yujian Fu, Xiangfang Li, Xishuang Dong
Abstract: In contrast to pedagogies like evidence-based teaching, personalized adaptive learning (PAL) distinguishes itself by closely monitoring the progress of individual students and tailoring the learning path to their unique knowledge and requirements. A crucial technique for effective PAL implementation is knowledge tracing, which models students' evolving knowledge to predict their future performance. Based on these predictions, personalized recommendations for resources and learning paths can be made to meet individual needs. Recent advancements in deep learning have successfully enhanced knowledge tracking through Deep Knowledge Tracing (DKT). This paper introduces generative AI models to further enhance DKT. Generative AI models, rooted in deep learning, are trained to generate synthetic data, addressing data scarcity challenges in various applications across fields such as natural language processing (NLP) and computer vision (CV). This study aims to tackle data shortage issues in student learning records to enhance DKT performance for PAL. Specifically, it employs TabDDPM, a diffusion model, to generate synthetic educational records to augment training data for enhancing DKT. The proposed method's effectiveness is validated through extensive experiments on ASSISTments datasets. The experimental results demonstrate that the AI-generated data by TabDDPM significantly improves DKT performance, particularly in scenarios with small data for training and large data for testing.
Authors: Mohamad Fazelnia, Viktoria Koscinski, Spencer Herzog, Mehdi Mirakhorli
Abstract: We investigate the use of Natural Language Inference (NLI) in automating requirements engineering tasks. In particular, we focus on three tasks: requirements classification, identification of requirements specification defects, and detection of conflicts in stakeholders' requirements. While previous research has demonstrated significant benefit in using NLI as a universal method for a broad spectrum of natural language processing tasks, these advantages have not been investigated within the context of software requirements engineering. Therefore, we design experiments to evaluate the use of NLI in requirements analysis. We compare the performance of NLI with a spectrum of approaches, including prompt-based models, conventional transfer learning, Large Language Models (LLMs)-powered chatbot models, and probabilistic models. Through experiments conducted under various learning settings including conventional learning and zero-shot, we demonstrate conclusively that our NLI method surpasses classical NLP methods as well as other LLMs-based and chatbot models in the analysis of requirements specifications. Additionally, we share lessons learned characterizing the learning settings that make NLI a suitable approach for automating requirements engineering tasks.
Authors: Zhaoxing Li, Jujie Yang, Jindi Wang, Lei Shi, Sebastian Stein
Abstract: The field of Knowledge Tracing aims to understand how students learn and master knowledge over time by analyzing their historical behaviour data. To achieve this goal, many researchers have proposed Knowledge Tracing models that use data from Intelligent Tutoring Systems to predict students' subsequent actions. However, with the development of Intelligent Tutoring Systems, large-scale datasets containing long-sequence data began to emerge. Recent deep learning based Knowledge Tracing models face obstacles such as low efficiency, low accuracy, and low interpretability when dealing with large-scale datasets containing long-sequence data. To address these issues and promote the sustainable development of Intelligent Tutoring Systems, we propose a LSTM BERT-based Knowledge Tracing model for long sequence data processing, namely LBKT, which uses a BERT-based architecture with a Rasch model-based embeddings block to deal with different difficulty levels information and an LSTM block to process the sequential characteristic in students' actions. LBKT achieves the best performance on most benchmark datasets on the metrics of ACC and AUC. Additionally, an ablation study is conducted to analyse the impact of each component of LBKT's overall performance. Moreover, we used t-SNE as the visualisation tool to demonstrate the model's embedding strategy. The results indicate that LBKT is faster, more interpretable, and has a lower memory cost than the traditional deep learning based Knowledge Tracing methods.
Authors: Dariush Salami, Francesc Wilhelmi, Lorenzo Galati-Giordano, Mika Kasslin
Abstract: The increasing cloudification and softwarization of networks foster the interplay among multiple independently managed deployments. An appealing reason for such an interplay lies in distributed Machine Learning (ML), which allows the creation of robust ML models by leveraging collective intelligence and computational power. In this paper, we study the application of the two cornerstones of distributed learning, namely Federated Learning (FL) and Knowledge Distillation (KD), on the Wi-Fi Access Point (AP) load prediction use case. The analysis conducted in this paper is done on a dataset that contains real measurements from a large Wi-Fi campus network, which we use to train the ML model under study based on different strategies. Performance evaluation includes relevant aspects for the suitability of distributed learning operation in real use cases, including the predictive performance, the associated communication overheads, or the energy consumption. In particular, we prove that distributed learning can improve the predictive accuracy centralized ML solutions by up to 93% while reducing the communication overheads and the energy cost by 80%.
Authors: Thomas Ortner, Horst Petschenig, Athanasios Vasilopoulos, Roland Renner, \v{S}pela Brglez, Thomas Limbacher, Enrique Pi\~nero, Alejandro Linares Barranco, Angeliki Pantazi, Robert Legenstein
Abstract: There is a growing demand for low-power, autonomously learning artificial intelligence (AI) systems that can be applied at the edge and rapidly adapt to the specific situation at deployment site. However, current AI models struggle in such scenarios, often requiring extensive fine-tuning, computational resources, and data. In contrast, humans can effortlessly adjust to new tasks by transferring knowledge from related ones. The concept of learning-to-learn (L2L) mimics this process and enables AI models to rapidly adapt with only little computational effort and data. In-memory computing neuromorphic hardware (NMHW) is inspired by the brain's operating principles and mimics its physical co-location of memory and compute. In this work, we pair L2L with in-memory computing NMHW based on phase-change memory devices to build efficient AI models that can rapidly adapt to new tasks. We demonstrate the versatility of our approach in two scenarios: a convolutional neural network performing image classification and a biologically-inspired spiking neural network generating motor commands for a real robotic arm. Both models rapidly learn with few parameter updates. Deployed on the NMHW, they perform on-par with their software equivalents. Moreover, meta-training of these models can be performed in software with high-precision, alleviating the need for accurate hardware models.
Authors: Thomas Trask
Abstract: The study in interaction patterns between students in on-campus and MOOC-style online courses has been broadly studied for the last 11 years. Yet there remains a gap in the literature comparing the habits of students completing the same course offered in both on-campus and MOOC-style online formats. This study will look at browser-based usage patterns for students in the Georgia Tech CS1301 edx course for both the online course offered to on-campus students and the MOOCstyle course offered to anyone to determine what, if any, patterns exist between the two cohorts.
Authors: Arthur Aubret, Timothy Schauml\"offel, Gemma Roig, Jochen Triesch
Abstract: Humans judge the similarity of two objects not just based on their visual appearance but also based on their semantic relatedness. However, it remains unclear how humans learn about semantic relationships between objects and categories. One important source of semantic knowledge is that semantically related objects frequently co-occur in the same context. For instance, forks and plates are perceived as similar, at least in part, because they are often experienced together in a ``kitchen" or ``eating'' context. Here, we investigate whether a bio-inspired learning principle exploiting such co-occurrence statistics suffices to learn a semantically structured object representation {\em de novo} from raw visual or combined visual and linguistic input. To this end, we simulate temporal sequences of visual experience by binding together short video clips of real-world scenes showing objects in different contexts. A bio-inspired neural network model aligns close-in-time visual representations while also aligning visual and category label representations to simulate visuo-language alignment. Our results show that our model clusters object representations based on their context, e.g. kitchen or bedroom, in particular in high-level layers of the network, akin to humans. In contrast, lower-level layers tend to better reflect object identity or category. To achieve this, the model exploits two distinct strategies: the visuo-language alignment ensures that different objects of the same category are represented similarly, whereas the temporal alignment leverages that objects from the same context are frequently seen in succession to make their representations more similar. Overall, our work suggests temporal and visuo-language alignment as plausible computational principles for explaining the origins of certain forms of semantic knowledge in humans.
Authors: Alexander Scarlatos, Wanyong Feng, Digory Smith, Simon Woodhead, Andrew Lan
Abstract: Multiple-choice questions (MCQs) are commonly used across all levels of math education since they can be deployed and graded at a large scale. A critical component of MCQs is the distractors, i.e., incorrect answers crafted to reflect student errors or misconceptions. Automatically generating them in math MCQs, e.g., with large language models, has been challenging. In this work, we propose a novel method to enhance the quality of generated distractors through overgenerate-and-rank, training a ranking model to predict how likely distractors are to be selected by real students. Experimental results on a real-world dataset and human evaluation with math teachers show that our ranking model increases alignment with human-authored distractors, although human-authored ones are still preferred over generated ones.
Authors: Luca Mossina, Joseba Dalmau, L\'eo and\'eol
Abstract: We propose a post-hoc, computationally lightweight method to quantify predictive uncertainty in semantic image segmentation. Our approach uses conformal prediction to generate statistically valid prediction sets that are guaranteed to include the ground-truth segmentation mask at a predefined confidence level. We introduce a novel visualization technique of conformalized predictions based on heatmaps, and provide metrics to assess their empirical validity. We demonstrate the effectiveness of our approach on well-known benchmark datasets and image segmentation prediction models, and conclude with practical insights.
Authors: Vanni Doffini, O. Anatole von Lilienfeld, Michael A. Nash
Abstract: We investigate trends in the data-error scaling behavior of machine learning (ML) models trained on discrete combinatorial spaces that are prone-to-mutation, such as proteins or organic small molecules. We trained and evaluated kernel ridge regression machines using variable amounts of computationally generated training data. Our synthetic datasets comprise i) two na\"ive functions based on many-body theory; ii) binding energy estimates between a protein and a mutagenised peptide; and iii) solvation energies of two 6-heavy atom structural graphs. In contrast to typical data-error scaling, our results showed discontinuous monotonic phase transitions during learning, observed as rapid drops in the test error at particular thresholds of training data. We observed two learning regimes, which we call saturated and asymptotic decay, and found that they are conditioned by the level of complexity (i.e. number of mutations) enclosed in the training set. We show that during training on this class of problems, the predictions were clustered by the ML models employed in the calibration plots. Furthermore, we present an alternative strategy to normalize learning curves (LCs) and the concept of mutant based shuffling. This work has implications for machine learning on mutagenisable discrete spaces such as chemical properties or protein phenotype prediction, and improves basic understanding of concepts in statistical learning theory.
Authors: Eugene Bagdasaryan, Ren Yi, Sahra Ghalebikesabi, Peter Kairouz, Marco Gruteser, Sewoong Oh, Borja Balle, Daniel Ramage
Abstract: The growing use of large language model (LLM)-based conversational agents to manage sensitive user data raises significant privacy concerns. While these agents excel at understanding and acting on context, this capability can be exploited by malicious actors. We introduce a novel threat model where adversarial third-party apps manipulate the context of interaction to trick LLM-based agents into revealing private information not relevant to the task at hand. Grounded in the framework of contextual integrity, we introduce AirGapAgent, a privacy-conscious agent designed to prevent unintended data leakage by restricting the agent's access to only the data necessary for a specific task. Extensive experiments using Gemini, GPT, and Mistral models as agents validate our approach's effectiveness in mitigating this form of context hijacking while maintaining core agent functionality. For example, we show that a single-query context hijacking attack on a Gemini Ultra agent reduces its ability to protect user data from 94% to 45%, while an AirGapAgent achieves 97% protection, rendering the same attack ineffective.
Authors: Kathryn Volk, Renu Malhotra
Abstract: Trans-Neptunian objects (TNOs) are small, icy bodies in the outer solar system. They are observed to have a complex orbital distribution that was shaped by the early dynamical history and migration of the giant planets. Comparisons between the different dynamical classes of modeled and observed TNOs can help constrain the history of the outer solar system. Because of the complex dynamics of TNOs, particularly those in and near mean motion resonances with Neptune, classification has traditionally been done by human inspection of plots of the time evolution of orbital parameters. This is very inefficient. The Vera Rubin Observatory's Legacy Survey of Space and Time (LSST) is expected to increase the number of known TNOs by a factor of $\sim$10, necessitating a much more automated process. In this chapter we present an improved supervised machine learning classifier for TNOs. Using a large and diverse training set as well as carefully chosen, dynamically motivated data features calculated from numerical integrations of TNO orbits, our classifier returns results that match those of a human classifier 98% of the time, and dynamically relevant classifications 99.7% of the time. This classifier is dramatically more efficient than human classification, and it will improve classification of both observed and modeled TNO data.
Authors: Yan Huang, Li Wang
Abstract: We propose a novel score-based particle method for solving the Landau equation in plasmas, that seamlessly integrates learning with structure-preserving particle methods [arXiv:1910.03080]. Building upon the Lagrangian viewpoint of the Landau equation, a central challenge stems from the nonlinear dependence of the velocity field on the density. Our primary innovation lies in recognizing that this nonlinearity is in the form of the score function, which can be approximated dynamically via techniques from score-matching. The resulting method inherits the conservation properties of the deterministic particle method while sidestepping the necessity for kernel density estimation in [arXiv:1910.03080]. This streamlines computation and enhances scalability with dimensionality. Furthermore, we provide a theoretical estimate by demonstrating that the KL divergence between our approximation and the true solution can be effectively controlled by the score-matching loss. Additionally, by adopting the flow map viewpoint, we derive an update formula for exact density computation. Extensive examples have been provided to show the efficiency of the method, including a physically relevant case of Coulomb interaction.
Authors: Shaddin Dughmi, Yusuf Kalayci, Grayson York
Abstract: Most work in the area of learning theory has focused on designing effective Probably Approximately Correct (PAC) learners. Recently, other models of learning such as transductive error have seen more scrutiny. We move toward showing that these problems are equivalent by reducing agnostic learning with a PAC guarantee to agnostic learning with a transductive guarantee by adding a small number of samples to the dataset. We first rederive the result of Aden-Ali et al. arXiv:2304.09167 reducing PAC learning to transductive learning in the realizable setting using simpler techniques and at more generality as background for our main positive result. Our agnostic transductive to PAC conversion technique extends the aforementioned argument to the agnostic case, showing that an agnostic transductive learner can be efficiently converted to an agnostic PAC learner. Finally, we characterize the performance of the agnostic one inclusion graph algorithm of Asilis et al. arXiv:2309.13692 for binary classification, and show that plugging it into our reduction leads to an agnostic PAC learner that is essentially optimal. Our results imply that transductive and PAC learning are essentially equivalent for supervised learning with pseudometric losses in the realizable setting, and for binary classification in the agnostic setting. We conjecture this is true more generally for the agnostic setting.
Authors: Ariel Neufeld, Philipp Schmocker, Sizhou Wu
Abstract: In this paper, we present a randomized extension of the deep splitting algorithm introduced in [Beck, Becker, Cheridito, Jentzen, and Neufeld (2021)] using random neural networks suitable to approximately solve both high-dimensional nonlinear parabolic PDEs and PIDEs with jumps having (possibly) infinite activity. We provide a full error analysis of our so-called random deep splitting method. In particular, we prove that our random deep splitting method converges to the (unique viscosity) solution of the nonlinear PDE or PIDE under consideration. Moreover, we empirically analyze our random deep splitting method by considering several numerical examples including both nonlinear PDEs and nonlinear PIDEs relevant in the context of pricing of financial derivatives under default risk. In particular, we empirically demonstrate in all examples that our random deep splitting method can approximately solve nonlinear PDEs and PIDEs in 10'000 dimensions within seconds.
Authors: Saiid El Hajj Chehade (EPFL), Sandra Siby (Imperial College London), Carmela Troncoso (EPFL)
Abstract: Privacy-enhancing blocking tools based on filter-list rules tend to break legitimate functionality. Filter-list maintainers could benefit from automated breakage detection tools that allow them to proactively fix problematic rules before deploying them to millions of users. We introduce SINBAD, an automated breakage detector that improves the accuracy over the state of the art by 20%, and is the first to detect dynamic breakage and breakage caused by style-oriented filter rules. The success of SINBAD is rooted in three innovations: (1) the use of user-reported breakage issues in forums that enable the creation of a high-quality dataset for training in which only breakage that users perceive as an issue is included; (2) the use of 'web saliency' to automatically identify user-relevant regions of a website on which to prioritize automated interactions aimed at triggering breakage; and (3) the analysis of webpages via subtrees which enables fine-grained identification of problematic filter rules.
Authors: Yixin Chen, Ankur Nath, Chunli Peng, Alan Kuhnle
Abstract: For constrained, not necessarily monotone submodular maximization, guiding the measured continuous greedy algorithm with a local search algorithm currently obtains the state-of-the-art approximation factor of 0.401 \citep{buchbinder2023constrained}. These algorithms rely upon the multilinear extension and the Lovasz extension of a submodular set function. However, the state-of-the-art approximation factor of combinatorial algorithms has remained $1/e \approx 0.367$ \citep{buchbinder2014submodular}. In this work, we develop combinatorial analogues of the guided measured continuous greedy algorithm and obtain approximation ratio of $0.385$ in $\oh{ kn }$ queries to the submodular set function for size constraint, and $0.305$ for a general matroid constraint. Further, we derandomize these algorithms, maintaining the same ratio and asymptotic time complexity. Finally, we develop a deterministic, nearly linear time algorithm with ratio $0.377$.
Authors: Michael Vitz, Hamed Mohammadbagherpoor, Samarth Sandeep, Andrew Vlasic, Richard Padbury, Anh Pham
Abstract: To accelerate the process of materials design, materials science has increasingly used data driven techniques to extract information from collected data. Specially, machine learning (ML) algorithms, which span the ML discipline, have demonstrated ability to predict various properties of materials with the level of accuracy similar to explicit calculation of quantum mechanical theories, but with significantly reduced run time and computational resources. Within ML, graph neural networks have emerged as an important algorithm within the field of machine learning, since they are capable of predicting accurately a wide range of important physical, chemical and electronic properties due to their higher learning ability based on the graph representation of material and molecular descriptors through the aggregation of information embedded within the graph. In parallel with the development of state of the art classical machine learning applications, the fusion of quantum computing and machine learning have created a new paradigm where classical machine learning model can be augmented with quantum layers which are able to encode high dimensional data more efficiently. Leveraging the structure of existing algorithms, we developed a unique and novel gradient free hybrid quantum classical convoluted graph neural network (HyQCGNN) to predict formation energies of perovskite materials. The performance of our hybrid statistical model is competitive with the results obtained purely from a classical convoluted graph neural network, and other classical machine learning algorithms, such as XGBoost. Consequently, our study suggests a new pathway to explore how quantum feature encoding and parametric quantum circuits can yield drastic improvements of complex ML algorithm like graph neural network.
Authors: Richard Ostert\'ag, Martin Stanek
Abstract: We propose an anomaly detection technique for X.509 certificates utilizing Isolation Forest. This method can be beneficial when compliance testing with X.509 linters proves unsatisfactory, and we seek to identify anomalies beyond standards compliance. The technique is validated on a sample of certificates from Certificate Transparency logs.
Authors: Hossein Mehri, Hao Chen, Hani Mehrpouyan
Abstract: Traffic pattern prediction has emerged as a promising approach for efficiently managing and mitigating the impacts of event-driven bursty traffic in massive machine-type communication (mMTC) networks. However, achieving accurate predictions of bursty traffic remains a non-trivial task due to the inherent randomness of events, and these challenges intensify within live network environments. Consequently, there is a compelling imperative to design a lightweight and agile framework capable of assimilating continuously collected data from the network and accurately forecasting bursty traffic in mMTC networks. This paper addresses these challenges by presenting a machine learning-based framework tailored for forecasting bursty traffic in multi-channel slotted ALOHA networks. The proposed machine learning network comprises long-term short-term memory (LSTM) and a DenseNet with feed-forward neural network (FFNN) layers, where the residual connections enhance the training ability of the machine learning network in capturing complicated patterns. Furthermore, we develop a new low-complexity online prediction algorithm that updates the states of the LSTM network by leveraging frequently collected data from the mMTC network. Simulation results and complexity analysis demonstrate the superiority of our proposed algorithm in terms of both accuracy and complexity, making it well-suited for time-critical live scenarios. We evaluate the performance of the proposed framework in a network with a single base station and thousands of devices organized into groups with distinct traffic-generating characteristics. Comprehensive evaluations and simulations indicate that our proposed machine learning approach achieves a remarkable $52\%$ higher accuracy in long-term predictions compared to traditional methods, without imposing additional processing load on the system.
Authors: Sahel Vahedi Noori, Bin Hu, Geir Dullerud, Peter Seiler
Abstract: This paper presents sufficient conditions for the stability and $\ell_2$-gain performance of recurrent neural networks (RNNs) with ReLU activation functions. These conditions are derived by combining Lyapunov/dissipativity theory with Quadratic Constraints (QCs) satisfied by repeated ReLUs. We write a general class of QCs for repeated RELUs using known properties for the scalar ReLU. Our stability and performance condition uses these QCs along with a "lifted" representation for the ReLU RNN. We show that the positive homogeneity property satisfied by a scalar ReLU does not expand the class of QCs for the repeated ReLU. We present examples to demonstrate the stability / performance condition and study the effect of the lifting horizon.
Authors: Hossein Mehri, Hao Chen, Hani Mehrpouyan
Abstract: The advent of 5G technology promises a paradigm shift in the realm of telecommunications, offering unprecedented speeds and connectivity. However, the efficient management of traffic in 5G networks remains a critical challenge. It is due to the dynamic and heterogeneous nature of network traffic, varying user behaviors, extended network size, and diverse applications, all of which demand highly accurate and adaptable prediction models to optimize network resource allocation and management. This paper investigates the efficacy of live prediction algorithms for forecasting cellular network traffic in real-time scenarios. We apply two live prediction algorithms on machine learning models, one of which is recently proposed Fast LiveStream Prediction (FLSP) algorithm. We examine the performance of these algorithms under two distinct data gathering methodologies: synchronous, where all network cells report statistics simultaneously, and asynchronous, where reporting occurs across consecutive time slots. Our study delves into the impact of these gathering scenarios on the predictive performance of traffic models. Our study reveals that the FLSP algorithm can halve the required bandwidth for asynchronous data reporting compared to conventional online prediction algorithms, while simultaneously enhancing prediction accuracy and reducing processing load. Additionally, we conduct a thorough analysis of algorithmic complexity and memory requirements across various machine learning models. Through empirical evaluation, we provide insights into the trade-offs inherent in different prediction strategies, offering valuable guidance for network optimization and resource allocation in dynamic environments.
Authors: Jack Hardwick
Abstract: This paper proposes a system for chord generation to monophonic symbolic melodies using an LSTM-based model trained on chroma histogram representations of chords. Chroma representations promise more harmonically rich generation than chord label-based approaches, whilst maintaining a small number of dimensions in the dataset. This system is shown to be suitable for limited real-time use. While it does not meet the state-of-the-art for coherent long-term generation, it does show diatonic generation with cadential chord relationships. The need for further study into chroma histograms as an extracted feature in chord generation tasks is highlighted.
Authors: Scott C. Lowe, Benjamin Misiuk, Isaac Xu, Shakhboz Abdulazizov, Amit R. Baroi, Alex C. Bastos, Merlin Best, Vicki Ferrini, Ariell Friedman, Deborah Hart, Ove Hoegh-Guldberg, Daniel Ierodiaconou, Julia Mackin-McLaughlin, Kathryn Markey, Pedro S. Menandro, Jacquomo Monk, Shreya Nemani, John O'Brien, Elizabeth Oh, Luba Y. Reshitnyk, Katleen Robert, Chris M. Roelfsema, Jessica A. Sameoto, Alexandre C. G. Schimel, Jordan A. Thomson, Brittany R. Wilson, Melisa C. Wong, Craig J. Brown, Thomas Trappenberg
Abstract: Advances in underwater imaging enable the collection of extensive seafloor image datasets that are necessary for monitoring important benthic ecosystems. The ability to collect seafloor imagery has outpaced our capacity to analyze it, hindering expedient mobilization of this crucial environmental information. Recent machine learning approaches provide opportunities to increase the efficiency with which seafloor image datasets are analyzed, yet large and consistent datasets necessary to support development of such approaches are scarce. Here we present BenthicNet: a global compilation of seafloor imagery designed to support the training and evaluation of large-scale image recognition models. An initial set of over 11.4 million images was collected and curated to represent a diversity of seafloor environments using a representative subset of 1.3 million images. These are accompanied by 2.6 million annotations translated to the CATAMI scheme, which span 190,000 of the images. A large deep learning model was trained on this compilation and preliminary results suggest it has utility for automating large and small-scale image analysis tasks. The compilation and model are made openly available for use by the scientific community at https://doi.org/10.20383/103.0614.
Authors: Mahesh Bhupati, Abhishek Mall, Anshuman Kumar, Pankaj K. Jha
Abstract: Advancements in optical quantum technologies have been enabled by the generation, manipulation, and characterization of light, with identification based on its photon statistics. However, characterizing light and its sources through single photon measurements often requires efficient detectors and longer measurement times to obtain high-quality photon statistics. Here we introduce a deep learning-based variational autoencoder (VAE) method for classifying single photon added coherent state (SPACS), single photon added thermal state (SPACS), mixed states between coherent/SPACS and thermal/SPATS of light. Our semisupervised learning-based VAE efficiently maps the photon statistics features of light to a lower dimension, enabling quasi-instantaneous classification with low average photon counts. The proposed VAE method is robust and maintains classification accuracy in the presence of losses inherent in an experiment, such as finite collection efficiency, non-unity quantum efficiency, finite number of detectors, etc. Additionally, leveraging the transfer learning capabilities of VAE enables successful classification of data of any quality using a single trained model. We envision that such a deep learning methodology will enable better classification of quantum light and light sources even in the presence of poor detection quality.
Authors: Hongjie Wang, Difan Liu, Yan Kang, Yijun Li, Zhe Lin, Niraj K. Jha, Yuchen Liu
Abstract: Diffusion Models (DMs) have exhibited superior performance in generating high-quality and diverse images. However, this exceptional performance comes at the cost of expensive architectural design, particularly due to the attention module heavily used in leading models. Existing works mainly adopt a retraining process to enhance DM efficiency. This is computationally expensive and not very scalable. To this end, we introduce the Attention-driven Training-free Efficient Diffusion Model (AT-EDM) framework that leverages attention maps to perform run-time pruning of redundant tokens, without the need for any retraining. Specifically, for single-denoising-step pruning, we develop a novel ranking algorithm, Generalized Weighted Page Rank (G-WPR), to identify redundant tokens, and a similarity-based recovery method to restore tokens for the convolution operation. In addition, we propose a Denoising-Steps-Aware Pruning (DSAP) approach to adjust the pruning budget across different denoising timesteps for better generation quality. Extensive evaluations show that AT-EDM performs favorably against prior art in terms of efficiency (e.g., 38.8% FLOPs saving and up to 1.53x speed-up over Stable Diffusion XL) while maintaining nearly the same FID and CLIP scores as the full model. Project webpage: https://atedm.github.io.
URLs: https://atedm.github.io.
Authors: Nayantara Mudur, Carolina Cuesta-Lazaro, Douglas P. Finkbeiner
Abstract: Diffusion generative models have excelled at diverse image generation and reconstruction tasks across fields. A less explored avenue is their application to discriminative tasks involving regression or classification problems. The cornerstone of modern cosmology is the ability to generate predictions for observed astrophysical fields from theory and constrain physical models from observations using these predictions. This work uses a single diffusion generative model to address these interlinked objectives -- as a surrogate model or emulator for cold dark matter density fields conditional on input cosmological parameters, and as a parameter inference model that solves the inverse problem of constraining the cosmological parameters of an input field. The model is able to emulate fields with summary statistics consistent with those of the simulated target distribution. We then leverage the approximate likelihood of the diffusion generative model to derive tight constraints on cosmology by using the Hamiltonian Monte Carlo method to sample the posterior on cosmological parameters for a given test image. Finally, we demonstrate that this parameter inference approach is more robust to the addition of noise than baseline parameter inference networks.
Authors: Prannay Kaul, Zhizhong Li, Hao Yang, Yonatan Dukler, Ashwin Swaminathan, C. J. Taylor, Stefano Soatto
Abstract: Mitigating hallucinations in large vision-language models (LVLMs) remains an open problem. Recent benchmarks do not address hallucinations in open-ended free-form responses, which we term "Type I hallucinations". Instead, they focus on hallucinations responding to very specific question formats -- typically a multiple-choice response regarding a particular object or attribute -- which we term "Type II hallucinations". Additionally, such benchmarks often require external API calls to models which are subject to change. In practice, we observe that a reduction in Type II hallucinations does not lead to a reduction in Type I hallucinations but rather that the two forms of hallucinations are often anti-correlated. To address this, we propose THRONE, a novel object-based automatic framework for quantitatively evaluating Type I hallucinations in LVLM free-form outputs. We use public language models (LMs) to identify hallucinations in LVLM responses and compute informative metrics. By evaluating a large selection of recent LVLMs using public datasets, we show that an improvement in existing metrics do not lead to a reduction in Type I hallucinations, and that established benchmarks for measuring Type I hallucinations are incomplete. Finally, we provide a simple and effective data augmentation method to reduce Type I and Type II hallucinations as a strong baseline.
Authors: Lingdong Kong, Xiang Xu, Jiawei Ren, Wenwei Zhang, Liang Pan, Kai Chen, Wei Tsang Ooi, Ziwei Liu
Abstract: Efficient data utilization is crucial for advancing 3D scene understanding in autonomous driving, where reliance on heavily human-annotated LiDAR point clouds challenges fully supervised methods. Addressing this, our study extends into semi-supervised learning for LiDAR semantic segmentation, leveraging the intrinsic spatial priors of driving scenes and multi-sensor complements to augment the efficacy of unlabeled datasets. We introduce LaserMix++, an evolved framework that integrates laser beam manipulations from disparate LiDAR scans and incorporates LiDAR-camera correspondences to further assist data-efficient learning. Our framework is tailored to enhance 3D scene consistency regularization by incorporating multi-modality, including 1) multi-modal LaserMix operation for fine-grained cross-sensor interactions; 2) camera-to-LiDAR feature distillation that enhances LiDAR feature learning; and 3) language-driven knowledge guidance generating auxiliary supervisions using open-vocabulary models. The versatility of LaserMix++ enables applications across LiDAR representations, establishing it as a universally applicable solution. Our framework is rigorously validated through theoretical analysis and extensive experiments on popular driving perception datasets. Results demonstrate that LaserMix++ markedly outperforms fully supervised alternatives, achieving comparable accuracy with five times fewer annotations and significantly improving the supervised-only baselines. This substantial advancement underscores the potential of semi-supervised approaches in reducing the reliance on extensive labeled data in LiDAR-based 3D scene understanding systems.
Authors: Vik Shirvaikar, Choudur Lakshminarayan
Abstract: Predictive modeling of criminal recidivism, or whether people will re-offend in the future, has a long and contentious history. Modern causal inference methods allow us to move beyond prediction and target the "treatment effect" of a specific intervention on an outcome in an observational dataset. In this paper, we look specifically at the effect of incarceration (prison time) on recidivism, using a well-known dataset from North Carolina. Two popular causal methods for addressing confounding bias are explained and demonstrated: directed acyclic graph (DAG) adjustment and double machine learning (DML), including a sensitivity analysis for unobserved confounders. We find that incarceration has a detrimental effect on recidivism, i.e., longer prison sentences make it more likely that individuals will re-offend after release, although this conclusion should not be generalized beyond the scope of our data. We hope that this case study can inform future applications of causal inference to criminal justice analysis.
Authors: Dwight Nwaigwe, Marek Rychlik
Abstract: We revisit the problem of the existence of the maximum likelihood estimate for multi-class logistic regression. We show that one method of ensuring its existence is by assigning positive probability to every class in the sample dataset. The notion of data separability is not needed, which is in contrast to the classical set up of multi-class logistic regression in which each data sample belongs to one class. We also provide a general and constructive estimate of the convergence rate to the maximum likelihood estimate when gradient descent is used as the optimizer. Our estimate involves bounding the condition number of the Hessian of the maximum likelihood function. The approaches used in this article rely on a simple operator-theoretic framework.
Authors: Xuwei Tan, Yangming Zhou, MengChu Zhou, Zhang-Hua Fu
Abstract: Detecting critical nodes in sparse graphs is important in a variety of application domains, such as network vulnerability assessment, epidemic control, and drug design. The critical node problem (CNP) aims to find a set of critical nodes from a network whose deletion maximally degrades the pairwise connectivity of the residual network. Due to its general NP-hard nature, state-of-the-art CNP solutions are based on heuristic approaches. Domain knowledge and trial-and-error are usually required when designing such approaches, thus consuming considerable effort and time. This work proposes a feature importance-aware graph attention network for node representation and combines it with dueling double deep Q-network to create an end-to-end algorithm to solve CNP for the first time. It does not need any problem-specific knowledge or labeled datasets as required by most of existing methods. Once the model is trained, it can be generalized to cope with various types of CNPs (with different sizes and topological structures) without re-training. Computational experiments on 28 real-world networks show that the proposed method is highly comparable to state-of-the-art methods. It does not require any problem-specific knowledge and, hence, can be applicable to many applications including those impossible ones by using the existing approaches. It can be combined with some local search methods to further improve its solution quality. Extensive comparison results are given to show its effectiveness in solving CNP.
Authors: Xin Liu, Wei Tao, Wei Li, Dazhi Zhan, Jun Wang, Zhisong Pan
Abstract: Due to its simplicity and efficiency, the first-order gradient method has been extensively employed in training neural networks. Although the optimization problem of the neural network is non-convex, recent research has proved that the first-order method is capable of attaining a global minimum during training over-parameterized neural networks, where the number of parameters is significantly larger than that of training instances. Momentum methods, including the heavy ball (HB) method and Nesterov's accelerated gradient (NAG) method, are the workhorse of first-order gradient methods owning to their accelerated convergence. In practice, NAG often exhibits superior performance than HB. However, current theoretical works fail to distinguish their convergence difference in training neural networks. To fill this gap, we consider the training problem of the two-layer ReLU neural network under over-parameterization and random initialization. Leveraging high-resolution dynamical systems and neural tangent kernel (NTK) theory, our result not only establishes tighter upper bounds of the convergence rate for both HB and NAG, but also provides the first theoretical guarantee for the acceleration of NAG over HB in training neural networks. Finally, we validate our theoretical results on three benchmark datasets.
Authors: Yihao Xue, Kyle Whitecross, Baharan Mirzasoleiman
Abstract: Increasing the size of overparameterized neural networks has been a key in achieving state-of-the-art performance. This is captured by the double descent phenomenon, where the test loss follows a decreasing-increasing-decreasing pattern (or sometimes monotonically decreasing) as model width increases. However, the effect of label noise on the test loss curve has not been fully explored. In this work, we uncover an intriguing phenomenon where label noise leads to a \textit{final ascent} in the originally observed double descent curve. Specifically, under a sufficiently large noise-to-sample-size ratio, optimal generalization is achieved at intermediate widths. Through theoretical analysis, we attribute this phenomenon to the shape transition of test loss variance induced by label noise. Furthermore, we extend the final ascent phenomenon to model density and provide the first theoretical characterization showing that reducing density by randomly dropping trainable parameters improves generalization under label noise. We also thoroughly examine the roles of regularization and sample size. Surprisingly, we find that larger $\ell_2$ regularization and robust learning methods against label noise exacerbate the final ascent. We confirm the validity of our findings through extensive experiments on ReLu networks trained on MNIST, ResNets/ViTs trained on CIFAR-10/100, and InceptionResNet-v2 trained on Stanford Cars with real-world noisy labels.
Authors: Wanqi Xue, Bo An, Shuicheng Yan, Zhongwen Xu
Abstract: The complexity of designing reward functions has been a major obstacle to the wide application of deep reinforcement learning (RL) techniques. Describing an agent's desired behaviors and properties can be difficult, even for experts. A new paradigm called reinforcement learning from human preferences (or preference-based RL) has emerged as a promising solution, in which reward functions are learned from human preference labels among behavior trajectories. However, existing methods for preference-based RL are limited by the need for accurate oracle preference labels. This paper addresses this limitation by developing a method for crowd-sourcing preference labels and learning from diverse human preferences. The key idea is to stabilize reward learning through regularization and correction in a latent space. To ensure temporal consistency, a strong constraint is imposed on the reward model that forces its latent space to be close to the prior distribution. Additionally, a confidence-based reward model ensembling method is designed to generate more stable and reliable predictions. The proposed method is tested on a variety of tasks in DMcontrol and Meta-world and has shown consistent and significant improvements over existing preference-based RL algorithms when learning from diverse feedback, paving the way for real-world applications of RL methods.
Authors: Kai Cui, Christian Fabian, Anam Tahir, Heinz Koeppl
Abstract: Multi-agent reinforcement learning (MARL) remains difficult to scale to many agents. Recent MARL using Mean Field Control (MFC) provides a tractable and rigorous approach to otherwise difficult cooperative MARL. However, the strict MFC assumption of many independent, weakly-interacting agents is too inflexible in practice. We generalize MFC to instead simultaneously model many similar and few complex agents -- as Major-Minor Mean Field Control (M3FC). Theoretically, we give approximation results for finite agent control, and verify the sufficiency of stationary policies for optimality together with a dynamic programming principle. Algorithmically, we propose Major-Minor Mean Field MARL (M3FMARL) for finite agent systems instead of the limiting system. The algorithm is shown to approximate the policy gradient of the underlying M3FC MDP. Finally, we demonstrate its capabilities experimentally in various scenarios. We observe a strong performance in comparison to state-of-the-art policy gradient MARL methods.
Authors: Di Fan, Yannian Kou, Chuanhou Gao
Abstract: Disentangled representation learning aims to learn low-dimensional representations of data, where each dimension corresponds to an underlying generative factor. Currently, Variational Auto-Encoder (VAE) are widely used for disentangled representation learning, with the majority of methods assuming independence among generative factors. However, in real-world scenarios, generative factors typically exhibit complex causal relationships. We thus design a new VAE-based framework named Disentangled Causal Variational Auto-Encoder (DCVAE), which includes a variant of autoregressive flows known as causal flows, capable of learning effective causal disentangled representations. We provide a theoretical analysis of the disentanglement identifiability of DCVAE, ensuring that our model can effectively learn causal disentangled representations. The performance of DCVAE is evaluated on both synthetic and real-world datasets, demonstrating its outstanding capability in achieving causal disentanglement and performing intervention experiments. Moreover, DCVAE exhibits remarkable performance on downstream tasks and has the potential to learn the true causal structure among factors.
Authors: Matthew Middlehurst, Patrick Sch\"afer, Anthony Bagnall
Abstract: In 2017, a research paper compared 18 Time Series Classification (TSC) algorithms on 85 datasets from the University of California, Riverside (UCR) archive. This study, commonly referred to as a `bake off', identified that only nine algorithms performed significantly better than the Dynamic Time Warping (DTW) and Rotation Forest benchmarks that were used. The study categorised each algorithm by the type of feature they extract from time series data, forming a taxonomy of five main algorithm types. This categorisation of algorithms alongside the provision of code and accessible results for reproducibility has helped fuel an increase in popularity of the TSC field. Over six years have passed since this bake off, the UCR archive has expanded to 112 datasets and there have been a large number of new algorithms proposed. We revisit the bake off, seeing how each of the proposed categories have advanced since the original publication, and evaluate the performance of newer algorithms against the previous best-of-category using an expanded UCR archive. We extend the taxonomy to include three new categories to reflect recent developments. Alongside the originally proposed distance, interval, shapelet, dictionary and hybrid based algorithms, we compare newer convolution and feature based algorithms as well as deep learning approaches. We introduce 30 classification datasets either recently donated to the archive or reformatted to the TSC format, and use these to further evaluate the best performing algorithm from each category. Overall, we find that two recently proposed algorithms, Hydra+MultiROCKET and HIVE-COTEv2, perform significantly better than other approaches on both the current and new TSC problems.
Authors: Cornelius Schr\"oder, Jakob H. Macke
Abstract: Many scientific models are composed of multiple discrete components, and scientists often make heuristic decisions about which components to include. Bayesian inference provides a mathematical framework for systematically selecting model components, but defining prior distributions over model components and developing associated inference schemes has been challenging. We approach this problem in a simulation-based inference framework: We define model priors over candidate components and, from model simulations, train neural networks to infer joint probability distributions over both model components and associated parameters. Our method, simulation-based model inference (SBMI), represents distributions over model components as a conditional mixture of multivariate binary distributions in the Grassmann formalism. SBMI can be applied to any compositional stochastic simulator without requiring likelihood evaluations. We evaluate SBMI on a simple time series model and on two scientific models from neuroscience, and show that it can discover multiple data-consistent model configurations, and that it reveals non-identifiable model components and parameters. SBMI provides a powerful tool for data-driven scientific inquiry which will allow scientists to identify essential model components and make uncertainty-informed modelling decisions.
Authors: Yucen Lily Li, Tim G. J. Rudner, Andrew Gordon Wilson
Abstract: Bayesian optimization is a highly efficient approach to optimizing objective functions which are expensive to query. These objectives are typically represented by Gaussian process (GP) surrogate models which are easy to optimize and support exact inference. While standard GP surrogates have been well-established in Bayesian optimization, Bayesian neural networks (BNNs) have recently become practical function approximators, with many benefits over standard GPs such as the ability to naturally handle non-stationarity and learn representations for high-dimensional data. In this paper, we study BNNs as alternatives to standard GP surrogates for optimization. We consider a variety of approximate inference procedures for finite-width BNNs, including high-quality Hamiltonian Monte Carlo, low-cost stochastic MCMC, and heuristics such as deep ensembles. We also consider infinite-width BNNs, linearized Laplace approximations, and partially stochastic models such as deep kernel learning. We evaluate this collection of surrogate models on diverse problems with varying dimensionality, number of objectives, non-stationarity, and discrete and continuous inputs. We find: (i) the ranking of methods is highly problem dependent, suggesting the need for tailored inductive biases; (ii) HMC is the most successful approximate inference procedure for fully stochastic BNNs; (iii) full stochasticity may be unnecessary as deep kernel learning is relatively competitive; (iv) deep ensembles perform relatively poorly; (v) infinite-width BNNs are particularly promising, especially in high dimensions.
Authors: Amit Rozner, Barak Battash, Henry Li, Lior Wolf, Ofir Lindenbaum
Abstract: We propose a modified density estimation problem that is highly effective for detecting anomalies in tabular data. Our approach assumes that the density function is relatively stable (with lower variance) around normal samples. We have verified this hypothesis empirically using a wide range of real-world data. Then, we present a variance-stabilized density estimation problem for maximizing the likelihood of the observed samples while minimizing the variance of the density around normal samples. To obtain a reliable anomaly detector, we introduce a spectral ensemble of autoregressive models for learning the variance-stabilized distribution. We have conducted an extensive benchmark with 52 datasets, demonstrating that our method leads to state-of-the-art results while alleviating the need for data-specific hyperparameter tuning. Finally, we have used an ablation study to demonstrate the importance of each of the proposed components, followed by a stability analysis evaluating the robustness of our model.
Authors: Xiangzhe Kong, Wenbing Huang, Yang Liu
Abstract: Many processes in biology and drug discovery involve various 3D interactions between molecules, such as protein and protein, protein and small molecule, etc. Given that different molecules are usually represented in different granularity, existing methods usually encode each type of molecules independently with different models, leaving it defective to learn the various underlying interaction physics. In this paper, we first propose to universally represent an arbitrary 3D complex as a geometric graph of sets, shedding light on encoding all types of molecules with one model. We then propose a Generalist Equivariant Transformer (GET) to effectively capture both domain-specific hierarchies and domain-agnostic interaction physics. To be specific, GET consists of a bilevel attention module, a feed-forward module and a layer normalization module, where each module is E(3) equivariant and specialized for handling sets of variable sizes. Notably, in contrast to conventional pooling-based hierarchical models, our GET is able to retain fine-grained information of all levels. Extensive experiments on the interactions between proteins, small molecules and RNA/DNAs verify the effectiveness and generalization capability of our proposed method across different domains.
Authors: Leixin Yang, Yu Xiang
Abstract: Mixup is an effective data augmentation method that generates new augmented samples by aggregating linear combinations of different original samples. However, if there are noises or aberrant features in the original samples, Mixup may propagate them to the augmented samples, leading to over-sensitivity of the model to these outliers . To solve this problem, this paper proposes a new Mixup method called AMPLIFY. This method uses the Attention mechanism of Transformer itself to reduce the influence of noises and aberrant values in the original samples on the prediction results, without increasing additional trainable parameters, and the computational cost is very low, thereby avoiding the problem of high resource consumption in common Mixup methods such as Sentence Mixup . The experimental results show that, under a smaller computational resource cost, AMPLIFY outperforms other Mixup methods in text classification tasks on 7 benchmark datasets, providing new ideas and new ways to further improve the performance of pre-trained models based on the Attention mechanism, such as BERT, ALBERT, RoBERTa, and GPT. Our code can be obtained at https://github.com/kiwi-lilo/AMPLIFY.
Authors: Shiguang Wu, Yaqing Wang, Quanming Yao
Abstract: Molecular property prediction (MPP) plays a crucial role in biomedical applications, but it often encounters challenges due to a scarcity of labeled data. Existing works commonly adopt gradient-based strategy to update a large amount of parameters for task-level adaptation. However, the increase of adaptive parameters can lead to overfitting and poor performance. Observing that graph neural network (GNN) performs well as both encoder and predictor, we propose PACIA, a parameter-efficient GNN adapter for few-shot MPP. We design a unified adapter to generate a few adaptive parameters to modulate the message passing process of GNN. We then adopt a hierarchical adaptation mechanism to adapt the encoder at task-level and the predictor at query-level by the unified GNN adapter. Extensive results show that PACIA obtains the state-of-the-art performance in few-shot MPP problems, and our proposed hierarchical adaptation mechanism is rational and effective.
Authors: Christopher A. Choquette-Choo, Krishnamurthy Dvijotham, Krishna Pillutla, Arun Ganesh, Thomas Steinke, Abhradeep Thakurta
Abstract: Differentially private learning algorithms inject noise into the learning process. While the most common private learning algorithm, DP-SGD, adds independent Gaussian noise in each iteration, recent work on matrix factorization mechanisms has shown empirically that introducing correlations in the noise can greatly improve their utility. We characterize the asymptotic learning utility for any choice of the correlation function, giving precise analytical bounds for linear regression and as the solution to a convex program for general convex functions. We show, using these bounds, how correlated noise provably improves upon vanilla DP-SGD as a function of problem parameters such as the effective dimension and condition number. Moreover, our analytical expression for the near-optimal correlation function circumvents the cubic complexity of the semi-definite program used to optimize the noise correlation matrix in previous work. We validate our theory with experiments on private deep learning. Our work matches or outperforms prior work while being efficient both in terms of compute and memory.
Authors: Jannik Deuschel, Caleb N. Ellington, Yingtao Luo, Benjamin J. Lengerich, Pascal Friederich, Eric P. Xing
Abstract: Interpretable policy learning seeks to estimate intelligible decision policies from observed actions; however, existing models force a tradeoff between accuracy and interpretability, limiting data-driven interpretations of human decision-making processes. Fundamentally, existing approaches are burdened by this tradeoff because they represent the underlying decision process as a universal policy, when in fact human decisions are dynamic and can change drastically under different contexts. Thus, we develop Contextualized Policy Recovery (CPR), which re-frames the problem of modeling complex decision processes as a multi-task learning problem, where each context poses a unique task and complex decision policies can be constructed piece-wise from many simple context-specific policies. CPR models each context-specific policy as a linear map, and generates new policy models $\textit{on-demand}$ as contexts are updated with new observations. We provide two flavors of the CPR framework: one focusing on exact local interpretability, and one retaining full global interpretability. We assess CPR through studies on simulated and real data, achieving state-of-the-art performance on predicting antibiotic prescription in intensive care units ($+22\%$ AUROC vs. previous SOTA) and predicting MRI prescription for Alzheimer's patients ($+7.7\%$ AUROC vs. previous SOTA). With this improvement, CPR closes the accuracy gap between interpretable and black-box methods, allowing high-resolution exploration and analysis of context-specific decision models.
Authors: Sebastian Damrich, Philipp Berens, Dmitry Kobak
Abstract: Persistent homology is a popular computational tool for analyzing the topology of point clouds, such as the presence of loops or voids. However, many real-world datasets with low intrinsic dimensionality reside in an ambient space of much higher dimensionality. We show that in this case traditional persistent homology becomes very sensitive to noise and fails to detect the correct topology. The same holds true for existing refinements of persistent homology. As a remedy, we find that spectral distances on the $k$-nearest-neighbor graph of the data, such as diffusion distance and effective resistance, allow to detect the correct topology even in the presence of high-dimensional noise. Moreover, we derive a novel closed-form formula for effective resistance, and describe its relation to diffusion distances. Finally, we apply these methods to high-dimensional single-cell RNA-sequencing data and show that spectral distances allow robust detection of cell cycle loops.
Authors: Yipeng Li, Xinchen Lyu
Abstract: There are two categories of methods in Federated Learning (FL) for joint training across multiple clients: i) parallel FL (PFL), where clients train models in a parallel manner; and ii) sequential FL (SFL), where clients train models in a sequential manner. In contrast to that of PFL, the convergence theory of SFL on heterogeneous data is still lacking. In this paper, we establish the convergence guarantees of SFL for strongly/general/non-convex objectives on heterogeneous data. The convergence guarantees of SFL are better than that of PFL on heterogeneous data with both full and partial client participation. Experimental results validate the counterintuitive analysis result that SFL outperforms PFL on extremely heterogeneous data in cross-device settings.
Authors: Zhong Zheng, Fengyu Gao, Lingzhou Xue, Jing Yang
Abstract: In this paper, we consider federated reinforcement learning for tabular episodic Markov Decision Processes (MDP) where, under the coordination of a central server, multiple agents collaboratively explore the environment and learn an optimal policy without sharing their raw data. While linear speedup in the number of agents has been achieved for some metrics, such as convergence rate and sample complexity, in similar settings, it is unclear whether it is possible to design a model-free algorithm to achieve linear regret speedup with low communication cost. We propose two federated Q-Learning algorithms termed as FedQ-Hoeffding and FedQ-Bernstein, respectively, and show that the corresponding total regrets achieve a linear speedup compared with their single-agent counterparts when the time horizon is sufficiently large, while the communication cost scales logarithmically in the total number of time steps $T$. Those results rely on an event-triggered synchronization mechanism between the agents and the server, a novel step size selection when the server aggregates the local estimates of the state-action values to form the global estimates, and a set of new concentration inequalities to bound the sum of non-martingale differences. This is the first work showing that linear regret speedup and logarithmic communication cost can be achieved by model-free algorithms in federated reinforcement learning.
Authors: Daniel Gei{\ss}ler, Bo Zhou, Mengxi Liu, Sungho Suh, Paul Lukowicz
Abstract: This work offers a heuristic evaluation of the effects of variations in machine learning training regimes and learning paradigms on the energy consumption of computing, especially HPC hardware with a life-cycle aware perspective. While increasing data availability and innovation in high-performance hardware fuels the training of sophisticated models, it also fosters the fading perception of energy consumption and carbon emission. Therefore, the goal of this work is to raise awareness about the energy impact of general training parameters and processes, from learning rate over batch size to knowledge transfer. Multiple setups with different hyperparameter configurations are evaluated on three different hardware systems. Among many results, we have found out that even with the same model and hardware to reach the same accuracy, improperly set training hyperparameters consume up to 5 times the energy of the optimal setup. We also extensively examined the energy-saving benefits of learning paradigms including recycling knowledge through pretraining and sharing knowledge through multitask training.
Authors: Navid Ziaei, Behzad Nazari, Uri T. Eden, Alik Widge, Ali Yousefi
Abstract: Extracting meaningful information from high-dimensional data poses a formidable modeling challenge, particularly when the data is obscured by noise or represented through different modalities. This research proposes a novel non-parametric modeling approach, leveraging the Gaussian process (GP), to characterize high-dimensional data by mapping it to a latent low-dimensional manifold. This model, named the latent discriminative generative decoder (LDGD), employs both the data and associated labels in the manifold discovery process. We derive a Bayesian solution to infer the latent variables, allowing LDGD to effectively capture inherent stochasticity in the data. We demonstrate applications of LDGD on both synthetic and benchmark datasets. Not only does LDGD infer the manifold accurately, but its accuracy in predicting data points' labels surpasses state-of-the-art approaches. In the development of LDGD, we have incorporated inducing points to reduce the computational complexity of Gaussian processes for large datasets, enabling batch training for enhanced efficient processing and scalability. Additionally, we show that LDGD can robustly infer manifold and precisely predict labels for scenarios in that data size is limited, demonstrating its capability to efficiently characterize high-dimensional data with limited samples. These collective attributes highlight the importance of developing non-parametric modeling approaches to analyze high-dimensional data.
Authors: Juefei Chen, Longxiu Huang, Yimin Wei
Abstract: Nonnegative Matrix Factorization (NMF) is an important unsupervised learning method to extract meaningful features from data. To address the NMF problem within a polynomial time framework, researchers have introduced a separability assumption, which has recently evolved into the concept of coseparability. This advancement offers a more efficient core representation for the original data. However, in the real world, the data is more natural to be represented as a multi-dimensional array, such as images or videos. The NMF's application to high-dimensional data involves vectorization, which risks losing essential multi-dimensional correlations. To retain these inherent correlations in the data, we turn to tensors (multidimensional arrays) and leverage the tensor t-product. This approach extends the coseparable NMF to the tensor setting, creating what we term coseparable Nonnegative Tensor Factorization (NTF). In this work, we provide an alternating index selection method to select the coseparable core. Furthermore, we validate the t-CUR sampling theory and integrate it with the tensor Discrete Empirical Interpolation Method (t-DEIM) to introduce an alternative, randomized index selection process. These methods have been tested on both synthetic and facial analysis datasets. The results demonstrate the efficiency of coseparable NTF when compared to coseparable NMF.
Authors: Akifumi Wachi, Xun Shen, Yanan Sui
Abstract: Safety is critical when applying reinforcement learning (RL) to real-world problems. As a result, safe RL has emerged as a fundamental and powerful paradigm for optimizing an agent's policy while incorporating notions of safety. A prevalent safe RL approach is based on a constrained criterion, which seeks to maximize the expected cumulative reward subject to specific safety constraints. Despite recent effort to enhance safety in RL, a systematic understanding of the field remains difficult. This challenge stems from the diversity of constraint representations and little exploration of their interrelations. To bridge this knowledge gap, we present a comprehensive review of representative constraint formulations, along with a curated selection of algorithms designed specifically for each formulation. In addition, we elucidate the theoretical underpinnings that reveal the mathematical mutual relations among common problem formulations. We conclude with a discussion of the current state and future directions of safe reinforcement learning research.
Authors: Z Liu, J Lou, W Bao, Y Hu, B Li, Z Qin, K Ren
Abstract: Fine-tuning on task-specific datasets is a widely-embraced paradigm of harnessing the powerful capability of pretrained LLMs for various downstream tasks. Due to the popularity of LLMs fine-tuning and its accompanying privacy concerns, differentially private (DP) fine-tuning of pretrained LLMs has been widely used to safeguarding the privacy of task-specific datasets. Lying at the design core of DP LLM fine-tuning methods is the satisfactory tradeoff among privacy, utility, and scalability. Most existing methods build upon the seminal work of DP-SGD. Despite pushing the scalability of DP-SGD to its limit, DP-SGD-based fine-tuning methods are unfortunately limited by the inherent inefficiency of SGD. In this paper, we investigate the potential of DP zeroth-order methods for LLM pretraining, which avoids the scalability bottleneck of SGD by approximating the gradient with the more efficient zeroth-order gradient. Rather than treating the zeroth-order method as a drop-in replacement for SGD, this paper presents a comprehensive study both theoretically and empirically. First, we propose the stagewise DP zeroth-order method (DP-ZOSO) that dynamically schedules key hyperparameters. This design is grounded on the synergy between DP random perturbation and the gradient approximation error of the zeroth-order method, and its effect on fine-tuning trajectory. We provide theoretical analysis for both proposed methods. We conduct extensive empirical analysis on both encoder-only masked language model and decoder-only autoregressive language model, achieving impressive results in terms of scalability and utility (compared with DPZero, DP-ZOPO improves 4.5% on SST-5, 5.5% on MNLI with RoBERTa-Large and 9.2% on CB, 3.9% on BoolQ with OPT-2.7B when $\epsilon=4$).
Authors: Franco Galante, Giovanni Neglia, Emilio Leonardi
Abstract: In numerous settings, agents lack sufficient data to directly learn a model. Collaborating with other agents may help, but it introduces a bias-variance trade-off, when local data distributions differ. A key challenge is for each agent to identify clients with similar distributions while learning the model, a problem that remains largely unresolved. This study focuses on a simplified version of the overarching problem, where each agent collects samples from a real-valued distribution over time to estimate its mean. Existing algorithms face impractical space and time complexities (quadratic in the number of agents A). To address scalability challenges, we propose a framework where agents self-organize into a graph, allowing each agent to communicate with only a selected number of peers r. We introduce two collaborative mean estimation algorithms: one draws inspiration from belief propagation, while the other employs a consensus-based approach, with complexity of O( r |A| log |A|) and O(r |A|), respectively. We establish conditions under which both algorithms yield asymptotically optimal estimates and offer a theoretical characterization of their performance.
Authors: Wee Chaimanowong, Ying Zhu
Abstract: Permutation invariance is among the most common symmetry that can be exploited to simplify complex problems in machine learning (ML). There has been a tremendous surge of research activities in building permutation invariant ML architectures. However, less attention is given to: (1) how to statistically test for permutation invariance of coordinates in a random vector where the dimension is allowed to grow with the sample size; (2) how to leverage permutation invariance in estimation problems and how does it help reduce dimensions. In this paper, we take a step back and examine these questions in several fundamental problems: (i) testing the assumption of permutation invariance of multivariate distributions; (ii) estimating permutation invariant densities; (iii) analyzing the metric entropy of permutation invariant function classes and compare them with their counterparts without imposing permutation invariance; (iv) deriving an embedding of permutation invariant reproducing kernel Hilbert spaces for efficient computation. In particular, our methods for (i) and (iv) are based on a sorting trick and (ii) is based on an averaging trick. These tricks substantially simplify the exploitation of permutation invariance.
Authors: Hannes Waclawek, Stefan Huber
Abstract: Piecewise Polynomials (PPs) are utilized in several engineering disciplines, like trajectory planning, to approximate position profiles given in the form of a set of points. While the approximation target along with domain-specific requirements, like Ck -continuity, can be formulated as a system of equations and a result can be computed directly, such closed-form solutions posses limited flexibility with respect to polynomial degrees, polynomial bases or adding further domain-specific requirements. Sufficiently complex optimization goals soon call for the use of numerical methods, like gradient descent. Since gradient descent lies at the heart of training Artificial Neural Networks (ANNs), modern Machine Learning (ML) frameworks like TensorFlow come with a set of gradient-based optimizers potentially suitable for a wide range of optimization problems beyond the training task for ANNs. Our approach is to utilize the versatility of PP models and combine it with the potential of modern ML optimizers for the use in function approximation in 1D trajectory planning in the context of electronic cam design. We utilize available optimizers of the ML framework TensorFlow directly, outside of the scope of ANNs, to optimize model parameters of our PP model. In this paper, we show how an orthogonal polynomial basis contributes to improving approximation and continuity optimization performance. Utilizing Chebyshev polynomials of the first kind, we develop a novel regularization approach enabling clearly improved convergence behavior. We show that, using this regularization approach, Chebyshev basis performs better than power basis for all relevant optimizers in the combined approximation and continuity optimization setting and demonstrate usability of the presented approach within the electronic cam domain.
Authors: Yasin Sonmez, Neelay Junnarkar, Murat Arcak
Abstract: Recent work in reinforcement learning has leveraged symmetries in the model to improve sample efficiency in training a policy. A commonly used simplifying assumption is that the dynamics and reward both exhibit the same symmetry. However, in many real-world environments, the dynamical model exhibits symmetry independent of the reward model: the reward may not satisfy the same symmetries as the dynamics. In this paper, we investigate scenarios where only the dynamics are assumed to exhibit symmetry, extending the scope of problems in reinforcement learning and learning in control theory where symmetry techniques can be applied. We use Cartan's moving frame method to introduce a technique for learning dynamics which, by construction, exhibit specified symmetries. We demonstrate through numerical experiments that the proposed method learns a more accurate dynamical model.
Authors: Jiawu Tian, Liwei Xu, Xiaowei Zhang, Yongqi Li
Abstract: Training deep neural networks is a challenging task. In order to speed up training and enhance the performance of deep neural networks, we rectify the vanilla conjugate gradient as conjugate-gradient-like and incorporate it into the generic Adam, and thus propose a new optimization algorithm named CG-like-Adam for deep learning. Specifically, both the first-order and the second-order moment estimation of generic Adam are replaced by the conjugate-gradient-like. Convergence analysis handles the cases where the exponential moving average coefficient of the first-order moment estimation is constant and the first-order moment estimation is unbiased. Numerical experiments show the superiority of the proposed algorithm based on the CIFAR10/100 dataset.
Authors: Yu Wang, Lei Sang, Yi Zhang, Yiwen Zhang
Abstract: Heterogeneous Graphs (HGs) can effectively model complex relationships in the real world by multi-type nodes and edges. In recent years, inspired by self-supervised learning, contrastive Heterogeneous Graphs Neural Networks (HGNNs) have shown great potential by utilizing data augmentation and contrastive discriminators for downstream tasks. However, data augmentation is still limited due to the graph data's integrity. Furthermore, the contrastive discriminators remain sampling bias and lack local heterogeneous information. To tackle the above limitations, we propose a novel Generative-Enhanced Heterogeneous Graph Contrastive Learning (GHGCL). Specifically, we first propose a heterogeneous graph generative learning enhanced contrastive paradigm. This paradigm includes: 1) A contrastive view augmentation strategy by using a masked autoencoder. 2) Position-aware and semantics-aware positive sample sampling strategy for generating hard negative samples. 3) A hierarchical contrastive learning strategy for capturing local and global information. Furthermore, the hierarchical contrastive learning and sampling strategies aim to constitute an enhanced contrastive discriminator under the generative-contrastive perspective. Finally, we compare our model with seventeen baselines on eight real-world datasets. Our model outperforms the latest contrastive and generative baselines on node classification and link prediction tasks. To reproduce our work, we have open-sourced our code at https://anonymous.4open.science/r/GC-HGNN-E50C.
Authors: Andrew Thompson
Abstract: Machine learning (ML) models are increasingly being used in metrology applications. However, for ML models to be credible in a metrology context they should be accompanied by principled uncertainty quantification. This paper addresses the challenge of uncertainty propagation through trained/fixed machine learning (ML) regression models. Analytical expressions for the mean and variance of the model output are obtained/presented for certain input data distributions and for a variety of ML models. Our results cover several popular ML models including linear regression, penalised linear regression, kernel ridge regression, Gaussian Processes (GPs), support vector machines (SVMs) and relevance vector machines (RVMs). We present numerical experiments in which we validate our methods and compare them with a Monte Carlo approach from a computational efficiency point of view. We also illustrate our methods in the context of a metrology application, namely modelling the state-of-health of lithium-ion cells based upon Electrical Impedance Spectroscopy (EIS) data
Authors: Peyman Gholami, Hulya Seferoglu
Abstract: This paper focuses on reducing the communication cost of federated learning by exploring generalization bounds and representation learning. We first characterize a tighter generalization bound for one-round federated learning based on local clients' generalizations and heterogeneity of data distribution (non-iid scenario). We also characterize a generalization bound in R-round federated learning and its relation to the number of local updates (local stochastic gradient descents (SGDs)). Then, based on our generalization bound analysis and our representation learning interpretation of this analysis, we show for the first time that less frequent aggregations, hence more local updates, for the representation extractor (usually corresponds to initial layers) leads to the creation of more generalizable models, particularly for non-iid scenarios. We design a novel Federated Learning with Adaptive Local Steps (FedALS) algorithm based on our generalization bound and representation learning analysis. FedALS employs varying aggregation frequencies for different parts of the model, so reduces the communication cost. The paper is followed with experimental results showing the effectiveness of FedALS.
Authors: Yujing Liu, Zongqian Wu, Zhengyu Lu, Ci Nie, Guoqiu Wen, Ping Hu, Xiaofeng Zhu
Abstract: Previous graph neural networks (GNNs) usually assume that the graph data is with clean labels for representation learning, but it is not true in real applications. In this paper, we propose a new multi-teacher distillation method based on bi-level optimization (namely BO-NNC), to conduct noisy node classification on the graph data. Specifically, we first employ multiple self-supervised learning methods to train diverse teacher models, and then aggregate their predictions through a teacher weight matrix. Furthermore, we design a new bi-level optimization strategy to dynamically adjust the teacher weight matrix based on the training progress of the student model. Finally, we design a label improvement module to improve the label quality. Extensive experimental results on real datasets show that our method achieves the best results compared to state-of-the-art methods.
Authors: Abdoul Jalil Djiberou Mahamadou, Lea Goetz, Russ Altman
Abstract: Inherent bias within society can be amplified and perpetuated by artificial intelligence (AI) systems. To address this issue, a wide range of solutions have been proposed to identify and mitigate bias and enforce fairness for individuals and groups. Recently, Graph Laplacian Regularizer (GLR), a regularization technique from the semi-supervised learning literature has been used as a substitute for the common Lipschitz condition to enhance individual fairness. Notable prior work has shown that enforcing individual fairness through a GLR can improve the transfer learning accuracy of AI models under covariate shifts. However, the prior work defines a GLR on the source and target data combined, implicitly assuming that the target data are available at train time, which might not hold in practice. In this work, we investigated whether defining a GLR independently on the train and target data could maintain similar accuracy. Furthermore, we introduced the Normalized Fairness Gain score (NFG) to measure individual fairness by measuring the amount of gained fairness when a GLR is used versus not. We evaluated the new and original methods under NFG, the Prediction Consistency (PC), and traditional classification metrics on the German Credit Approval dataset. The results showed that the two models achieved similar statistical mean performances over five-fold cross-validation. Furthermore, the proposed metric showed that PC scores can be misleading as the scores can be high and statistically similar to fairness-enhanced models while NFG scores are small. This work therefore provides new insights into when a GLR effectively enhances individual fairness and the pitfalls of PC.
Authors: Daniel Fesalbon
Abstract: With recent studies related to Neural Networks being used on different forecasting and time series investigations, this study aims to expand these contexts to ferry passenger traffic. The primary objective of the study is to investigate and evaluate an LSTM-based Neural Networks' capability to forecast ferry passengers of two ports in the Philippines. The proposed model's fitting and evaluation of the passenger flow forecasting of the two ports is based on monthly passenger traffic from 2016 to 2022 data that was acquired from the Philippine Ports Authority (PPA). This work uses Mean Absolute Percentage Error (MAPE) as its primary metric to evaluate the model's forecasting capability. The proposed LSTM-based Neural Networks model achieved 72% forecasting accuracy to the Batangas port ferry passenger data and 74% forecasting accuracy to the Mindoro port ferry passenger data. Using Keras and Scikit-learn Python libraries, this work concludes a reasonable forecasting performance of the presented LSTM model. Aside from these notable findings, this study also recommends further investigation and studies on employing other statistical, machine learning, and deep learning methods on forecasting ferry passenger flows.
Authors: Dahyun Jeong, Hyelim Son, Yunjin Choi, Keunwoo Kim
Abstract: Our study presents a framework for predicting image-based social media content popularity that focuses on addressing complex image information and a hierarchical data structure. We utilize the Google Cloud Vision API to effectively extract key image and color information from users' postings, achieving 6.8% higher accuracy compared to using non-image covariates alone. For prediction, we explore a wide range of prediction models, including Linear Mixed Model, Support Vector Regression, Multi-layer Perceptron, Random Forest, and XGBoost, with linear regression as the benchmark. Our comparative study demonstrates that models that are capable of capturing the underlying nonlinear interactions between covariates outperform other methods.
Authors: Luise Ge, Brendan Juba, Yevgeniy Vorobeychik
Abstract: We study learnability of linear utility functions from pairwise comparison queries. In particular, we consider two learning objectives. The first objective is to predict out-of-sample responses to pairwise comparisons, whereas the second is to approximately recover the true parameters of the utility function. We show that in the passive learning setting, linear utilities are efficiently learnable with respect to the first objective, both when query responses are uncorrupted by noise, and under Tsybakov noise when the distributions are sufficiently "nice". In contrast, we show that utility parameters are not learnable for a large set of data distributions without strong modeling assumptions, even when query responses are noise-free. Next, we proceed to analyze the learning problem in an active learning setting. In this case, we show that even the second objective is efficiently learnable, and present algorithms for both the noise-free and noisy query response settings. Our results thus exhibit a qualitative learnability gap between passive and active learning from pairwise preference queries, demonstrating the value of the ability to select pairwise queries for utility learning.
Authors: Alberto Caron, Chris Hicks, Vasilios Mavroudis
Abstract: We study the problem of efficiently detecting Out-of-Distribution (OOD) samples at test time in supervised and unsupervised learning contexts. While ML models are typically trained under the assumption that training and test data stem from the same distribution, this is often not the case in realistic settings, thus reliably detecting distribution shifts is crucial at deployment. We re-formulate the OOD problem under the lenses of statistical testing and then discuss conditions that render the OOD problem identifiable in statistical terms. Building on this framework, we study convergence guarantees of an OOD test based on the Wasserstein distance, and provide a simple empirical evaluation.
Authors: Sher Badshah, Hassan Sajjad
Abstract: Scale is often attributed as one of the factors that cause an increase in the performance of LLMs, resulting in models with billion and trillion parameters. One of the limitations of such large models is the high computational requirements that limit their usage, deployment, and debugging in resource-constrained scenarios. Two commonly used alternatives to bypass these limitations are to use the smaller versions of LLMs (e.g. Llama 7B instead of Llama 70B) and lower the memory requirements by using quantization. While these approaches effectively address the limitation of resources, their impact on model performance needs thorough examination. In this study, we perform a comprehensive evaluation to investigate the effect of model scale and quantization on the performance. We experiment with two major families of open-source instruct models ranging from 7 billion to 70 billion parameters. Our extensive zero-shot experiments across various tasks including natural language understanding, reasoning, misinformation detection, and hallucination reveal that larger models generally outperform their smaller counterparts, suggesting that scale remains an important factor in enhancing performance. We found that larger models show exceptional resilience to precision reduction and can maintain high accuracy even at 4-bit quantization for numerous tasks and they serve as a better solution than using smaller models at high precision under similar memory requirements.
Authors: Tao Han, Zhenghao Chen, Song Guo, Wanghan Xu, Lei Bai
Abstract: The advent of data-driven weather forecasting models, which learn from hundreds of terabytes (TB) of reanalysis data, has significantly advanced forecasting capabilities. However, the substantial costs associated with data storage and transmission present a major challenge for data providers and users, affecting resource-constrained researchers and limiting their accessibility to participate in AI-based meteorological research. To mitigate this issue, we introduce an efficient neural codec, the Variational Autoencoder Transformer (VAEformer), for extreme compression of climate data to significantly reduce data storage cost, making AI-based meteorological research portable to researchers. Our approach diverges from recent complex neural codecs by utilizing a low-complexity Auto-Encoder transformer. This encoder produces a quantized latent representation through variance inference, which reparameterizes the latent space as a Gaussian distribution. This method improves the estimation of distributions for cross-entropy coding. Extensive experiments demonstrate that our VAEformer outperforms existing state-of-the-art compression methods in the context of climate data. By applying our VAEformer, we compressed the most popular ERA5 climate dataset (226 TB) into a new dataset, CRA5 (0.7 TB). This translates to a compression ratio of over 300 while retaining the dataset's utility for accurate scientific analysis. Further, downstream experiments show that global weather forecasting models trained on the compact CRA5 dataset achieve forecasting accuracy comparable to the model trained on the original dataset. Code, the CRA5 dataset, and the pre-trained model are available at https://github.com/taohan10200/CRA5.
Authors: Guanghao Wei, Yining Huang, Chenru Duan, Yue Song, Yuanqi Du
Abstract: Recent progress of deep generative models in the vision and language domain has stimulated significant interest in more structured data generation such as molecules. However, beyond generating new random molecules, efficient exploration and a comprehensive understanding of the vast chemical space are of great importance to molecular science and applications in drug design and materials discovery. In this paper, we propose a new framework, ChemFlow, to traverse chemical space through navigating the latent space learned by molecule generative models through flows. We introduce a dynamical system perspective that formulates the problem as learning a vector field that transports the mass of the molecular distribution to the region with desired molecular properties or structure diversity. Under this framework, we unify previous approaches on molecule latent space traversal and optimization and propose alternative competing methods incorporating different physical priors. We validate the efficacy of ChemFlow on molecule manipulation and single- and multi-objective molecule optimization tasks under both supervised and unsupervised molecular discovery settings. Codes and demos are publicly available on GitHub at https://github.com/garywei944/ChemFlow.
Authors: Rudy Bunel, Krishnamurthy Dvijotham, M. Pawan Kumar, Alessandro De Palma, Robert Stanforth
Abstract: We develop the first (to the best of our knowledge) provably correct neural networks for a precise computational task, with the proof of correctness generated by an automated verification algorithm without any human input. Prior work on neural network verification has focused on partial specifications that, even when satisfied, are not sufficient to ensure that a neural network never makes errors. We focus on applying neural network verification to computational tasks with a precise notion of correctness, where a verifiably correct neural network provably solves the task at hand with no caveats. In particular, we develop an approach to train and verify the first provably correct neural networks for compressed sensing, i.e., recovering sparse vectors from a number of measurements smaller than the dimension of the vector. We show that for modest problem dimensions (up to 50), we can train neural networks that provably recover a sparse vector from linear and binarized linear measurements. Furthermore, we show that the complexity of the network (number of neurons/layers) can be adapted to the problem difficulty and solve problems where traditional compressed sensing methods are not known to provably work.
Authors: Ding Chen, Peixi Peng, Tiejun Huang, Yonghong Tian
Abstract: With the help of special neuromorphic hardware, spiking neural networks (SNNs) are expected to realize artificial intelligence (AI) with less energy consumption. It provides a promising energy-efficient way for realistic control tasks by combining SNNs with deep reinforcement learning (RL). There are only a few existing SNN-based RL methods at present. Most of them either lack generalization ability or employ Artificial Neural Networks (ANNs) to estimate value function in training. The former needs to tune numerous hyper-parameters for each scenario, and the latter limits the application of different types of RL algorithm and ignores the large energy consumption in training. To develop a robust spike-based RL method, we draw inspiration from non-spiking interneurons found in insects and propose the deep spiking Q-network (DSQN), using the membrane voltage of non-spiking neurons as the representation of Q-value, which can directly learn robust policies from high-dimensional sensory inputs using end-to-end RL. Experiments conducted on 17 Atari games demonstrate the DSQN is effective and even outperforms the ANN-based deep Q-network (DQN) in most games. Moreover, the experiments show superior learning stability and robustness to adversarial attacks of DSQN.
Authors: Pedram Agand, Michael Chang, Mo Chen
Abstract: Utilizing a single camera for measuring object distances is a cost-effective alternative to stereo-vision and LiDAR. Although monocular distance estimation has been explored in the literature, most existing techniques rely on object class knowledge to achieve high performance. Without this contextual data, monocular distance estimation becomes more challenging, lacking reference points and object-specific cues. However, these cues can be misleading for objects with wide-range variation or adversarial situations, which is a challenging aspect of object-agnostic distance estimation. In this paper, we propose DMODE, a class-agnostic method for monocular distance estimation that does not require object class knowledge. DMODE estimates an object's distance by fusing its fluctuation in size over time with the camera's motion, making it adaptable to various object detectors and unknown objects, thus addressing these challenges. We evaluate our model on the KITTI MOTS dataset using ground-truth bounding box annotations and outputs from TrackRCNN and EagerMOT. The object's location is determined using the change in bounding box sizes and camera position without measuring the object's detection source or class attributes. Our approach demonstrates superior performance in multi-class object distance detection scenarios compared to conventional methods.
Authors: Abrar Zahin, Rajasekhar Anguluri, Lalitha Sankar, Oliver Kosut, Gautam Dasarathy
Abstract: In Gaussian graphical model selection, noise-corrupted samples present significant challenges. It is known that even minimal amounts of noise can obscure the underlying structure, leading to fundamental identifiability issues. A recent line of work addressing this "robust model selection" problem narrows its focus to tree-structured graphical models. Even within this specific class of models, exact structure recovery is shown to be impossible. However, several algorithms have been developed that are known to provably recover the underlying tree-structure up to an (unavoidable) equivalence class. In this paper, we extend these results beyond tree-structured graphs. We first characterize the equivalence class up to which general graphs can be recovered in the presence of noise. Despite the inherent ambiguity (which we prove is unavoidable), the structure that can be recovered reveals local clustering information and global connectivity patterns in the underlying model. Such information is useful in a range of real-world problems, including power grids, social networks, protein-protein interactions, and neural structures. We then propose an algorithm which provably recovers the underlying graph up to the identified ambiguity. We further provide finite sample guarantees in the high-dimensional regime for our algorithm and validate our results through numerical simulations.
Authors: Linyuan Gong, Jiayi Wang, Alvin Cheung
Abstract: We propose the Adversarial DEep Learning Transpiler (ADELT), a novel approach to source-to-source transpilation between deep learning frameworks. ADELT uniquely decouples code skeleton transpilation and API keyword mapping. For code skeleton transpilation, it uses few-shot prompting on large language models (LLMs), while for API keyword mapping, it uses contextual embeddings from a code-specific BERT. These embeddings are trained in a domain-adversarial setup to generate a keyword translation dictionary. ADELT is trained on an unlabeled web-crawled deep learning corpus, without relying on any hand-crafted rules or parallel data. It outperforms state-of-the-art transpilers, improving pass@1 rate by 17.4 pts and 15.0 pts for PyTorch-Keras and PyTorch-MXNet transpilation pairs respectively. We provide open access to our code at https://github.com/gonglinyuan/adelt.
Authors: Berk Iskender, Marc L. Klasky, Yoram Bresler
Abstract: Dynamic imaging addresses the recovery of a time-varying 2D or 3D object at each time instant using its undersampled measurements. In particular, in the case of dynamic tomography, only a single projection at a single view angle may be available at a time, making the problem severely ill-posed. We propose an approach, RED-PSM, which combines for the first time two powerful techniques to address this challenging imaging problem. The first, are non-parametric factorized low rank models, also known as partially separable models (PSMs), which have been used to efficiently introduce a low-rank prior for the spatio-temporal object. The second is the recent Regularization by Denoising (RED), which provides a flexible framework to exploit the impressive performance of state-of-the-art image denoising algorithms, for various inverse problems. We propose a partially separable objective with RED and a computationally efficient and scalable optimization scheme with variable splitting and ADMM. Theoretical analysis proves the convergence of our objective to a value corresponding to a stationary point satisfying the first-order optimality conditions. Convergence is accelerated by a particular projection-domain-based initialization. We demonstrate the performance and computational improvements of our proposed RED-PSM with a learned image denoiser by comparing it to a recent deep-prior-based method known as TD-DIP. Although the main focus is on dynamic tomography, we also show performance advantages of RED-PSM in a cardiac dynamic MRI setting.
Authors: Sacha Morin, Robin Legault, F\'elix Lalibert\'e, Zsuzsa Bakk, Charles-\'Edouard Gigu\`ere, Roxane de la Sablonni\`ere, \'Eric Lacourse
Abstract: StepMix is an open-source Python package for the pseudo-likelihood estimation (one-, two- and three-step approaches) of generalized finite mixture models (latent profile and latent class analysis) with external variables (covariates and distal outcomes). In many applications in social sciences, the main objective is not only to cluster individuals into latent classes, but also to use these classes to develop more complex statistical models. These models generally divide into a measurement model that relates the latent classes to observed indicators, and a structural model that relates covariates and outcome variables to the latent classes. The measurement and structural models can be estimated jointly using the so-called one-step approach or sequentially using stepwise methods, which present significant advantages for practitioners regarding the interpretability of the estimated latent classes. In addition to the one-step approach, StepMix implements the most important stepwise estimation methods from the literature, including the bias-adjusted three-step methods with Bolk-Croon-Hagenaars and maximum likelihood corrections and the more recent two-step approach. These pseudo-likelihood estimators are presented in this paper under a unified framework as specific expectation-maximization subroutines. To facilitate and promote their adoption among the data science community, StepMix follows the object-oriented design of the scikit-learn library and provides an additional R wrapper.
Authors: Sai Sathiesh Rajan, Ezekiel Soremekun, Yves Le Traon, Sudipta Chattopadhyay
Abstract: Ensuring that all classes of objects are detected with equal accuracy is essential in AI systems. For instance, being unable to identify any one class of objects could have fatal consequences in autonomous driving systems. Hence, ensuring the reliability of image recognition systems is crucial. This work addresses how to validate group fairness in image recognition software. We propose a distribution-aware fairness testing approach (called DistroFair) that systematically exposes class-level fairness violations in image classifiers via a synergistic combination of out-of-distribution (OOD) testing and semantic-preserving image mutation. DistroFair automatically learns the distribution (e.g., number/orientation) of objects in a set of images. Then it systematically mutates objects in the images to become OOD using three semantic-preserving image mutations - object deletion, object insertion and object rotation. We evaluate DistroFair using two well-known datasets (CityScapes and MS-COCO) and three major, commercial image recognition software (namely, Amazon Rekognition, Google Cloud Vision and Azure Computer Vision). Results show that about 21% of images generated by DistroFair reveal class-level fairness violations using either ground truth or metamorphic oracles. DistroFair is up to 2.3x more effective than two main baselines, i.e., (a) an approach which focuses on generating images only within the distribution (ID) and (b) fairness analysis using only the original image dataset. We further observed that DistroFair is efficient, it generates 460 images per hour, on average. Finally, we evaluate the semantic validity of our approach via a user study with 81 participants, using 30 real images and 30 corresponding mutated images generated by DistroFair. We found that images generated by DistroFair are 80% as realistic as real-world images.
Authors: Sicen Liu, Xiaolong Wang, Xianbing Zhao, Hao Chen
Abstract: Medication recommendation is a fundamental yet crucial branch of healthcare that presents opportunities to assist physicians in making more accurate medication prescriptions for patients with complex health conditions. Previous studies have primarily focused on learning patient representation from electronic health records (EHR). While considering the clinical manifestations of the patient is important, incorporating domain-specific prior knowledge is equally significant in diagnosing the patient's health conditions. However, effectively integrating domain knowledge with the patient's clinical manifestations can be challenging, particularly when dealing with complex clinical manifestations. Therefore, in this paper, we first identify comprehensive domain-specific prior knowledge, namely the Unified Medical Language System (UMLS), which is a comprehensive repository of biomedical vocabularies and standards, for knowledge extraction. Subsequently, we propose a knowledge injection module that addresses the effective integration of domain knowledge with complex clinical manifestations, enabling an effective characterization of the health conditions of the patient. Furthermore, considering the significant impact of a patient's medication history on their current medication, we introduce a historical medication-aware patient representation module to capture the longitudinal influence of historical medication information on the representation of current patients. Extensive experiments on three publicly benchmark datasets verify the superiority of our proposed method, which outperformed other methods by a significant margin. The code is available at: https://github.com/sherry6247/DKINet.
Authors: Jos\'e E. Chac\'on, Javier Fern\'andez Serrano
Abstract: The number of modes in a probability density function is representative of the complexity of a model and can also be viewed as the number of subpopulations. Despite its relevance, there has been limited research in this area. A novel approach to estimating the number of modes in the univariate setting is presented, focusing on prediction accuracy and inspired by some overlooked aspects of the problem: the need for structure in the solutions, the subjective and uncertain nature of modes, and the convenience of a holistic view that blends local and global density properties. The technique combines flexible kernel estimators and parsimonious compositional splines in the Bayesian inference paradigm, providing soft solutions and incorporating expert judgment. The procedure includes feature exploration, model selection, and mode testing, illustrated in a sports analytics case study showcasing multiple companion visualisation tools. A thorough simulation study also demonstrates that traditional modality-driven approaches paradoxically struggle to provide accurate results. In this context, the new method emerges as a top-tier alternative, offering innovative solutions for analysts.
Authors: Oscar Carlsson, Jan E. Gerken, Hampus Linander, Heiner Spie{\ss}, Fredrik Ohlsson, Christoffer Petersson, Daniel Persson
Abstract: High-resolution wide-angle fisheye images are becoming more and more important for robotics applications such as autonomous driving. However, using ordinary convolutional neural networks or vision transformers on this data is problematic due to projection and distortion losses introduced when projecting to a rectangular grid on the plane. We introduce the HEAL-SWIN transformer, which combines the highly uniform Hierarchical Equal Area iso-Latitude Pixelation (HEALPix) grid used in astrophysics and cosmology with the Hierarchical Shifted-Window (SWIN) transformer to yield an efficient and flexible model capable of training on high-resolution, distortion-free spherical data. In HEAL-SWIN, the nested structure of the HEALPix grid is used to perform the patching and windowing operations of the SWIN transformer, enabling the network to process spherical representations with minimal computational overhead. We demonstrate the superior performance of our model on both synthetic and real automotive datasets, as well as a selection of other image datasets, for semantic segmentation, depth regression and classification tasks. Our code is publicly available at https://github.com/JanEGerken/HEAL-SWIN.
Authors: Yongcheng Dai, Bangti Jin, Ramesh Sau, Zhi Zhou
Abstract: In this work, we investigate a neural network based solver for optimal control problems (without / with box constraint) for linear and semilinear second-order elliptic problems. It utilizes a coupled system derived from the first-order optimality system of the optimal control problem, and employs deep neural networks to represent the solutions to the reduced system. We present an error analysis of the scheme, and provide $L^2(\Omega)$ error bounds on the state, control and adjoint in terms of neural network parameters (e.g., depth, width, and parameter bounds) and the numbers of sampling points. The main tools in the analysis include offset Rademacher complexity and boundedness and Lipschitz continuity of neural network functions. We present several numerical examples to illustrate the method and compare it with two existing ones.
Authors: Reem I. Masoud, Ziquan Liu, Martin Ferianc, Philip Treleaven, Miguel Rodrigues
Abstract: The deployment of large language models (LLMs) raises concerns regarding their cultural misalignment and potential ramifications on individuals and societies with diverse cultural backgrounds. While the discourse has focused mainly on political and social biases, our research proposes a Cultural Alignment Test (Hoftede's CAT) to quantify cultural alignment using Hofstede's cultural dimension framework, which offers an explanatory cross-cultural comparison through the latent variable analysis. We apply our approach to quantitatively evaluate LLMs, namely Llama 2, GPT-3.5, and GPT-4, against the cultural dimensions of regions like the United States, China, and Arab countries, using different prompting styles and exploring the effects of language-specific fine-tuning on the models' behavioural tendencies and cultural values. Our results quantify the cultural alignment of LLMs and reveal the difference between LLMs in explanatory cultural dimensions. Our study demonstrates that while all LLMs struggle to grasp cultural values, GPT-4 shows a unique capability to adapt to cultural nuances, particularly in Chinese settings. However, it faces challenges with American and Arab cultures. The research also highlights that fine-tuning LLama 2 models with different languages changes their responses to cultural questions, emphasizing the need for culturally diverse development in AI for worldwide acceptance and ethical use. For more details or to contribute to this research, visit our GitHub page https://github.com/reemim/Hofstedes_CAT/
Authors: Lasse Elsem\"uller, Hans Olischl\"ager, Marvin Schmitt, Paul-Christian B\"urkner, Ullrich K\"othe, Stefan T. Radev
Abstract: Sensitivity analyses reveal the influence of various modeling choices on the outcomes of statistical analyses. While theoretically appealing, they are overwhelmingly inefficient for complex Bayesian models. In this work, we propose sensitivity-aware amortized Bayesian inference (SA-ABI), a multifaceted approach to efficiently integrate sensitivity analyses into simulation-based inference with neural networks. First, we utilize weight sharing to encode the structural similarities between alternative likelihood and prior specifications in the training process with minimal computational overhead. Second, we leverage the rapid inference of neural networks to assess sensitivity to data perturbations and preprocessing steps. In contrast to most other Bayesian approaches, both steps circumvent the costly bottleneck of refitting the model for each choice of likelihood, prior, or data set. Finally, we propose to use deep ensembles to detect sensitivity arising from unreliable approximation (e.g., due to model misspecification). We demonstrate the effectiveness of our method in applied modeling problems, ranging from disease outbreak dynamics and global warming thresholds to human decision-making. Our results support sensitivity-aware inference as a default choice for amortized Bayesian workflows, automatically providing modelers with insights into otherwise hidden dimensions.
Authors: Ming Zhong, Chenxin An, Weizhu Chen, Jiawei Han, Pengcheng He
Abstract: Large Language Models (LLMs) inherently encode a wealth of knowledge within their parameters through pre-training on extensive corpora. While prior research has delved into operations on these parameters to manipulate the underlying implicit knowledge (encompassing detection, editing, and merging), there remains an ambiguous understanding regarding their transferability across models with varying scales. In this paper, we seek to empirically investigate knowledge transfer from larger to smaller models through a parametric perspective. To achieve this, we employ sensitivity-based techniques to extract and align knowledge-specific parameters between different LLMs. Moreover, the LoRA module is used as the intermediary mechanism for injecting the extracted knowledge into smaller models. Evaluations across four benchmarks validate the efficacy of our proposed method. Our findings highlight the critical factors contributing to the process of parametric knowledge transfer, underscoring the transferability of model parameters across LLMs of different scales. Project website: https://maszhongming.github.io/ParaKnowTransfer.
Authors: Sa\'ul Alonso-Monsalve, Davide Sgalaberna, Xingyu Zhao, Adrien Molines, Clark McGrew, Andr\'e Rubbia
Abstract: Image decomposition plays a crucial role in various computer vision tasks, enabling the analysis and manipulation of visual content at a fundamental level. Overlapping images, which occur when multiple objects or scenes partially occlude each other, pose unique challenges for decomposition algorithms. The task intensifies when working with sparse images, where the scarcity of meaningful information complicates the precise extraction of components. This paper presents a solution that leverages the power of deep learning to accurately extract individual objects within multi-dimensional overlapping-sparse images, with a direct application in high-energy physics with decomposition of overlaid elementary particles obtained from imaging detectors. In particular, the proposed approach tackles a highly complex yet unsolved problem: identifying and measuring independent particles at the vertex of neutrino interactions, where one expects to observe detector images with multiple indiscernible overlapping charged particles. By decomposing the image of the detector activity at the vertex through deep learning, it is possible to infer the kinematic parameters of the identified low-momentum particles - which otherwise would remain neglected - and enhance the reconstructed energy resolution of the neutrino event. We also present an additional step - that can be tuned directly on detector data - combining the above method with a fully-differentiable generative model to improve the image decomposition further and, consequently, the resolution of the measured parameters, achieving unprecedented results. This improvement is crucial for precisely measuring the parameters that govern neutrino flavour oscillations and searching for asymmetries between matter and antimatter.
Authors: Shijie Pan, Wenjie Huang
Abstract: A novel Follow-the-Perturbed-Leader type algorithm is proposed and analyzed for solving general long-term constrained optimization problems in online manner, where the objective and constraints are arbitrarily generated and not necessarily convex. In each period, random linear perturbation and strongly concave perturbation are incorporated in primal and dual directions, respectively, to the offline oracle, and a global minimax point is searched as the solution. Based on a proposed expected static cumulative regret, we derive the first sublinear $O(T^{8/9})$ regret complexity for this class of problems. The proposed algorithm is applied to tackle a long-term (extreme value) constrained river pollutant source identification problem, validate the theoretical results and exhibit superior performance compared to existing methods.
Authors: Dian Xu, Shanshan Wang, Feng Gao, Wei Li, Jianmin Shen
Abstract: Machine learning has recently achieved remarkable success in studying phase transitions. It is generally believed that the latent variables of unsupervised learning can capture the information related to phase transitions, which is usually achieved through the so-called order parameter. In most models, for instance the Ising, the order parameters are simply the particle number densities. The percolation, the simplest model which can generate a phase transition, however, has a unique order parameter which is not particle number density. In this paper, we use unsupervised learning to study the relationship between particle number density, critical point, and latent variables in the site percolation model. It is found that if the input of learning is the original configuration, then the output of unsupervised learning does not convey any information related to the phase transition. Therefore, the maximum cluster is employed in order to effectively capture the critical point of the model. Unsupervised learning yields reliable results consistent with Monte Carlo simulations. We also propose a method called Fake Finite Size Scaling (FFSS) to calculate the critical value, which improves the accuracy of fitting to a great extent.
Authors: Afsara Benazir (University of Virginia), Zhiming Xu (University of Virginia), Felix Xiaozhu Lin (University of Virginia)
Abstract: This paper addresses spoken language understanding (SLU) on microcontroller-like embedded devices, integrating on-device execution with cloud offloading in a novel fashion. We leverage temporal locality in the speech inputs to a device and reuse recent SLU inferences accordingly. Our idea is simple: let the device match incoming inputs against cached results, and only offload inputs not matched to any cached ones to the cloud for full inference. Realization of this idea, however, is non-trivial: the device needs to compare acoustic features in a robust yet low-cost way. To this end, we present SpeechCache (or SC), a speech cache for tiny devices. It matches speech inputs at two levels of representations: first by sequences of clustered raw sound units, then as sequences of phonemes. Working in tandem, the two representations offer complementary tradeoffs between cost and efficiency. To boost accuracy even further, our cache learns to personalize: with the mismatched and then offloaded inputs, it continuously finetunes the device's feature extractors with the assistance of the cloud. We implement SC on an off-the-shelf STM32 microcontroller. The complete implementation has a small memory footprint of 2MB. Evaluated on challenging speech benchmarks, our system resolves 45%-90% of inputs on device, reducing the average latency by up to 80% compared to offloading to popular cloud speech recognition services. The benefit brought by our proposed SC is notable even in adversarial settings - noisy environments, cold cache, or one device shared by a number of users.
Authors: Mu Yuan, Lan Zhang, Xiang-Yang Li
Abstract: Security of model parameters and user data is critical for Transformer-based services, such as ChatGPT. While recent strides in secure two-party protocols have successfully addressed security concerns in serving Transformer models, their adoption is practically infeasible due to the prohibitive cryptographic overheads involved. Drawing insights from our hands-on experience in developing two real-world Transformer-based services, we identify the inherent efficiency bottleneck in the two-party assumption. To overcome this limitation, we propose a novel three-party threat model. Within this framework, we design a semi-symmetric permutation-based protection scheme and present STIP, the first secure Transformer inference protocol without any inference accuracy loss. Experiments on representative Transformer models in real systems show that STIP has practical security and outperforms state-of-the-art secure two-party protocols in efficiency by millions of times.
Authors: Mehmet Can Yavuz, Berrin Yanikoglu
Abstract: Learning a discriminative semantic space using unlabelled and noisy data remains unaddressed in a multi-label setting. We present a contrastive self-supervised learning method which is robust to data noise, grounded in the domain of variational methods. The method (VCL) utilizes variational contrastive learning with beta-divergence to learn robustly from unlabelled datasets, including uncurated and noisy datasets. We demonstrate the effectiveness of the proposed method through rigorous experiments including linear evaluation and fine-tuning scenarios with multi-label datasets in the face understanding domain. In almost all tested scenarios, VCL surpasses the performance of state-of-the-art self-supervised methods, achieving a noteworthy increase in accuracy.
Authors: Haonan Shi, Tu Ouyang, An Wang
Abstract: Machine learning models, in particular deep neural networks, are currently an integral part of various applications, from healthcare to finance. However, using sensitive data to train these models raises concerns about privacy and security. One method that has emerged to verify if the trained models are privacy-preserving is Membership Inference Attacks (MIA), which allows adversaries to determine whether a specific data point was part of a model's training dataset. While a series of MIAs have been proposed in the literature, only a few can achieve high True Positive Rates (TPR) in the low False Positive Rate (FPR) region (0.01%~1%). This is a crucial factor to consider for an MIA to be practically useful in real-world settings. In this paper, we present a novel approach to MIA that is aimed at significantly improving TPR at low FPRs. Our method, named learning-based difficulty calibration for MIA(LDC-MIA), characterizes data records by their hardness levels using a neural network classifier to determine membership. The experiment results show that LDC-MIA can improve TPR at low FPR by up to 4x compared to the other difficulty calibration based MIAs. It also has the highest Area Under ROC curve (AUC) across all datasets. Our method's cost is comparable with most of the existing MIAs, but is orders of magnitude more efficient than one of the state-of-the-art methods, LiRA, while achieving similar performance.
Authors: Rafael Rivera Soto, Kailin Koch, Aleem Khan, Barry Chen, Marcus Bishop, Nicholas Andrews
Abstract: The advent of instruction-tuned language models that convincingly mimic human writing poses a significant risk of abuse. However, such abuse may be counteracted with the ability to detect whether a piece of text was composed by a language model rather than a human author. Some previous approaches to this problem have relied on supervised methods by training on corpora of confirmed human- and machine- written documents. Unfortunately, model under-specification poses an unavoidable challenge for neural network-based detectors, making them brittle in the face of data shifts, such as the release of newer language models producing still more fluent text than the models used to train the detectors. Other approaches require access to the models that may have generated a document in question, which is often impractical. In light of these challenges, we pursue a fundamentally different approach not relying on samples from language models of concern at training time. Instead, we propose to leverage representations of writing style estimated from human-authored text. Indeed, we find that features effective at distinguishing among human authors are also effective at distinguishing human from machine authors, including state-of-the-art large language models like Llama-2, ChatGPT, and GPT-4. Furthermore, given a handful of examples composed by each of several specific language models of interest, our approach affords the ability to predict which model generated a given document. The code and data to reproduce our experiments are available at https://github.com/LLNL/LUAR/tree/main/fewshot_iclr2024.
URLs: https://github.com/LLNL/LUAR/tree/main/fewshot_iclr2024.
Authors: Sofiene Lassoued, Andreas Schwung
Abstract: Resource utilization and production process optimization are crucial for companies in today's competitive industrial landscape. Addressing the complexities of job shop scheduling problems (JSSP) is essential to improving productivity, reducing costs, and ensuring timely delivery. We propose PetriRL, a novel framework integrating Petri nets and deep reinforcement learning (DRL) for JSSP optimization. PetriRL capitalizes on the inherent strengths of Petri nets in modelling discrete event systems while leveraging the advantages of a graph structure. The Petri net governs automated components of the process, ensuring adherence to JSSP constraints. This allows for synergistic collaboration with optimization algorithms such as DRL, particularly in critical decision-making. Unlike traditional methods, PetriRL eliminates the need to preprocess JSSP instances into disjunctive graphs and enhances the explainability of process status through its graphical structure based on places and transitions. Additionally, the inherent graph structure of Petri nets enables the dynamic additions of job operations during the inference phase without requiring agent retraining, thus enhancing flexibility. Experimental results demonstrate PetriRL's robust generalization across various instance sizes and its competitive performance on public test benchmarks and randomly generated instances. Results are compared to a wide range of optimization solutions such as heuristics, metaheuristics, and learning-based algorithms. Finally, the added values of the framework's key elements, such as event-based control and action masking, are studied in the ablation study.
Authors: Paolo Sortino, Salvatore Contino, Ugo Perricone, Roberto Pirrone
Abstract: Background: Graph Neural Networks (GNN) have emerged in very recent years as a powerful tool for supporting in silico Virtual Screening. In this work we present a GNN which uses Graph Convolutional architectures to achieve very accurate multi-target screening. We also devised a hierarchical Explainable Artificial Intelligence (XAI) technique to catch information directly at atom, ring, and whole molecule level by leveraging the message passing mechanism. In this way, we find the most relevant moieties involved in bioactivity prediction. Results: We report a state-of-the-art GNN classifier on twenty Cyclin-dependent Kinase targets in support of VS. Our classifier outperforms previous SOTA approaches proposed by the authors. Moreover, a CDK1-only high-sensitivity version of the GNN has been designed to use our explainer in order to avoid the inherent bias of multi-class models. The hierarchical explainer has been validated by an expert chemist on 19 approved drugs on CDK1. Our explainer provided information in accordance to the docking analysis for 17 out of the 19 test drugs. Conclusion: Our approach is a valid support for shortening both the screening and the hit-to-lead phase. Detailed knowledge about the molecular substructures that play a role in the inhibitory action, can help the computational chemist to gain insights into the pharmacophoric function of the molecule also for repurposing purposes. Scientific Contribution Statement: The core scientific innovation of our work is the use of a hierarchical XAI approach on a GNN trained for a ligand-based VS task. The application of the hierarchical explainer allows for eliciting also structural information...
Authors: Hyoungseob Park, Anjali Gupta, Alex Wong
Abstract: It is common to observe performance degradation when transferring models trained on some (source) datasets to target testing data due to a domain gap between them. Existing methods for bridging this gap, such as domain adaptation (DA), may require the source data on which the model was trained (often not available), while others, i.e., source-free DA, require many passes through the testing data. We propose an online test-time adaptation method for depth completion, the task of inferring a dense depth map from a single image and associated sparse depth map, that closes the performance gap in a single pass. We first present a study on how the domain shift in each data modality affects model performance. Based on our observations that the sparse depth modality exhibits a much smaller covariate shift than the image, we design an embedding module trained in the source domain that preserves a mapping from features encoding only sparse depth to those encoding image and sparse depth. During test time, sparse depth features are projected using this map as a proxy for source domain features and are used as guidance to train a set of auxiliary parameters (i.e., adaptation layer) to align image and sparse depth features from the target test domain to that of the source domain. We evaluate our method on indoor and outdoor scenarios and show that it improves over baselines by an average of 21.1%.
Authors: Ethan Smith, Nayan Saxena, Aninda Saha
Abstract: Attention mechanism has been crucial for image diffusion models, however, their quadratic computational complexity limits the sizes of images we can process within reasonable time and memory constraints. This paper investigates the importance of dense attention in generative image models, which often contain redundant features, making them suitable for sparser attention mechanisms. We propose a novel training-free method ToDo that relies on token downsampling of key and value tokens to accelerate Stable Diffusion inference by up to 2x for common sizes and up to 4.5x or more for high resolutions like 2048x2048. We demonstrate that our approach outperforms previous methods in balancing efficient throughput and fidelity.
Authors: Ayushi Nirmal, Amrita Bhattacharjee, Paras Sheth, Huan Liu
Abstract: Although social media platforms are a prominent arena for users to engage in interpersonal discussions and express opinions, the facade and anonymity offered by social media may allow users to spew hate speech and offensive content. Given the massive scale of such platforms, there arises a need to automatically identify and flag instances of hate speech. Although several hate speech detection methods exist, most of these black-box methods are not interpretable or explainable by design. To address the lack of interpretability, in this paper, we propose to use state-of-the-art Large Language Models (LLMs) to extract features in the form of rationales from the input text, to train a base hate speech classifier, thereby enabling faithful interpretability by design. Our framework effectively combines the textual understanding capabilities of LLMs and the discriminative power of state-of-the-art hate speech classifiers to make these classifiers faithfully interpretable. Our comprehensive evaluation on a variety of English language social media hate speech datasets demonstrate: (1) the goodness of the LLM-extracted rationales, and (2) the surprising retention of detector performance even after training to ensure interpretability. All code and data will be made available at https://github.com/AmritaBh/shield.
Authors: Blake Gella, Howard Zhang, Rishi Upadhyay, Tiffany Chang, Nathan Wei, Matthew Waliman, Yunhao Ba, Celso de Melo, Alex Wong, Achuta Kadambi
Abstract: We propose a method to infer semantic segmentation maps from images captured under adverse weather conditions. We begin by examining existing models on images degraded by weather conditions such as rain, fog, or snow, and found that they exhibit a large performance drop as compared to those captured under clear weather. To control for changes in scene structures, we propose WeatherProof, the first semantic segmentation dataset with accurate clear and adverse weather image pairs that share an underlying scene. Through this dataset, we analyze the error modes in existing models and found that they were sensitive to the highly complex combination of different weather effects induced on the image during capture. To improve robustness, we propose a way to use language as guidance by identifying contributions of adverse weather conditions and injecting that as "side information". Models trained using our language guidance exhibit performance gains by up to 10.2% in mIoU on WeatherProof, up to 8.44% in mIoU on the widely used ACDC dataset compared to standard training techniques, and up to 6.21% in mIoU on the ACDC dataset as compared to previous SOTA methods.
Authors: Ahmad Idrissi-Yaghir, Amin Dada, Henning Sch\"afer, Kamyar Arzideh, Giulia Baldini, Jan Trienes, Max Hasin, Jeanette Bewersdorff, Cynthia S. Schmidt, Marie Bauer, Kaleb E. Smith, Jiang Bian, Yonghui Wu, J\"org Schl\"otterer, Torsten Zesch, Peter A. Horn, Christin Seifert, Felix Nensa, Jens Kleesiek, Christoph M. Friedrich
Abstract: Recent advances in natural language processing (NLP) can be largely attributed to the advent of pre-trained language models such as BERT and RoBERTa. While these models demonstrate remarkable performance on general datasets, they can struggle in specialized domains such as medicine, where unique domain-specific terminologies, domain-specific abbreviations, and varying document structures are common. This paper explores strategies for adapting these models to domain-specific requirements, primarily through continuous pre-training on domain-specific data. We pre-trained several German medical language models on 2.4B tokens derived from translated public English medical data and 3B tokens of German clinical data. The resulting models were evaluated on various German downstream tasks, including named entity recognition (NER), multi-label classification, and extractive question answering. Our results suggest that models augmented by clinical and translation-based pre-training typically outperform general domain models in medical contexts. We conclude that continuous pre-training has demonstrated the ability to match or even exceed the performance of clinical models trained from scratch. Furthermore, pre-training on clinical data or leveraging translated texts have proven to be reliable methods for domain adaptation in medical NLP tasks.
Authors: Tianyu Cao, Natraj Raman, Danial Dervovic, Chenhao Tan
Abstract: As large language models (LLMs) expand the power of natural language processing to handle long inputs, rigorous and systematic analyses are necessary to understand their abilities and behavior. A salient application is summarization, due to its ubiquity and controversy (e.g., researchers have declared the death of summarization). In this paper, we use financial report summarization as a case study because financial reports not only are long but also use numbers and tables extensively. We propose a computational framework for characterizing multimodal long-form summarization and investigate the behavior of Claude 2.0/2.1, GPT-4/3.5, and Command. We find that GPT-3.5 and Command fail to perform this summarization task meaningfully. For Claude 2 and GPT-4, we analyze the extractiveness of the summary and identify a position bias in LLMs. This position bias disappears after shuffling the input for Claude, which suggests that Claude has the ability to recognize important information. We also conduct a comprehensive investigation on the use of numeric data in LLM-generated summaries and offer a taxonomy of numeric hallucination. We employ prompt engineering to improve GPT-4's use of numbers with limited success. Overall, our analyses highlight the strong capability of Claude 2 in handling long multimodal inputs compared to GPT-4.
Authors: Sebastian Doerrich, Francesco Di Salvo, Julius Brockmann, Christian Ledig
Abstract: The integration of deep learning based systems in clinical practice is often impeded by challenges rooted in limited and heterogeneous medical datasets. In addition, prioritization of marginal performance improvements on a few, narrowly scoped benchmarks over clinical applicability has slowed down meaningful algorithmic progress. This trend often results in excessive fine-tuning of existing methods to achieve state-of-the-art performance on selected datasets rather than fostering clinically relevant innovations. In response, this work presents a comprehensive benchmark for the MedMNIST+ database to diversify the evaluation landscape and conduct a thorough analysis of common convolutional neural networks (CNNs) and Transformer-based architectures, for medical image classification. Our evaluation encompasses various medical datasets, training methodologies, and input resolutions, aiming to reassess the strengths and limitations of widely used model variants. Our findings suggest that computationally efficient training schemes and modern foundation models hold promise in bridging the gap between expensive end-to-end training and more resource-refined approaches. Additionally, contrary to prevailing assumptions, we observe that higher resolutions may not consistently improve performance beyond a certain threshold, advocating for the use of lower resolutions, particularly in prototyping stages, to expedite processing. Notably, our analysis reaffirms the competitiveness of convolutional models compared to ViT-based architectures emphasizing the importance of comprehending the intrinsic capabilities of different model architectures. Moreover, we hope that our standardized evaluation framework will help enhance transparency, reproducibility, and comparability on the MedMNIST+ dataset collection as well as future research within the field. Code is available at https://github.com/sdoerrich97 .
Authors: Simona Bernardi, Tommaso Zoppi
Abstract: The goal of the Fast Abstracts track is to bring together researchers and practitioners working on dependable computing to discuss work in progress or opinion pieces. Contributions are welcome from academia and industry. Fast Abstracts aim to serve as a rapid and flexible mechanism to: (i) Report on current work that may or may not be complete; (ii) Introduce new ideas to the community; (iii) State positions on controversial issues or open problems; (iv) Share lessons learnt from real-word dependability engineering; and (v) Debunk or question results from other papers based on contra-indications. The Student Forum aims at creating a vibrant and friendly environment where students can present and discuss their work, and exchange ideas and experiences with other students, researchers and industry. One of the key goals of the Forum is to provide students with feedback on their preliminary results that might help with their future research directions.
Authors: Jens Egholm Pedersen, J\"org Conradt, Tony Lindeberg
Abstract: Biological nervous systems constitute important sources of inspiration towards computers that are faster, cheaper, and more energy efficient. Neuromorphic disciplines view the brain as a coevolved system, simultaneously optimizing the hardware and the algorithms running on it. There are clear efficiency gains when bringing the computations into a physical substrate, but we presently lack theories to guide efficient implementations. Here, we present a principled computational model for neuromorphic systems in terms of spatio-temporal receptive fields, based on affine Gaussian kernels over space and leaky-integrator and leaky integrate-and-fire models over time. Our theory is provably covariant to spatial affine and temporal scaling transformations, and with close similarities to the visual processing in mammalian brains. We use these spatio-temporal receptive fields as a prior in an event-based vision task, and show that this improves the training of spiking networks, which otherwise is known as problematic for event-based vision. This work combines efforts within scale-space theory and computational neuroscience to identify theoretically well-founded ways to process spatio-temporal signals in neuromorphic systems. Our contributions are immediately relevant for signal processing and event-based vision, and can be extended to other processing tasks over space and time, such as memory and control.
Authors: Hiroki Waida, Kimihiro Yamazaki, Atsushi Tokuhisa, Mutsuyo Wada, Yuichiro Wada
Abstract: Self-supervised learning for image denoising problems in the presence of denaturation for noisy data is a crucial approach in machine learning. However, theoretical understanding of the performance of the approach that uses denatured data is lacking. To provide better understanding of the approach, in this paper, we analyze a self-supervised denoising algorithm that uses denatured data in depth through theoretical analysis and numerical experiments. Through the theoretical analysis, we discuss that the algorithm finds desired solutions to the optimization problem with the population risk, while the guarantee for the empirical risk depends on the hardness of the denoising task in terms of denaturation levels. We also conduct several experiments to investigate the performance of an extended algorithm in practice. The results indicate that the algorithm training with denatured images works, and the empirical performance aligns with the theoretical results. These results suggest several insights for further improvement of self-supervised image denoising that uses denatured data in future directions.
Authors: Ziquan Deng, Xiwei Xuan, Kwan-Liu Ma, Zhaodan Kong
Abstract: Time series anomaly detection is a critical machine learning task for numerous applications, such as finance, healthcare, and industrial systems. However, even high-performed models may exhibit potential issues such as biases, leading to unreliable outcomes and misplaced confidence. While model explanation techniques, particularly visual explanations, offer valuable insights to detect such issues by elucidating model attributions of their decision, many limitations still exist -- They are primarily instance-based and not scalable across dataset, and they provide one-directional information from the model to the human side, lacking a mechanism for users to address detected issues. To fulfill these gaps, we introduce HILAD, a novel framework designed to foster a dynamic and bidirectional collaboration between humans and AI for enhancing anomaly detection models in time series. Through our visual interface, HILAD empowers domain experts to detect, interpret, and correct unexpected model behaviors at scale. Our evaluation with two time series datasets and user studies demonstrates the effectiveness of HILAD in fostering a deeper human understanding, immediate corrective actions, and the reliability enhancement of models.
Authors: Kyle Doherty, Max Gurinas, Erik Samsoe, Charles Casper, Beau Larkin, Philip Ramsey, Brandon Trabucco, Ruslan Salakhutdinov
Abstract: Invasive plant species are detrimental to the ecology of both agricultural and wildland areas. Euphorbia esula, or leafy spurge, is one such plant that has spread through much of North America from Eastern Europe. When paired with contemporary computer vision systems, unmanned aerial vehicles, or drones, offer the means to track expansion of problem plants, such as leafy spurge, and improve chances of controlling these weeds. We gathered a dataset of leafy spurge presence and absence in grasslands of western Montana, USA, then surveyed these areas with a commercial drone. We trained image classifiers on these data, and our best performing model, a pre-trained DINOv2 vision transformer, identified leafy spurge with 0.84 accuracy (test set). This result indicates that classification of leafy spurge is tractable, but not solved. We release this unique dataset of labelled and unlabelled, aerial drone imagery for the machine learning community to explore. Improving classification performance of leafy spurge would benefit the fields of ecology, conservation, and remote sensing alike. Code and data are available at our website: leafy-spurge-dataset.github.io.