Authors: Haotian Chen, Anna Kuzina, Babak Esmaeili, Jakub M Tomczak
Abstract: Optimizing deep neural networks is one of the main tasks in successful deep learning. Current state-of-the-art optimizers are adaptive gradient-based optimization methods such as Adam. Recently, there has been an increasing interest in formulating gradient-based optimizers in a probabilistic framework for better estimation of gradients and modeling uncertainties. Here, we propose to combine both approaches, resulting in the Variational Stochastic Gradient Descent (VSGD) optimizer. We model gradient updates as a probabilistic model and utilize stochastic variational inference (SVI) to derive an efficient and effective update rule. Further, we show how our VSGD method relates to other adaptive gradient-based optimizers like Adam. Lastly, we carry out experiments on two image classification datasets and four deep neural network architectures, where we show that VSGD outperforms Adam and SGD.
Authors: Thomas Cass, Cristopher Salvi
Abstract: These notes expound the recent use of the signature transform and rough path theory in data science and machine learning. We develop the core theory of the signature from first principles and then survey some recent popular applications of this approach, including signature-based kernel methods and neural rough differential equations. The notes are based on a course given by the two authors at Imperial College London.
Authors: Omar Ghannou, Youn\`es Bennani
Abstract: Multi-source Domain Adaptation (MDA) aims to adapt models trained on multiple labeled source domains to an unlabeled target domain. In this paper, we introduce our approach as a collaborative MDA framework, which comprises two adaptation phases. Firstly, we conduct domain adaptation for each source individually with the target, utilizing optimal transport. Then, in the second phase, which constitutes the final part of the framework, we design the architecture of centralized federated learning to collaborate the N models representing the N sources. This architecture offers the advantage of using the sources without accessing their data, thus resolving data privacy issues inherent in domain adaptation. Additionally, during this phase, the server guides and fine-tunes the adaptation using a small number of pseudo-labeled samples available in the target domain, referred to as the target validation subset of the dataset.
Authors: Yonggi Park, Yuanfang Ren, Benjamin Shickel, Ziyuan Guan, Ayush Patela, Yingbo Ma, Zhenhong Hu, Tyler J. Loftus, Parisa Rashidi, Tezcan Ozrazgat-Baslanti, Azra Bihorac
Abstract: Background: The accurate prediction of postoperative complication risk using Electronic Health Records (EHR) and artificial intelligence shows great potential. Training a robust artificial intelligence model typically requires large-scale and diverse datasets. In reality, collecting medical data often encounters challenges surrounding privacy protection. Methods: This retrospective cohort study includes adult patients who were admitted to UFH Gainesville (GNV) (n = 79,850) and Jacksonville (JAX) (n = 28,636) for any type of inpatient surgical procedure. Using perioperative and intraoperative features, we developed federated learning models to predict nine major postoperative complications (i.e., prolonged intensive care unit stay and mechanical ventilation). We compared federated learning models with local learning models trained on a single site and central learning models trained on pooled dataset from two centers. Results: Our federated learning models achieved the area under the receiver operating characteristics curve (AUROC) values ranged from 0.81 for wound complications to 0.92 for prolonged ICU stay at UFH GNV center. At UFH JAX center, these values ranged from 0.73-0.74 for wound complications to 0.92-0.93 for hospital mortality. Federated learning models achieved comparable AUROC performance to central learning models, except for prolonged ICU stay, where the performance of federated learning models was slightly higher than central learning models at UFH GNV center, but slightly lower at UFH JAX center. In addition, our federated learning model obtained comparable performance to the best local learning model at each center, demonstrating strong generalizability. Conclusion: Federated learning is shown to be a useful tool to train robust and generalizable models from large scale data across multiple institutions where data protection barriers are high.
Authors: Hailong Shu, Yue Wang, Weiwei Song, Huichuang Guo, Zhen Song
Abstract: The field of meteorological forecasting has undergone a significant transformation with the integration of large models, especially those employing deep learning techniques. This paper reviews the advancements and applications of these models in weather prediction, emphasizing their role in transforming traditional forecasting methods. Models like FourCastNet, Pangu-Weather, GraphCast, ClimaX, and FengWu have made notable contributions by providing accurate, high-resolution forecasts, surpassing the capabilities of traditional Numerical Weather Prediction (NWP) models. These models utilize advanced neural network architectures, such as Convolutional Neural Networks (CNNs), Graph Neural Networks (GNNs), and Transformers, to process diverse meteorological data, enhancing predictive accuracy across various time scales and spatial resolutions. The paper addresses challenges in this domain, including data acquisition and computational demands, and explores future opportunities for model optimization and hardware advancements. It underscores the integration of artificial intelligence with conventional meteorological techniques, promising improved weather prediction accuracy and a significant contribution to addressing climate-related challenges. This synergy positions large models as pivotal in the evolving landscape of meteorological forecasting.
Authors: Jae-Won Chung, Mosharaf Chowdhury
Abstract: The enormous energy consumption of machine learning (ML) and generative AI workloads shows no sign of waning, taking a toll on operating costs, power delivery, and environmental sustainability. Despite a long line of research on energy-efficient hardware, we found that software plays a critical role in ML energy optimization through two recent works: Zeus and Perseus. This is especially true for large language models (LLMs) because their model sizes and, therefore, energy demands are growing faster than hardware efficiency improvements. Therefore, we advocate for a cross-layer approach for energy optimizations in ML systems, where hardware provides architectural support that pushes energy-efficient software further, while software leverages and abstracts the hardware to develop techniques that bring hardware-agnostic energy-efficiency gains.
Authors: Tianming Cai, Guoying Zhao, Junbin Zang, Chen Zong, Zhidong Zhang, Chenyang Xue
Abstract: In recent years, the preliminary diagnosis of Attention Deficit Hyperactivity Disorder (ADHD) using electroencephalography (EEG) has garnered attention from researchers. EEG, known for its expediency and efficiency, plays a pivotal role in the diagnosis and treatment of ADHD. However, the non-stationarity of EEG signals and inter-subject variability pose challenges to the diagnostic and classification processes. Topological Data Analysis (TDA) offers a novel perspective for ADHD classification, diverging from traditional time-frequency domain features. Yet, conventional TDA models are restricted to single-channel time series and are susceptible to noise, leading to the loss of topological features in persistence diagrams.This paper presents an enhanced TDA approach applicable to multi-channel EEG in ADHD. Initially, optimal input parameters for multi-channel EEG are determined. Subsequently, each channel's EEG undergoes phase space reconstruction (PSR) followed by the utilization of k-Power Distance to Measure (k-PDTM) for approximating ideal point clouds. Then, multi-dimensional time series are re-embedded, and TDA is applied to obtain topological feature information. Gaussian function-based Multivariate Kernel Density Estimation (MKDE) is employed in the merger persistence diagram to filter out desired topological feature mappings. Finally, persistence image (PI) method is utilized to extract topological features, and the influence of various weighting functions on the results is discussed.The effectiveness of our method is evaluated using the IEEE ADHD dataset. Results demonstrate that the accuracy, sensitivity, and specificity reach 85.60%, 83.61%, and 88.33%, respectively. Compared to traditional TDA methods, our method was effectively improved and outperforms typical nonlinear descriptors. These findings indicate that our method exhibits higher precision and robustness.
Authors: Yifei Wang, Wenhan Ma, Yisen Wang
Abstract: Relying only on unlabeled data, Self-supervised learning (SSL) can learn rich features in an economical and scalable way. As the drive-horse for building foundation models, SSL has received a lot of attention recently with wide applications, which also raises security concerns where backdoor attack is a major type of threat: if the released dataset is maliciously poisoned, backdoored SSL models can behave badly when triggers are injected to test samples. The goal of this work is to investigate this potential risk. We notice that existing backdoors all require a considerable amount of \emph{labeled} data that may not be available for SSL. To circumvent this limitation, we explore a more restrictive setting called no-label backdoors, where we only have access to the unlabeled data alone, where the key challenge is how to select the proper poison set without using label information. We propose two strategies for poison selection: clustering-based selection using pseudolabels, and contrastive selection derived from the mutual information principle. Experiments on CIFAR-10 and ImageNet-100 show that both no-label backdoors are effective on many SSL methods and outperform random poisoning by a large margin. Code will be available at https://github.com/PKU-ML/nlb.
Authors: Yingbo Ma, Suraj Kolla, Zhenhong Hu, Dhruv Kaliraman, Victoria Nolan, Ziyuan Guan, Yuanfang Ren, Brooke Armfield, Tezcan Ozrazgat-Baslanti, Jeremy A. Balch, Tyler J. Loftus, Parisa Rashidi, Azra Bihorac, Benjamin Shickel
Abstract: Modern electronic health records (EHRs) hold immense promise in tracking personalized patient health trajectories through sequential deep learning, owing to their extensive breadth, scale, and temporal granularity. Nonetheless, how to effectively leverage multiple modalities from EHRs poses significant challenges, given its complex characteristics such as high dimensionality, multimodality, sparsity, varied recording frequencies, and temporal irregularities. To this end, this paper introduces a novel multimodal contrastive learning framework, specifically focusing on medical time series and clinical notes. To tackle the challenge of sparsity and irregular time intervals in medical time series, the framework integrates temporal cross-attention transformers with a dynamic embedding and tokenization scheme for learning multimodal feature representations. To harness the interconnected relationships between medical time series and clinical notes, the framework equips a global contrastive loss, aligning a patient's multimodal feature representations with the corresponding discharge summaries. Since discharge summaries uniquely pertain to individual patients and represent a holistic view of the patient's hospital stay, machine learning models are led to learn discriminative multimodal features via global contrasting. Extensive experiments with a real-world EHR dataset demonstrated that our framework outperformed state-of-the-art approaches on the exemplar task of predicting the occurrence of nine postoperative complications for more than 120,000 major inpatient surgeries using multimodal data from UF health system split among three hospitals (UF Health Gainesville, UF Health Jacksonville, and UF Health Jacksonville-North).
Authors: Yiwei Lu, Matthew Y. R. Yang, Zuoqiu Liu, Gautam Kamath, Yaoliang Yu
Abstract: Copyright infringement may occur when a generative model produces samples substantially similar to some copyrighted data that it had access to during the training phase. The notion of access usually refers to including copyrighted samples directly in the training dataset, which one may inspect to identify an infringement. We argue that such visual auditing largely overlooks a concealed copyright infringement, where one constructs a disguise that looks drastically different from the copyrighted sample yet still induces the effect of training Latent Diffusion Models on it. Such disguises only require indirect access to the copyrighted material and cannot be visually distinguished, thus easily circumventing the current auditing tools. In this paper, we provide a better understanding of such disguised copyright infringement by uncovering the disguises generation algorithm, the revelation of the disguises, and importantly, how to detect them to augment the existing toolbox. Additionally, we introduce a broader notion of acknowledgment for comprehending such indirect access.
Authors: Chuanqi Chen, Nan Chen, Jin-Long Wu
Abstract: A new knowledge-based and machine learning hybrid modeling approach, called conditional Gaussian neural stochastic differential equation (CGNSDE), is developed to facilitate modeling complex dynamical systems and implementing analytic formulae of the associated data assimilation (DA). In contrast to the standard neural network predictive models, the CGNSDE is designed to effectively tackle both forward prediction tasks and inverse state estimation problems. The CGNSDE starts by exploiting a systematic causal inference via information theory to build a simple knowledge-based nonlinear model that nevertheless captures as much explainable physics as possible. Then, neural networks are supplemented to the knowledge-based model in a specific way, which not only characterizes the remaining features that are challenging to model with simple forms but also advances the use of analytic formulae to efficiently compute the nonlinear DA solution. These analytic formulae are used as an additional computationally affordable loss to train the neural networks that directly improve the DA accuracy. This DA loss function promotes the CGNSDE to capture the interactions between state variables and thus advances its modeling skills. With the DA loss, the CGNSDE is more capable of estimating extreme events and quantifying the associated uncertainty. Furthermore, crucial physical properties in many complex systems, such as the translate-invariant local dependence of state variables, can significantly simplify the neural network structures and facilitate the CGNSDE to be applied to high-dimensional systems. Numerical experiments based on chaotic systems with intermittency and strong non-Gaussian features indicate that the CGNSDE outperforms knowledge-based regression models, and the DA loss further enhances the modeling skills of the CGNSDE.
Authors: Kaixi Hu, Lin Li, Qing Xie, Xiaohui Tao, Guandong Xu
Abstract: Granularity and accuracy are two crucial factors for crime event prediction. Within fine-grained event classification, multiple criminal intents may alternately exhibit in preceding sequential events, and progress differently in next. Such intensive intent dynamics makes training models hard to capture unobserved intents, and thus leads to sub-optimal generalization performance, especially in the intertwining of numerous potential events. To capture comprehensive criminal intents, this paper proposes a fine-grained sequential crime prediction framework, CrimeAlarm, that equips with a novel mutual distillation strategy inspired by curriculum learning. During the early training phase, spot-shared criminal intents are captured through high-confidence sequence samples. In the later phase, spot-specific intents are gradually learned by increasing the contribution of low-confidence sequences. Meanwhile, the output probability distributions are reciprocally learned between prediction networks to model unobserved criminal intents. Extensive experiments show that CrimeAlarm outperforms state-of-the-art methods in terms of NDCG@5, with improvements of 4.51% for the NYC16 and 7.73% for the CHI18 in accuracy measures.
Authors: Yu Qiao, Chaoning Zhang, Apurba Adhikary, Choong Seon Hong
Abstract: Federated learning (FL) is a privacy-preserving distributed framework for collaborative model training on devices in edge networks. However, challenges arise due to vulnerability to adversarial examples (AEs) and the non-independent and identically distributed (non-IID) nature of data distribution among devices, hindering the deployment of adversarially robust and accurate learning models at the edge. While adversarial training (AT) is commonly acknowledged as an effective defense strategy against adversarial attacks in centralized training, we shed light on the adverse effects of directly applying AT in FL that can severely compromise accuracy, especially in non-IID challenges. Given this limitation, this paper proposes FatCC, which incorporates local logit \underline{C}alibration and global feature \underline{C}ontrast into the vanilla federated adversarial training (\underline{FAT}) process from both logit and feature perspectives. This approach can effectively enhance the federated system's robust accuracy (RA) and clean accuracy (CA). First, we propose logit calibration, where the logits are calibrated during local adversarial updates, thereby improving adversarial robustness. Second, FatCC introduces feature contrast, which involves a global alignment term that aligns each local representation with unbiased global features, thus further enhancing robustness and accuracy in federated adversarial environments. Extensive experiments across multiple datasets demonstrate that FatCC achieves comparable or superior performance gains in both CA and RA compared to other baselines.
Authors: Wenqian Li, Haozhi Wang, Zhe Huang, Yan Pang
Abstract: Wasserstein distance is a principle measure of data divergence from a distributional standpoint. However, its application becomes challenging in the context of data privacy, where sharing raw data is restricted. Prior attempts have employed techniques like Differential Privacy or Federated optimization to approximate Wasserstein distance. Nevertheless, these approaches often lack accuracy and robustness against potential attack. In this study, we investigate the underlying triangular properties within the Wasserstein space, leading to a straightforward solution named TriangleWad. This approach enables the computation of Wasserstein distance between datasets stored across different entities. Notably, TriangleWad is 20 times faster, making raw data information truly invisible, enhancing resilience against attacks, and without sacrificing estimation accuracy. Through comprehensive experimentation across various tasks involving both image and text data, we demonstrate its superior performance and generalizations.
Authors: Zhuo Li, He Zhao, Zhen Li, Tongliang Liu, Dandan Guo, Xiang Wan
Abstract: Real-world datasets usually are class-imbalanced and corrupted by label noise. To solve the joint issue of long-tailed distribution and label noise, most previous works usually aim to design a noise detector to distinguish the noisy and clean samples. Despite their effectiveness, they may be limited in handling the joint issue effectively in a unified way. In this work, we develop a novel pseudo labeling method using class prototypes from the perspective of distribution matching, which can be solved with optimal transport (OT). By setting a manually-specific probability measure and using a learned transport plan to pseudo-label the training samples, the proposed method can reduce the side-effects of noisy and long-tailed data simultaneously. Then we introduce a simple yet effective filter criteria by combining the observed labels and pseudo labels to obtain a more balanced and less noisy subset for a robust model training. Extensive experiments demonstrate that our method can extract this class-balanced subset with clean labels, which brings effective performance gains for long-tailed classification with label noise.
Authors: Taeuk Jeong, Yoon Mo Jung
Abstract: Dimensionality reduction represents the process of generating a low dimensional representation of high dimensional data. Motivated by the formation control of mobile agents, we propose a nonlinear dynamical system for dimensionality reduction. The system consists of two parts; the control of neighbor points, addressing local structures, and the control of remote points, accounting for global structures. We also include a brief mathematical observation of the model and its numerical procedure. Numerical experiments are performed on both synthetic and real datasets and comparisons with existing models demonstrate the soundness and effectiveness of the proposed model.
Authors: Phuong Bich Duong, Ben Van Herbruggen, Arne Broering, Adnan Shahid, Eli De Poorter
Abstract: Indoor positioning systems based on Ultra-wideband (UWB) technology are gaining recognition for their ability to provide cm-level localization accuracy. However, these systems often encounter challenges caused by dense multi-path fading, leading to positioning errors. To address this issue, in this letter, we propose a novel methodology for unsupervised anchor node selection using deep embedded clustering (DEC). Our approach uses an Auto Encoder (AE) before clustering, thereby better separating UWB features into separable clusters of UWB input signals. We furthermore investigate how to rank these clusters based on their cluster quality, allowing us to remove untrustworthy signals. Experimental results show the efficiency of our proposed method, demonstrating a significant 23.1% reduction in mean absolute error (MAE) compared to without anchor exclusion. Especially in the dense multi-path area, our algorithm achieves even more significant enhancements, reducing the MAE by 26.6% and the 95th percentile error by 49.3% compared to without anchor exclusion.
Authors: Ayush Sawarni, Nirjhar Das, Gaurav Sinha, Siddharth Barman
Abstract: We study the generalized linear contextual bandit problem within the requirements of limited adaptivity. In this paper, we present two algorithms, \texttt{B-GLinCB} and \texttt{RS-GLinCB}, that address, respectively, two prevalent limited adaptivity models: batch learning with stochastic contexts and rare policy switches with adversarial contexts. For both these models, we establish essentially tight regret bounds. Notably, in the obtained bounds, we manage to eliminate a dependence on a key parameter $\kappa$, which captures the non-linearity of the underlying reward model. For our batch learning algorithm \texttt{B-GLinCB}, with $\Omega\left( \log{\log T} \right)$ batches, the regret scales as $\tilde{O}(\sqrt{T})$. Further, we establish that our rarely switching algorithm \texttt{RS-GLinCB} updates its policy at most $\tilde{O}(\log^2 T)$ times and achieves a regret of $\tilde{O}(\sqrt{T})$. Our approach for removing the dependence on $\kappa$ for generalized linear contextual bandits might be of independent interest.
Authors: Daniel Biebert, Christian Hakert, Kuan-Hsun Chen, Jian-Jia Chen
Abstract: Bringing high-level machine learning models to efficient and well-suited machine implementations often invokes a bunch of tools, e.g.~code generators, compilers, and optimizers. Along such tool chains, abstractions have to be applied. This leads to not optimally used CPU registers. This is a shortcoming, especially in resource constrained embedded setups. In this work, we present a code generation approach for decision tree ensembles, which produces machine assembly code within a single conversion step directly from the high-level model representation. Specifically, we develop various approaches to effectively allocate registers for the inference of decision tree ensembles. Extensive evaluations of the proposed method are conducted in comparison to the basic realization of C code from the high-level machine learning model and succeeding compilation. The results show that the performance of decision tree ensemble inference can be significantly improved (by up to $\approx1.6\times$), if the methods are applied carefully to the appropriate scenario.
Authors: Shirel Attia, Revital Shani Hershkovich, Alissa Tabakhov, Angeleene Ang, Sharon Haimov, Riva Tauman, Joachim A. Behar
Abstract: Background: Sleep staging is a fundamental component in the diagnosis of sleep disorders and the management of sleep health. Traditionally, this analysis is conducted in clinical settings and involves a time-consuming scoring procedure. Recent data-driven algorithms for sleep staging, using the photoplethysmogram (PPG) time series, have shown high performance on local test sets but lower performance on external datasets due to data drift. Methods: This study aimed to develop a generalizable deep learning model for the task of four class (wake, light, deep, and rapid eye movement (REM)) sleep staging from raw PPG physiological time-series. Six sleep datasets, totaling 2,574 patients recordings, were used. In order to create a more generalizable representation, we developed and evaluated a deep learning model called SleepPPG-Net2, which employs a multi-source domain training approach.SleepPPG-Net2 was benchmarked against two state-of-the-art models. Results: SleepPPG-Net2 showed consistently higher performance over benchmark approaches, with generalization performance (Cohen's kappa) improving by up to 19%. Performance disparities were observed in relation to age, sex, and sleep apnea severity. Conclusion: SleepPPG-Net2 sets a new standard for staging sleep from raw PPG time-series.
Authors: Hongru Du (Frank), Jianan Zhao (Frank), Yang Zhao (Frank), Shaochong Xu (Frank), Xihong Lin (Frank), Yiran Chen (Frank), Lauren M. Gardner (Frank), Hao (Frank), Yang
Abstract: Forecasting the short-term spread of an ongoing disease outbreak is a formidable challenge due to the complexity of contributing factors, some of which can be characterized through interlinked, multi-modality variables such as epidemiological time series data, viral biology, population demographics, and the intersection of public policy and human behavior. Existing forecasting model frameworks struggle with the multifaceted nature of relevant data and robust results translation, which hinders their performances and the provision of actionable insights for public health decision-makers. Our work introduces PandemicLLM, a novel framework with multi-modal Large Language Models (LLMs) that reformulates real-time forecasting of disease spread as a text reasoning problem, with the ability to incorporate real-time, complex, non-numerical information that previously unattainable in traditional forecasting models. This approach, through a unique AI-human cooperative prompt design and time series representation learning, encodes multi-modal data for LLMs. The model is applied to the COVID-19 pandemic, and trained to utilize textual public health policies, genomic surveillance, spatial, and epidemiological time series data, and is subsequently tested across all 50 states of the U.S. Empirically, PandemicLLM is shown to be a high-performing pandemic forecasting framework that effectively captures the impact of emerging variants and can provide timely and accurate predictions. The proposed PandemicLLM opens avenues for incorporating various pandemic-related data in heterogeneous formats and exhibits performance benefits over existing models. This study illuminates the potential of adapting LLMs and representation learning to enhance pandemic forecasting, illustrating how AI innovations can strengthen pandemic responses and crisis management in the future.
Authors: Johannes Burchert, Thorben Werner, Vijaya Krishna Yalavarthi, Diego Coello de Portugal, Maximilian Stubbemann, Lars Schmidt-Thieme
Abstract: As with most other data domains, EEG data analysis relies on rich domain-specific preprocessing. Beyond such preprocessing, machine learners would hope to deal with such data as with any other time series data. For EEG classification many models have been developed with layer types and architectures we typically do not see in time series classification. Furthermore, typically separate models for each individual subject are learned, not one model for all of them. In this paper, we systematically study the differences between EEG classification models and generic time series classification models. We describe three different model setups to deal with EEG data from different subjects, subject-specific models (most EEG literature), subject-agnostic models and subject-conditional models. In experiments on three datasets, we demonstrate that off-the-shelf time series classification models trained per subject perform close to EEG classification models, but that do not quite reach the performance of domain-specific modeling. Additionally, we combine time-series models with subject embeddings to train one joint subject-conditional classifier on all subjects. The resulting models are competitive with dedicated EEG models in 2 out of 3 datasets, even outperforming all EEG methods on one of them.
Authors: Meyer Scetbon, Joel Jennings, Agrin Hilmkil, Cheng Zhang, Chao Ma
Abstract: Modeling true world data-generating processes lies at the heart of empirical science. Structural Causal Models (SCMs) and their associated Directed Acyclic Graphs (DAGs) provide an increasingly popular answer to such problems by defining the causal generative process that transforms random noise into observations. However, learning them from observational data poses an ill-posed and NP-hard inverse problem in general. In this work, we propose a new and equivalent formalism that do not require DAGs to describe them, viewed as fixed-point problems on the causally ordered variables, and show three important cases where they can be uniquely recovered given the topological ordering (TO). To the best of our knowledge, we obtain the most general recovery results when the TO is known. Based on our theoretical findings, we design a two-stage causal generative model that first infers the causal order from observations in a zero-shot manner, thus by-passing the search, and then learns the generative fixed-point SCM on the ordered variables. To infer TOs from observations, we propose to amortize the learning of TOs on generated datasets by sequentially predicting the leaves of graphs seen during training. To learn fixed-point SCMs, we design a transformer-based architecture that exploits a new attention mechanism enabling the modeling of causal structures, and show that this parameterization is consistent with our formalism. Finally, we conduct an extensive evaluation of each method individually, and show that when combined, our model outperforms various baselines on generated out-of-distribution problems.
Authors: Konat\'e Mohamed Abbas, Anne-Fran\c{c}oise Yao, Thierry Chateau, Pierre Bouges
Abstract: In this paper, we investigate continual learning performance metrics used in class incremental learning strategies for continual learning (CL) using some high performing methods. We investigate especially mean task accuracy. First, we show that it lacks of expressiveness through some simple experiments to capture performance. We show that monitoring average tasks performance is over optimistic and can lead to misleading conclusions for future real life industrial uses. Then, we propose first a simple metric, Minimal Incremental Class Accuracy (MICA) which gives a fair and more useful evaluation of different continual learning methods. Moreover, in order to provide a simple way to easily compare different methods performance in continual learning, we derive another single scalar metric that take into account the learning performance variation as well as our newly introduced metric.
Authors: Ryan S. Baker, Nigel Bosch, Stephen Hutt, Andres F. Zambrano, Alex J. Bowers
Abstract: Recently, ACM FAccT published an article by Kwegyir-Aggrey and colleagues (2023), critiquing the use of AUC ROC in predictive analytics in several domains. In this article, we offer a critique of that article. Specifically, we highlight technical inaccuracies in that paper's comparison of metrics, mis-specification of the interpretation and goals of AUC ROC, the article's use of the accuracy metric as a gold standard for comparison to AUC ROC, and the article's application of critiques solely to AUC ROC for concerns that would apply to the use of any metric. We conclude with a re-framing of the very valid concerns raised in that article, and discuss how the use of AUC ROC can remain a valid and appropriate practice in a well-informed predictive analytics approach taking those concerns into account. We conclude by discussing the combined use of multiple metrics, including machine learning bias metrics, and AUC ROC's place in such an approach. Like broccoli, AUC ROC is healthy, but also like broccoli, researchers and practitioners in our field shouldn't eat a diet of only AUC ROC.
Authors: Lenka T\v{e}tkov\'a, Teresa Karen Scheidt, Maria Mandrup Fogh, Ellen Marie Gaunby J{\o}rgensen, Finn {\AA}rup Nielsen, Lars Kai Hansen
Abstract: Concept-based explainable AI is promising as a tool to improve the understanding of complex models at the premises of a given user, viz.\ as a tool for personalized explainability. An important class of concept-based explainability methods is constructed with empirically defined concepts, indirectly defined through a set of positive and negative examples, as in the TCAV approach (Kim et al., 2018). While it is appealing to the user to avoid formal definitions of concepts and their operationalization, it can be challenging to establish relevant concept datasets. Here, we address this challenge using general knowledge graphs (such as, e.g., Wikidata or WordNet) for comprehensive concept definition and present a workflow for user-driven data collection in both text and image domains. The concepts derived from knowledge graphs are defined interactively, providing an opportunity for personalization and ensuring that the concepts reflect the user's intentions. We test the retrieved concept datasets on two concept-based explainability methods, namely concept activation vectors (CAVs) and concept activation regions (CARs) (Crabbe and van der Schaar, 2022). We show that CAVs and CARs based on these empirical concept datasets provide robust and accurate explanations. Importantly, we also find good alignment between the models' representations of concepts and the structure of knowledge graphs, i.e., human representations. This supports our conclusion that knowledge graph-based concepts are relevant for XAI.
Authors: Amit Thombre
Abstract: In this work the decision trees are used for explanation of support vector regression model. The decision trees act as a global technique as well as a local technique. They are compared against the popular technique of LIME which is a local explanatory technique and with multi linear regression. It is observed that decision trees give a lower RMSE value when fitted to support vector regression as compared to LIME in 87% of the runs over 5 datasets. The comparison of results is statistically significant. Multi linear regression also gives a lower RMSE value when fitted to support vector regression model as compared to LIME in 73% of the runs over 5 datasets but the comparison of results is not statistically significant. Also, when used as a local explanatory technique, decision trees give better performance than LIME and the comparison of results is statistically significant.
Authors: Justin N. Kreikemeyer, Philipp Andelfinger, Adelinde M. Uhrmacher
Abstract: Increasing effort is put into the development of methods for learning mechanistic models from data. This task entails not only the accurate estimation of parameters, but also a suitable model structure. Recent work on the discovery of dynamical systems formulates this problem as a linear equation system. Here, we explore several simulation-based optimization approaches, which allow much greater freedom in the objective formulation and weaker conditions on the available data. We show that even for relatively small stochastic population models, simultaneous estimation of parameters and structure poses major challenges for optimization procedures. Particularly, we investigate the application of the local stochastic gradient descent method, commonly used for training machine learning models. We demonstrate accurate estimation of models but find that enforcing the inference of parsimonious, interpretable models drastically increases the difficulty. We give an outlook on how this challenge can be overcome.
Authors: Nathaniel Dean, Dilip Sarkar
Abstract: Overparameterized deep neural networks (DNNs), if not sufficiently regularized, are susceptible to overfitting their training examples and not generalizing well to test data. To discourage overfitting, researchers have developed multicomponent loss functions that reduce intra-class feature correlation and maximize inter-class feature distance in one or more layers of the network. By analyzing the penultimate feature layer activations output by a DNN's feature extraction section prior to the linear classifier, we find that modified forms of the intra-class feature covariance and inter-class prototype separation are key components of a fundamental Chebyshev upper bound on the probability of misclassification, which we designate the Chebyshev Prototype Risk (CPR). While previous approaches' covariance loss terms scale quadratically with the number of network features, our CPR bound indicates that an approximate covariance loss in log-linear time is sufficient to reduce the bound and is scalable to large architectures. We implement the terms of the CPR bound into our Explicit CPR (exCPR) loss function and observe from empirical results on multiple datasets and network architectures that our training algorithm reduces overfitting and improves upon previous approaches in many settings. Our code is available $\href{https://github.com/Deano1718/Regularization_exCPR}{here}$.
Authors: Rachid Zeghlache, Pierre-Henri Conze, Mostafa El Habib Daho, Yihao Li, Hugo Le Boit\'e, Ramin Tadayoni, Pascal Massin, B\'eatrice Cochener, Alireza Rezaei, Ikram Brahim, Gwenol\'e Quellec, Mathieu Lamard
Abstract: This work proposes a novel framework for analyzing disease progression using time-aware neural ordinary differential equations (NODE). We introduce a "time-aware head" in a framework trained through self-supervised learning (SSL) to leverage temporal information in latent space for data augmentation. This approach effectively integrates NODEs with SSL, offering significant performance improvements compared to traditional methods that lack explicit temporal integration. We demonstrate the effectiveness of our strategy for diabetic retinopathy progression prediction using the OPHDIAT database. Compared to the baseline, all NODE architectures achieve statistically significant improvements in area under the ROC curve (AUC) and Kappa metrics, highlighting the efficacy of pre-training with SSL-inspired approaches. Additionally, our framework promotes stable training for NODEs, a commonly encountered challenge in time-aware modeling.
Authors: Linas Nasvytis, Kai Sandbrink, Jakob Foerster, Tim Franzmeyer, Christian Schroeder de Witt
Abstract: While reinforcement learning (RL) algorithms have been successfully applied across numerous sequential decision-making problems, their generalization to unforeseen testing environments remains a significant concern. In this paper, we study the problem of out-of-distribution (OOD) detection in RL, which focuses on identifying situations at test time that RL agents have not encountered in their training environments. We first propose a clarification of terminology for OOD detection in RL, which aligns it with the literature from other machine learning domains. We then present new benchmark scenarios for OOD detection, which introduce anomalies with temporal autocorrelation into different components of the agent-environment loop. We argue that such scenarios have been understudied in the current literature, despite their relevance to real-world situations. Confirming our theoretical predictions, our experimental results suggest that state-of-the-art OOD detectors are not able to identify such anomalies. To address this problem, we propose a novel method for OOD detection, which we call DEXTER (Detection via Extraction of Time Series Representations). By treating environment observations as time series data, DEXTER extracts salient time series features, and then leverages an ensemble of isolation forest algorithms to detect anomalies. We find that DEXTER can reliably identify anomalies across benchmark scenarios, exhibiting superior performance compared to both state-of-the-art OOD detectors and high-dimensional changepoint detectors adopted from statistics.
Authors: Aaditya K. Singh, Ted Moskovitz, Felix Hill, Stephanie C. Y. Chan, Andrew M. Saxe
Abstract: In-context learning is a powerful emergent ability in transformer models. Prior work in mechanistic interpretability has identified a circuit element that may be critical for in-context learning -- the induction head (IH), which performs a match-and-copy operation. During training of large transformers on natural language data, IHs emerge around the same time as a notable phase change in the loss. Despite the robust evidence for IHs and this interesting coincidence with the phase change, relatively little is known about the diversity and emergence dynamics of IHs. Why is there more than one IH, and how are they dependent on each other? Why do IHs appear all of a sudden, and what are the subcircuits that enable them to emerge? We answer these questions by studying IH emergence dynamics in a controlled setting by training on synthetic data. In doing so, we develop and share a novel optogenetics-inspired causal framework for modifying activations throughout training. Using this framework, we delineate the diverse and additive nature of IHs. By clamping subsets of activations throughout training, we then identify three underlying subcircuits that interact to drive IH formation, yielding the phase change. Furthermore, these subcircuits shed light on data-dependent properties of formation, such as phase change timing, already showing the promise of this more in-depth understanding of subcircuits that need to "go right" for an induction head.
Authors: Unnseo Park, Venkatesh Sivaraman, Adam Perer
Abstract: Reinforcement learning (RL) is a promising approach to generate treatment policies for sepsis patients in intensive care. While retrospective evaluation metrics show decreased mortality when these policies are followed, studies with clinicians suggest their recommendations are often spurious. We propose that these shortcomings may be due to lack of diversity in observed actions and outcomes in the training data, and we construct experiments to investigate the feasibility of predicting sepsis disease severity changes due to clinician actions. Preliminary results suggest incorporating action information does not significantly improve model performance, indicating that clinician actions may not be sufficiently variable to yield measurable effects on disease progression. We discuss the implications of these findings for optimizing sepsis treatment.
Authors: Neel Mishra, Bamdev Mishra, Pratik Jawanpuria, Pawan Kumar
Abstract: A novel first-order method is proposed for training generative adversarial networks (GANs). It modifies the Gauss-Newton method to approximate the min-max Hessian and uses the Sherman-Morrison inversion formula to calculate the inverse. The method corresponds to a fixed-point method that ensures necessary contraction. To evaluate its effectiveness, numerical experiments are conducted on various datasets commonly used in image generation tasks, such as MNIST, Fashion MNIST, CIFAR10, FFHQ, and LSUN. Our method is capable of generating high-fidelity images with greater diversity across multiple datasets. It also achieves the highest inception score for CIFAR10 among all compared methods, including state-of-the-art second-order methods. Additionally, its execution time is comparable to that of first-order min-max methods.
Authors: Sachin Goyal, Pratyush Maini, Zachary C. Lipton, Aditi Raghunathan, J. Zico Kolter
Abstract: Vision-language models (VLMs) are trained for thousands of GPU hours on carefully curated web datasets. In recent times, data curation has gained prominence with several works developing strategies to retain 'high-quality' subsets of 'raw' scraped data. For instance, the LAION public dataset retained only 10% of the total crawled data. However, these strategies are typically developed agnostic of the available compute for training. In this paper, we first demonstrate that making filtering decisions independent of training compute is often suboptimal: the limited high-quality data rapidly loses its utility when repeated, eventually requiring the inclusion of 'unseen' but 'lower-quality' data. To address this quality-quantity tradeoff ($\texttt{QQT}$), we introduce neural scaling laws that account for the non-homogeneous nature of web data, an angle ignored in existing literature. Our scaling laws (i) characterize the $\textit{differing}$ 'utility' of various quality subsets of web data; (ii) account for how utility diminishes for a data point at its 'nth' repetition; and (iii) formulate the mutual interaction of various data pools when combined, enabling the estimation of model performance on a combination of multiple data pools without ever jointly training on them. Our key message is that data curation $\textit{cannot}$ be agnostic of the total compute that a model will be trained for. Our scaling laws allow us to curate the best possible pool for achieving top performance on Datacomp at various compute budgets, carving out a pareto-frontier for data curation. Code is available at https://github.com/locuslab/scaling_laws_data_filtering.
URLs: https://github.com/locuslab/scaling_laws_data_filtering.
Authors: Florian Sestak, Lisa Schneckenreiter, Johannes Brandstetter, Sepp Hochreiter, Andreas Mayr, G\"unter Klambauer
Abstract: Being able to identify regions within or around proteins, to which ligands can potentially bind, is an essential step to develop new drugs. Binding site identification methods can now profit from the availability of large amounts of 3D structures in protein structure databases or from AlphaFold predictions. Current binding site identification methods heavily rely on graph neural networks (GNNs), usually designed to output E(3)-equivariant predictions. Such methods turned out to be very beneficial for physics-related tasks like binding energy or motion trajectory prediction. However, the performance of GNNs at binding site identification is still limited potentially due to the lack of dedicated nodes that model hidden geometric entities, such as binding pockets. In this work, we extend E(n)-Equivariant Graph Neural Networks (EGNNs) by adding virtual nodes and applying an extended message passing scheme. The virtual nodes in these graphs are dedicated quantities to learn representations of binding sites, which leads to improved predictive performance. In our experiments, we show that our proposed method VN-EGNN sets a new state-of-the-art at locating binding site centers on COACH420, HOLO4K and PDBbind2020.
Authors: Shaoxiang Qin, Fuyuan Lyu, Wenhui Peng, Dingyang Geng, Ju Wang, Naiping Gao, Xue Liu, Liangzhu Leon Wang
Abstract: In solving partial differential equations (PDEs), Fourier Neural Operators (FNOs) have exhibited notable effectiveness compared to Convolutional Neural Networks (CNNs). This paper presents clear empirical evidence through spectral analysis to elucidate the superiority of FNO over CNNs: FNO is significantly more capable of learning low-frequencies. This empirical evidence also unveils FNO's distinct low-frequency bias, which limits FNO's effectiveness in learning high-frequency information from PDE data. To tackle this challenge, we introduce SpecBoost, an ensemble learning framework that employs multiple FNOs to better capture high-frequency information. Specifically, a secondary FNO is utilized to learn the overlooked high-frequency information from the prediction residual of the initial FNO. Experiments demonstrate that SpecBoost noticeably enhances FNO's prediction accuracy on diverse PDE applications, achieving an up to 71% improvement.
Authors: Desai Xie, Jiahao Li, Hao Tan, Xin Sun, Zhixin Shu, Yi Zhou, Sai Bi, S\"oren Pirk, Arie E. Kaufman
Abstract: Multi-view diffusion models, obtained by applying Supervised Finetuning (SFT) to text-to-image diffusion models, have driven recent breakthroughs in text-to-3D research. However, due to the limited size and quality of existing 3D datasets, they still suffer from multi-view inconsistencies and Neural Radiance Field (NeRF) reconstruction artifacts. We argue that multi-view diffusion models can benefit from further Reinforcement Learning Finetuning (RLFT), which allows models to learn from the data generated by themselves and improve beyond their dataset limitations during SFT. To this end, we introduce Carve3D, an improved RLFT algorithm coupled with a novel Multi-view Reconstruction Consistency (MRC) metric, to enhance the consistency of multi-view diffusion models. To measure the MRC metric on a set of multi-view images, we compare them with their corresponding NeRF renderings at the same camera viewpoints. The resulting model, which we denote as Carve3DM, demonstrates superior multi-view consistency and NeRF reconstruction quality than existing models. Our results suggest that pairing SFT with Carve3D's RLFT is essential for developing multi-view-consistent diffusion models, mirroring the standard Large Language Model (LLM) alignment pipeline. Our code, training and testing data, and video results are available at: https://desaixie.github.io/carve-3d.
Authors: Sahara Ali, Uzma Hasan, Xingyan Li, Omar Faruque, Akila Sampath, Yiyi Huang, Md Osman Gani, Jianwu Wang
Abstract: This survey paper covers the breadth and depth of time-series and spatiotemporal causality methods, and their applications in Earth Science. More specifically, the paper presents an overview of causal discovery and causal inference, explains the underlying causal assumptions, and enlists evaluation techniques and key terminologies of the domain area. The paper elicits the various state-of-the-art methods introduced for time-series and spatiotemporal causal analysis along with their strengths and limitations. The paper further describes the existing applications of several methods for answering specific Earth Science questions such as extreme weather events, sea level rise, teleconnections etc. This survey paper can serve as a primer for Data Science researchers interested in data-driven causal study as we share a list of resources, such as Earth Science datasets (synthetic, simulated and observational data) and open source tools for causal analysis. It will equally benefit the Earth Science community interested in taking an AI-driven approach to study the causality of different dynamic and thermodynamic processes as we present the open challenges and opportunities in performing causality-based Earth Science study.
Authors: Jing Dong, Baoxiang Wang, Yaoliang Yu
Abstract: In this work, we study potential games and Markov potential games under stochastic cost and bandit feedback. We propose a variant of the Frank-Wolfe algorithm with sufficient exploration and recursive gradient estimation, which provably converges to the Nash equilibrium while attaining sublinear regret for each individual player. Our algorithm simultaneously achieves a Nash regret and a regret bound of $O(T^{4/5})$ for potential games, which matches the best available result, without using additional projection steps. Through carefully balancing the reuse of past samples and exploration of new samples, we then extend the results to Markov potential games and improve the best available Nash regret from $O(T^{5/6})$ to $O(T^{4/5})$. Moreover, our algorithm requires no knowledge of the game, such as the distribution mismatch coefficient, which provides more flexibility in its practical implementation. Experimental results corroborate our theoretical findings and underscore the practical effectiveness of our method.
Authors: Jason Stock, Jaideep Pathak, Yair Cohen, Mike Pritchard, Piyush Garg, Dale Durran, Morteza Mardani, Noah Brenowitz
Abstract: This work presents an autoregressive generative diffusion model (DiffObs) to predict the global evolution of daily precipitation, trained on a satellite observational product, and assessed with domain-specific diagnostics. The model is trained to probabilistically forecast day-ahead precipitation. Nonetheless, it is stable for multi-month rollouts, which reveal a qualitatively realistic superposition of convectively coupled wave modes in the tropics. Cross-spectral analysis confirms successful generation of low frequency variations associated with the Madden--Julian oscillation, which regulates most subseasonal to seasonal predictability in the observed atmosphere, and convectively coupled moist Kelvin waves with approximately correct dispersion relationships. Despite secondary issues and biases, the results affirm the potential for a next generation of global diffusion models trained on increasingly sparse, and increasingly direct and differentiated observations of the world, for practical applications in subseasonal and climate prediction.
Authors: Milad Aghajohari, Tim Cooijmans, Juan Agustin Duque, Shunichi Akatsuka, Aaron Courville
Abstract: We investigate the challenge of multi-agent deep reinforcement learning in partially competitive environments, where traditional methods struggle to foster reciprocity-based cooperation. LOLA and POLA agents learn reciprocity-based cooperative policies by differentiation through a few look-ahead optimization steps of their opponent. However, there is a key limitation in these techniques. Because they consider a few optimization steps, a learning opponent that takes many steps to optimize its return may exploit them. In response, we introduce a novel approach, Best Response Shaping (BRS), which differentiates through an opponent approximating the best response, termed the "detective." To condition the detective on the agent's policy for complex games we propose a state-aware differentiable conditioning mechanism, facilitated by a question answering (QA) method that extracts a representation of the agent based on its behaviour on specific environment states. To empirically validate our method, we showcase its enhanced performance against a Monte Carlo Tree Search (MCTS) opponent, which serves as an approximation to the best response in the Coin Game. This work expands the applicability of multi-agent RL in partially competitive environments and provides a new pathway towards achieving improved social welfare in general sum games.
Authors: Gavin S. Hartnett, Aaron Barbosa, Pranav S. Mundada, Michael Hush, Michael J. Biercuk, Yuval Baum
Abstract: We introduce and experimentally test a machine-learning-based method for ranking logically equivalent quantum circuits based on expected performance estimates derived from a training procedure conducted on real hardware. We apply our method to the problem of layout selection, in which abstracted qubits are assigned to physical qubits on a given device. Circuit measurements performed on IBM hardware indicate that the maximum and median fidelities of logically equivalent layouts can differ by an order of magnitude. We introduce a circuit score used for ranking that is parameterized in terms of a physics-based, phenomenological error model whose parameters are fit by training a ranking-loss function over a measured dataset. The dataset consists of quantum circuits exhibiting a diversity of structures and executed on IBM hardware, allowing the model to incorporate the contextual nature of real device noise and errors without the need to perform an exponentially costly tomographic protocol. We perform model training and execution on the 16-qubit ibmq_guadalupe device and compare our method to two common approaches: random layout selection and a publicly available baseline called Mapomatic. Our model consistently outperforms both approaches, predicting layouts that exhibit lower noise and higher performance. In particular, we find that our best model leads to a $1.8\times$ reduction in selection error when compared to the baseline approach and a $3.2\times$ reduction when compared to random selection. Beyond delivering a new form of predictive quantum characterization, verification, and validation, our results reveal the specific way in which context-dependent and coherent gate errors appear to dominate the divergence from performance estimates extrapolated from simple proxy measures.
Authors: Lindsey Linxi Wei, Chung Yik Edward Yeung, Hongjian Yu, Jingchuan Zhou, Dong He, Magdalena Balazinska
Abstract: We demonstrate MaskSearch, a system designed to accelerate queries over databases of image masks generated by machine learning models. MaskSearch formalizes and accelerates a new category of queries for retrieving images and their corresponding masks based on mask properties, which support various applications, from identifying spurious correlations learned by models to exploring discrepancies between model saliency and human attention. This demonstration makes the following contributions:(1) the introduction of MaskSearch's graphical user interface (GUI), which enables interactive exploration of image databases through mask properties, (2) hands-on opportunities for users to explore MaskSearch's capabilities and constraints within machine learning workflows, and (3) an opportunity for conference attendees to understand how MaskSearch accelerates queries over image masks.
Authors: Tong Wang, Ninad Kulkarni, Yanjun Qi
Abstract: Assessing the factual consistency of automatically generated texts in relation to source context is crucial for developing reliable natural language generation applications. Recent literature proposes AlignScore which uses a unified alignment model to evaluate factual consistency and substantially outperforms previous methods across many benchmark tasks. In this paper, we take a closer look of datasets used in AlignScore and uncover an unexpected finding: utilizing a smaller number of data points can actually improve performance. We process the original AlignScore training dataset to remove noise, augment with robustness-enhanced samples, and utilize a subset comprising 10\% of the data to train an improved factual consistency evaluation model, we call LIM-RA (Less Is More for Robust AlignScore). LIM-RA demonstrates superior performance, consistently outperforming AlignScore and other strong baselines like ChatGPT across four benchmarks (two utilizing traditional natural language generation datasets and two focused on large language model outputs). Our experiments show that LIM-RA achieves the highest score on 24 of the 33 test datasets, while staying competitive on the rest, establishing the new state-of-the-art benchmarks.
Authors: Tamir Shor, Chaim Baskin, Alex Bronstein
Abstract: Breast cancer is a prominent health concern worldwide, currently being the secondmost common and second-deadliest type of cancer in women. While current breast cancer diagnosis mainly relies on mammography imaging, in recent years the use of thermography for breast cancer imaging has been garnering growing popularity. Thermographic imaging relies on infrared cameras to capture body-emitted heat distributions. While these heat signatures have proven useful for computer-vision systems for accurate breast cancer segmentation and classification, prior work often relies on handcrafted feature engineering or complex architectures, potentially limiting the comparability and applicability of these methods. In this work, we present a novel algorithm for both breast cancer classification and segmentation. Rather than focusing efforts on manual feature and architecture engineering, our algorithm focuses on leveraging an informative, learned feature space, thus making our solution simpler to use and extend to other frameworks and downstream tasks, as well as more applicable to data-scarce settings. Our classification produces SOTA results, while we are the first work to produce segmentation regions studied in this paper.
Authors: Md. Farhadul Islam, Md. Tanzim Reza, Meem Arafat Manab, Mohammad Rakibul Hasan Mahin, Sarah Zabeen, Jannatun Noor
Abstract: Spatial optimization is often overlooked in many computer vision tasks. Filters should be able to recognize the features of an object regardless of where it is in the image. Similarity search is a crucial task where spatial features decide an important output. The capacity of convolution to capture visual patterns across various locations is limited. In contrast to convolution, the involution kernel is dynamically created at each pixel based on the pixel value and parameters that have been learned. This study demonstrates that utilizing a single layer of involution feature extractor alongside a compact convolution model significantly enhances the performance of similarity search. Additionally, we improve predictions by using the GELU activation function rather than the ReLU. The negligible amount of weight parameters in involution with a compact model with better performance makes the model very useful in real-world implementations. Our proposed model is below 1 megabyte in size. We have experimented with our proposed methodology and other models on CIFAR-10, FashionMNIST, and MNIST datasets. Our proposed method outperforms across all three datasets.
Authors: Jane Dwivedi-Yu, Raaz Dwivedi, Timo Schick
Abstract: The accurate evaluation of differential treatment in language models to specific groups is critical to ensuring a positive and safe user experience. An ideal evaluation should have the properties of being robust, extendable to new groups or attributes, and being able to capture biases that appear in typical usage (rather than just extreme, rare cases). Relatedly, bias evaluation should surface not only egregious biases but also ones that are subtle and commonplace, such as a likelihood for talking about appearances with regard to women. We present FairPair, an evaluation framework for assessing differential treatment that occurs during ordinary usage. FairPair operates through counterfactual pairs, but crucially, the paired continuations are grounded in the same demographic group, which ensures equivalent comparison. Additionally, unlike prior work, our method factors in the inherent variability that comes from the generation process itself by measuring the sampling variability. We present an evaluation of several commonly used generative models and a qualitative analysis that indicates a preference for discussing family and hobbies with regard to women.
Authors: Bernard J. Koch, David Peterson
Abstract: Over the past decade, AI research has focused heavily on building ever-larger deep learning models. This approach has simultaneously unlocked incredible achievements in science and technology, and hindered AI from overcoming long-standing limitations with respect to explainability, ethical harms, and environmental efficiency. Drawing on qualitative interviews and computational analyses, our three-part history of AI research traces the creation of this "epistemic monoculture" back to a radical reconceptualization of scientific progress that occurred in the 1990s. In the first era of AI research (1950s-late 1980s), researchers and patrons approached AI as a "basic" science that would advance through autonomous exploration and organic assessments of progress (e.g., peer-review, theoretical consensus). The failure of this approach led to a retrenchment of funding in the 1980s. Amid this "AI Winter," an intervention by the U.S. government reoriented the field towards measurable progress on tasks of military and commercial interest. A new evaluation system called "benchmarking" provided an objective way to quantify progress on tasks by focusing exclusively on increasing predictive accuracy on example datasets. Distilling science down to verifiable metrics clarified the roles of scientists, allowed the field to rapidly integrate talent, and provided clear signals of significance and progress. But history has also revealed a tradeoff to this streamlined approach to science: the consolidation around external interests and inherent conservatism of benchmarking has disincentivized exploration beyond scaling monoculture. In the discussion, we explain how AI's monoculture offers a compelling challenge to the belief that basic, exploration-driven research is needed for scientific progress. Implications for the spread of AI monoculture to other sciences in the era of generative AI are also discussed.
Authors: Haiying Huang, Adnan Darwiche
Abstract: The unit selection problem aims to find objects, called units, that optimize a causal objective function which describes the objects' behavior in a causal context (e.g., selecting customers who are about to churn but would most likely change their mind if encouraged). While early studies focused mainly on bounding a specific class of counterfactual objective functions using data, more recent work allows one to find optimal units exactly by reducing the causal objective to a classical objective on a meta-model, and then applying a variant of the classical Variable Elimination (VE) algorithm to the meta-model -- assuming a fully specified causal model is available. In practice, however, finding optimal units using this approach can be very expensive because the used VE algorithm must be exponential in the constrained treewidth of the meta-model, which is larger and denser than the original model. We address this computational challenge by introducing a new approach for unit selection that is not necessarily limited by the constrained treewidth. This is done through compiling the meta-model into a special class of tractable arithmetic circuits that allows the computation of optimal units in time linear in the circuit size. We finally present empirical results on random causal models that show order-of-magnitude speedups based on the proposed method for solving unit selection.
Authors: Leying Zhang, Yao Qian, Long Zhou, Shujie Liu, Dongmei Wang, Xiaofei Wang, Midia Yousefi, Yanmin Qian, Jinyu Li, Lei He, Sheng Zhao, Michael Zeng
Abstract: Recent advancements in zero-shot text-to-speech (TTS) modeling have led to significant strides in generating high-fidelity and diverse speech. However, dialogue generation, along with achieving human-like naturalness in speech, continues to be a challenge in the field. In this paper, we introduce CoVoMix: Conversational Voice Mixture Generation, a novel model for zero-shot, human-like, multi-speaker, multi-round dialogue speech generation. CoVoMix is capable of first converting dialogue text into multiple streams of discrete tokens, with each token stream representing semantic information for individual talkers. These token streams are then fed into a flow-matching based acoustic model to generate mixed mel-spectrograms. Finally, the speech waveforms are produced using a HiFi-GAN model. Furthermore, we devise a comprehensive set of metrics for measuring the effectiveness of dialogue modeling and generation. Our experimental results show that CoVoMix can generate dialogues that are not only human-like in their naturalness and coherence but also involve multiple talkers engaging in multiple rounds of conversation. These dialogues, generated within a single channel, are characterized by seamless speech transitions, including overlapping speech, and appropriate paralinguistic behaviors such as laughter. Audio samples are available at https://aka.ms/covomix.
URLs: https://aka.ms/covomix.
Authors: Ningfeng Liu (State Key Laboratory of Natural and Biomimetic Drugs, School of Pharmaceutical Sciences, Peking University, Peking-Tsinghua Center for Life Science), Jie Yu (State Key Laboratory of Natural and Biomimetic Drugs, School of Pharmaceutical Sciences, Peking University), Siyu Xiu (State Key Laboratory of Natural and Biomimetic Drugs, School of Pharmaceutical Sciences, Peking University), Xinfang Zhao (State Key Laboratory of Natural and Biomimetic Drugs, School of Pharmaceutical Sciences, Peking University), Siyu Lin (State Key Laboratory of Natural and Biomimetic Drugs, School of Pharmaceutical Sciences, Peking University), Bo Qiang (State Key Laboratory of Natural and Biomimetic Drugs, School of Pharmaceutical Sciences, Peking University), Ruqiu Zheng (State Key Laboratory of Natural and Biomimetic Drugs, School of Pharmaceutical Sciences, Peking University), Hongwei Jin (State Key Laboratory of Natural and Biomimetic Drugs, School of Pharmaceutical Sciences, Peking University), Liangren Zhang (State Key Laboratory of Natural and Biomimetic Drugs, School of Pharmaceutical Sciences, Peking University), Zhenming Liu (State Key Laboratory of Natural and Biomimetic Drugs, School of Pharmaceutical Sciences, Peking University, State Key Laboratory of Pharmaceutical Biotechnology, Nanjing University)
Abstract: Molecular generation, an essential method for identifying new drug structures, has been supported by advancements in machine learning and computational technology. However, challenges remain in multi-objective generation, model adaptability, and practical application in drug discovery. In this study, we developed a versatile 'plug-in' molecular generation model that incorporates multiple objectives related to target affinity, drug-likeness, and synthesizability, facilitating its application in various drug development contexts. We improved the Particle Swarm Optimization (PSO) in the context of drug discoveries, and identified PSO-ENP as the optimal variant for multi-objective molecular generation and optimization through comparative experiments. The model also incorporates a novel target-ligand affinity predictor, enhancing the model's utility by supporting three-dimensional information and improving synthetic feasibility. Case studies focused on generating and optimizing drug-like big marine natural products were performed, underscoring PSO-ENP's effectiveness and demonstrating its considerable potential for practical drug discovery applications.
Authors: Moise Blanchard
Abstract: In this paper we provide oracle complexity lower bounds for finding a point in a given set using a memory-constrained algorithm that has access to a separation oracle. We assume that the set is contained within the unit $d$-dimensional ball and contains a ball of known radius $\epsilon>0$. This setup is commonly referred to as the feasibility problem. We show that to solve feasibility problems with accuracy $\epsilon \geq e^{-d^{o(1)}}$, any deterministic algorithm either uses $d^{1+\delta}$ bits of memory or must make at least $1/(d^{0.01\delta }\epsilon^{2\frac{1-\delta}{1+1.01 \delta}-o(1)})$ oracle queries, for any $\delta\in[0,1]$. Additionally, we show that randomized algorithms either use $d^{1+\delta}$ memory or make at least $1/(d^{2\delta} \epsilon^{2(1-4\delta)-o(1)})$ queries for any $\delta\in[0,\frac{1}{4}]$. Because gradient descent only uses linear memory $\mathcal O(d\ln 1/\epsilon)$ but makes $\Omega(1/\epsilon^2)$ queries, our results imply that it is Pareto-optimal in the oracle complexity/memory tradeoff. Further, our results show that the oracle complexity for deterministic algorithms is always polynomial in $1/\epsilon$ if the algorithm has less than quadratic memory in $d$. This reveals a sharp phase transition since with quadratic $\mathcal O(d^2 \ln1/\epsilon)$ memory, cutting plane methods only require $\mathcal O(d\ln 1/\epsilon)$ queries.
Authors: Jie Wang, Yash Vardhan Pant, Lei Zhao, Micha{\l} Antkiewicz, Krzysztof Czarnecki
Abstract: With the increasing presence of autonomous vehicles (AVs) on public roads, developing robust control strategies to navigate the uncertainty of human-driven vehicles (HVs) is crucial. This paper introduces an advanced method for modeling HV behavior, combining a first-principles model with Gaussian process (GP) learning to enhance velocity prediction accuracy and provide a measurable uncertainty. We validated this innovative HV model using real-world data from field experiments and applied it to develop a GP-enhanced model predictive control (GP-MPC) strategy. This strategy aims to improve safety in mixed vehicle platoons by integrating uncertainty assessment into distance constraints. Comparative simulation studies with a conventional model predictive control (MPC) approach demonstrated that our GP-MPC strategy ensures more reliable safe distancing and fosters efficient vehicular dynamics, achieving notably higher speeds within the platoon. By incorporating a sparse GP technique in HV modeling and adopting a dynamic GP prediction within the MPC framework, we significantly reduced the computation time of GP-MPC, marking it only 4.6% higher than that of the conventional MPC. This represents a substantial improvement, making the process about 100 times faster than our preliminary work without these approximations. Our findings underscore the effectiveness of learning-based HV modeling in enhancing both safety and operational efficiency in mixed-traffic environments, paving the way for more harmonious AV-HV interactions.
Authors: Qi Zhang, Bing Li, Lingzhou Xue
Abstract: Motivated by modern data forms such as images and multi-view data, the multi-attribute graphical model aims to explore the conditional independence structure among vectors. Under the Gaussian assumption, the conditional independence between vectors is characterized by blockwise zeros in the precision matrix. To relax the restrictive Gaussian assumption, in this paper, we introduce a novel semiparametric multi-attribute graphical model based on a new copula named Cyclically Monotone Copula. This new copula treats the distribution of the node vectors as multivariate marginals and transforms them into Gaussian distributions based on the optimal transport theory. Since the model allows the node vectors to have arbitrary continuous distributions, it is more flexible than the classical Gaussian copula method that performs coordinatewise Gaussianization. We establish the concentration inequalities of the estimated covariance matrices and provide sufficient conditions for selection consistency of the group graphical lasso estimator. For the setting with high-dimensional attributes, a {Projected Cyclically Monotone Copula} model is proposed to address the curse of dimensionality issue that arises from solving high-dimensional optimal transport problems. Numerical results based on synthetic and real data show the efficiency and flexibility of our methods.
Authors: Jon Kleinberg, Sendhil Mullainathan
Abstract: Although current large language models are complex, the most basic specifications of the underlying language generation problem itself are simple to state: given a finite set of training samples from an unknown language, produce valid new strings from the language that don't already appear in the training data. Here we ask what we can conclude about language generation using only this specification, without further assumptions. In particular, suppose that an adversary enumerates the strings of an unknown target language L that is known only to come from one of a possibly infinite list of candidates. A computational agent is trying to learn to generate from this language; we say that the agent generates from L in the limit if after some finite point in the enumeration of L, the agent is able to produce new elements that come exclusively from L and that have not yet been presented by the adversary. Our main result is that there is an agent that is able to generate in the limit for every countable list of candidate languages. This contrasts dramatically with negative results due to Gold and Angluin in a well-studied model of language learning where the goal is to identify an unknown language from samples; the difference between these results suggests that identifying a language is a fundamentally different problem than generating from it.
Authors: Taegyun Kwon, Dasaem Jeong, Juhan Nam
Abstract: In recent years, advancements in neural network designs and the availability of large-scale labeled datasets have led to significant improvements in the accuracy of piano transcription models. However, most previous work focused on high-performance offline transcription, neglecting deliberate consideration of model size. The goal of this work is to implement real-time inference for piano transcription while ensuring both high performance and lightweight. To this end, we propose novel architectures for convolutional recurrent neural networks, redesigning an existing autoregressive piano transcription model. First, we extend the acoustic module by adding a frequency-conditioned FiLM layer to the CNN module to adapt the convolutional filters on the frequency axis. Second, we improve note-state sequence modeling by using a pitchwise LSTM that focuses on note-state transitions within a note. In addition, we augment the autoregressive connection with an enhanced recursive context. Using these components, we propose two types of models; one for high performance and the other for high compactness. Through extensive experiments, we show that the proposed models are comparable to state-of-the-art models in terms of note accuracy on the MAESTRO dataset. We also investigate the effective model size and real-time inference latency by gradually streamlining the architecture. Finally, we conduct cross-data evaluation on unseen piano datasets and in-depth analysis to elucidate the effect of the proposed components in the view of note length and pitch range.
Authors: Mathis Kruse, Marco Rudolph, Dominik Woiwode, Bodo Rosenhahn
Abstract: Detecting anomalies in images has become a well-explored problem in both academia and industry. State-of-the-art algorithms are able to detect defects in increasingly difficult settings and data modalities. However, most current methods are not suited to address 3D objects captured from differing poses. While solutions using Neural Radiance Fields (NeRFs) have been proposed, they suffer from excessive computation requirements, which hinder real-world usability. For this reason, we propose the novel 3D Gaussian splatting-based framework SplatPose which, given multi-view images of a 3D object, accurately estimates the pose of unseen views in a differentiable manner, and detects anomalies in them. We achieve state-of-the-art results in both training and inference speed, and detection performance, even when using less training data than competing methods. We thoroughly evaluate our framework using the recently proposed Pose-agnostic Anomaly Detection benchmark and its multi-pose anomaly detection (MAD) data set.
Authors: Guanhang Lei, Zhen Lei, Lei Shi, Chenyu Zeng
Abstract: We propose the POD-DNN, a novel algorithm leveraging deep neural networks (DNNs) along with radial basis functions (RBFs) in the context of the proper orthogonal decomposition (POD) reduced basis method (RBM), aimed at approximating the parametric mapping of parametric partial differential equations on irregular domains. The POD-DNN algorithm capitalizes on the low-dimensional characteristics of the solution manifold for parametric equations, alongside the inherent offline-online computational strategy of RBM and DNNs. In numerical experiments, POD-DNN demonstrates significantly accelerated computation speeds during the online phase. Compared to other algorithms that utilize RBF without integrating DNNs, POD-DNN substantially improves the computational speed in the online inference process. Furthermore, under reasonable assumptions, we have rigorously derived upper bounds on the complexity of approximating parametric mappings with POD-DNN, thereby providing a theoretical analysis of the algorithm's empirical performance.
Authors: Mohamadreza Rostami, Marco Chilese, Shaza Zeitouni, Rahul Kande, Jeyavijayan Rajendran, Ahmad-Reza Sadeghi
Abstract: Modern computing systems heavily rely on hardware as the root of trust. However, their increasing complexity has given rise to security-critical vulnerabilities that cross-layer at-tacks can exploit. Traditional hardware vulnerability detection methods, such as random regression and formal verification, have limitations. Random regression, while scalable, is slow in exploring hardware, and formal verification techniques are often concerned with manual effort and state explosions. Hardware fuzzing has emerged as an effective approach to exploring and detecting security vulnerabilities in large-scale designs like modern processors. They outperform traditional methods regarding coverage, scalability, and efficiency. However, state-of-the-art fuzzers struggle to achieve comprehensive coverage of intricate hardware designs within a practical timeframe, often falling short of a 70% coverage threshold. We propose a novel ML-based hardware fuzzer, ChatFuzz, to address this challenge. Ourapproach leverages LLMs like ChatGPT to understand processor language, focusing on machine codes and generating assembly code sequences. RL is integrated to guide the input generation process by rewarding the inputs using code coverage metrics. We use the open-source RISCV-based RocketCore processor as our testbed. ChatFuzz achieves condition coverage rate of 75% in just 52 minutes compared to a state-of-the-art fuzzer, which requires a lengthy 30-hour window to reach a similar condition coverage. Furthermore, our fuzzer can attain 80% coverage when provided with a limited pool of 10 simulation instances/licenses within a 130-hour window. During this time, it conducted a total of 199K test cases, of which 6K produced discrepancies with the processor's golden model. Our analysis identified more than 10 unique mismatches, including two new bugs in the RocketCore and discrepancies from the RISC-V ISA Simulator.
Authors: Thomas Merth, Qichen Fu, Mohammad Rastegari, Mahyar Najibi
Abstract: Despite the successes of large language models (LLMs), they exhibit significant drawbacks, particularly when processing long contexts. Their inference cost scales quadratically with respect to sequence length, making it expensive for deployment in some real-world text processing applications, such as retrieval-augmented generation (RAG). Additionally, LLMs also exhibit the "distraction phenomenon," where irrelevant context in the prompt degrades output quality. To address these drawbacks, we propose a novel RAG prompting methodology, superposition prompting, which can be directly applied to pre-trained transformer-based LLMs without the need for fine-tuning. At a high level, superposition prompting allows the LLM to process input documents in parallel prompt paths, discarding paths once they are deemed irrelevant. We demonstrate the capability of our method to simultaneously enhance time efficiency across a variety of question-answering benchmarks using multiple pre-trained LLMs. Furthermore, our technique significantly improves accuracy when the retrieved context is large relative the context the model was trained on. For example, our approach facilitates an 93x reduction in compute time while improving accuracy by 43\% on the NaturalQuestions-Open dataset with the MPT-7B instruction-tuned model over naive RAG.
Authors: Chen Zhou, Ghassan AlRegib, Armin Parchami, Kunjan Singh
Abstract: Forecasting human trajectories in traffic scenes is critical for safety within mixed or fully autonomous systems. Human future trajectories are driven by two major stimuli, social interactions, and stochastic goals. Thus, reliable forecasting needs to capture these two stimuli. Edge-based relation modeling represents social interactions using pairwise correlations from precise individual states. Nevertheless, edge-based relations can be vulnerable under perturbations. To alleviate these issues, we propose a region-based relation learning paradigm that models social interactions via region-wise dynamics of joint states, i.e., the changes in the density of crowds. In particular, region-wise agent joint information is encoded within convolutional feature grids. Social relations are modeled by relating the temporal changes of local joint information from a global perspective. We show that region-based relations are less susceptible to perturbations. In order to account for the stochastic individual goals, we exploit a conditional variational autoencoder to realize multi-goal estimation and diverse future prediction. Specifically, we perform variational inference via the latent distribution, which is conditioned on the correlation between input states and associated target goals. Sampling from the latent distribution enables the framework to reliably capture the stochastic behavior in test data. We integrate multi-goal estimation and region-based relation learning to model the two stimuli, social interactions, and stochastic goals, in a prediction framework. We evaluate our framework on the ETH-UCY dataset and Stanford Drone Dataset (SDD). We show that the diverse prediction better fits the ground truth when incorporating the relation module. Our framework outperforms the state-of-the-art models on SDD by $27.61\%$/$18.20\%$ of ADE/FDE metrics.
Authors: Zeno Woywood, Jasper I. Wiltfang, Julius Luy, Tobias Enders, Maximilian Schiffer
Abstract: We study a sequential decision-making problem for a profit-maximizing operator of an Autonomous Mobility-on-Demand system. Optimizing a central operator's vehicle-to-request dispatching policy requires efficient and effective fleet control strategies. To this end, we employ a multi-agent Soft Actor-Critic algorithm combined with weighted bipartite matching. We propose a novel vehicle-based algorithm architecture and adapt the critic's loss function to appropriately consider global actions. Furthermore, we extend our algorithm to incorporate rebalancing capabilities. Through numerical experiments, we show that our approach outperforms state-of-the-art benchmarks by up to 12.9% for dispatching and up to 38.9% with integrated rebalancing.
Authors: Hanna Meyer, Marvin Ludwig, Carles Mil\`a, Jan Linnenbrink, Fabian Schumacher
Abstract: One key task in environmental science is to map environmental variables continuously in space or even in space and time. Machine learning algorithms are frequently used to learn from local field observations to make spatial predictions by estimating the value of the variable of interest in places where it has not been measured. However, the application of machine learning strategies for spatial mapping involves additional challenges compared to "non-spatial" prediction tasks that often originate from spatial autocorrelation and from training data that are not independent and identically distributed. In the past few years, we developed a number of methods to support the application of machine learning for spatial data which involves the development of suitable cross-validation strategies for performance assessment and model selection, spatial feature selection, and methods to assess the area of applicability of the trained models. The intention of the CAST package is to support the application of machine learning strategies for predictive mapping by implementing such methods and making them available for easy integration into modelling workflows. Here we introduce the CAST package and its core functionalities. At the case study of mapping plant species richness, we will go through the different steps of the modelling workflow and show how CAST can be used to support more reliable spatial predictions.
Authors: Otto Sumray, Heather A. Harrington, Vidit Nanda
Abstract: The challenge of selecting the most relevant features of a given dataset arises ubiquitously in data analysis and dimensionality reduction. However, features found to be of high importance for the entire dataset may not be relevant to subsets of interest, and vice versa. Given a feature selector and a fixed decomposition of the data into subsets, we describe a method for identifying selected features which are compatible with the decomposition into subsets. We achieve this by re-framing the problem of finding compatible features to one of finding sections of a suitable quiver representation. In order to approximate such sections, we then introduce a Laplacian operator for quiver representations valued in Hilbert spaces. We provide explicit bounds on how the spectrum of a quiver Laplacian changes when the representation and the underlying quiver are modified in certain natural ways. Finally, we apply this machinery to the study of peak-calling algorithms which measure chromatin accessibility in single-cell data. We demonstrate that eigenvectors of the associated quiver Laplacian yield locally and globally compatible features.
Authors: Wanting Yang, Zehui Xiong, Yanli Yuan, Wenchao Jiang, Tony Q. S. Quek, Merouane Debbah
Abstract: In the era of 6G, featuring compelling visions of intelligent transportation system, digital twins, remote surveillance is poised to become a ubiquitous practice. The substantial data volume and frequent updates present challenges in wireless networks. To address this, we propose a novel agent-driven generative semantic communication (A-GSC) framework based on reinforcement learning. In contrast to the existing research on semantic communication (SemCom), which mainly focuses on semantic compression or semantic sampling, we seamlessly cascade both together by jointly considering the intrinsic attributes of source information and the contextual information regarding the task. Notably, the introduction of the generative artificial intelligence (GAI) enables the independent design of semantic encoders and decoders. In this work, we develop an agent-assisted semantic encoder leveraging the knowledge based soft actor-critic algorithm, which can track the semantic changes, channel condition, and sampling intervals, so as to perform adaptive semantic sampling. Accordingly, we design a semantic decoder with both predictive and generative capabilities, which consists of two tailored modules. Moreover, the effectiveness of the designed models has been verified based on the dataset generated from CDNet2014, and the performance gain of the overall A-GSC framework in both energy saving and reconstruction accuracy have been demonstrated.
Authors: Kuo-Yu Liao, Cheng-Shang Chang, Y. -W. Peter Hong
Abstract: Recent advances in Large Language Models (LLMs) have demonstrated the emergence of capabilities (learned skills) when the number of system parameters and the size of training data surpass certain thresholds. The exact mechanisms behind such phenomena are not fully understood and remain a topic of active research. Inspired by the skill-text bipartite graph model presented in [1] for modeling semantic language, we develop a mathematical theory to explain the emergence of learned skills, taking the learning (or training) process into account. Our approach models the learning process for skills in the skill-text bipartite graph as an iterative decoding process in Low-Density Parity Check (LDPC) codes and Irregular Repetition Slotted ALOHA (IRSA). Using density evolution analysis, we demonstrate the emergence of learned skills when the ratio of the size of training texts to the number of skills exceeds a certain threshold. Our analysis also yields a scaling law for testing errors relative to the size of training texts. Upon completion of the training, we propose a method for semantic compression and discuss its application in semantic communication.
Authors: Elisa Sanchez-Bayona, Rodrigo Agerri
Abstract: Metaphors, although occasionally unperceived, are ubiquitous in our everyday language. Thus, it is crucial for Language Models to be able to grasp the underlying meaning of this kind of figurative language. In this work, we present Meta4XNLI, a novel parallel dataset for the tasks of metaphor detection and interpretation that contains metaphor annotations in both Spanish and English. We investigate language models' metaphor identification and understanding abilities through a series of monolingual and cross-lingual experiments by leveraging our proposed corpus. In order to comprehend how these non-literal expressions affect models' performance, we look over the results and perform an error analysis. Additionally, parallel data offers many potential opportunities to investigate metaphor transferability between these languages and the impact of translation on the development of multilingual annotated resources.
Authors: Alessandro Stolfo
Abstract: We present an empirical study of groundedness in long-form question answering (LFQA) by retrieval-augmented large language models (LLMs). In particular, we evaluate whether every generated sentence is grounded in the retrieved documents or the model's pre-training data. Across 3 datasets and 4 model families, our findings reveal that a significant fraction of generated sentences are consistently ungrounded, even when those sentences contain correct ground-truth answers. Additionally, we examine the impacts of factors such as model size, decoding strategy, and instruction tuning on groundedness. Our results show that while larger models tend to ground their outputs more effectively, a significant portion of correct answers remains compromised by hallucinations. This study provides novel insights into the groundedness challenges in LFQA and underscores the necessity for more robust mechanisms in LLMs to mitigate the generation of ungrounded content.
Authors: Mingyu Jin, Qinkai Yu, Jingyuan Huang, Qingcheng Zeng, Zhenting Wang, Wenyue Hua, Haiyan Zhao, Kai Mei, Yanda Meng, Kaize Ding, Fan Yang, Mengnan Du, Yongfeng Zhang
Abstract: This paper studies the phenomenon that different concepts are learned in different layers of large language models, i.e. more difficult concepts are fully acquired with deeper layers. We define the difficulty of concepts by the level of abstraction, and here it is crudely categorized by factual, emotional, and inferential. Each category contains a spectrum of tasks, arranged from simple to complex. For example, within the factual dimension, tasks range from lie detection to categorizing mathematical problems. We employ a probing technique to extract representations from different layers of the model and apply these to classification tasks. Our findings reveal that models tend to efficiently classify simpler tasks, indicating that these concepts are learned in shallower layers. Conversely, more complex tasks may only be discernible at deeper layers, if at all. This paper explores the implications of these findings for our understanding of model learning processes and internal representations. Our implementation is available at \url{https://github.com/Luckfort/CD}.
Authors: Bowen Jin, Chulin Xie, Jiawei Zhang, Kashob Kumar Roy, Yu Zhang, Suhang Wang, Yu Meng, Jiawei Han
Abstract: Large language models (LLMs), while exhibiting exceptional performance, suffer from hallucinations, especially on knowledge-intensive tasks. Existing works propose to augment LLMs with individual text units retrieved from external knowledge corpora to alleviate the issue. However, in many domains, texts are interconnected (e.g., academic papers in a bibliographic graph are linked by citations and co-authorships) which form a (text-attributed) graph. The knowledge in such graphs is encoded not only in single texts/nodes but also in their associated connections. To facilitate the research of augmenting LLMs with graphs, we manually construct a Graph Reasoning Benchmark dataset called GRBench, containing 1,740 questions that can be answered with the knowledge from 10 domain graphs. Then, we propose a simple and effective framework called Graph Chain-of-thought (Graph-CoT) to augment LLMs with graphs by encouraging LLMs to reason on the graph iteratively. Each Graph-CoT iteration consists of three sub-steps: LLM reasoning, LLM-graph interaction, and graph execution. We conduct systematic experiments with three LLM backbones on GRBench, where Graph-CoT outperforms the baselines consistently. The code is available at https://github.com/PeterGriffinJin/Graph-CoT.
Authors: Mat\'ias Mattamala, Jonas Frey, Piotr Libera, Nived Chebrolu, Georg Martius, Cesar Cadena, Marco Hutter, Maurice Fallon
Abstract: Natural environments such as forests and grasslands are challenging for robotic navigation because of the false perception of rigid obstacles from high grass, twigs, or bushes. In this work, we present Wild Visual Navigation (WVN), an online self-supervised learning system for visual traversability estimation. The system is able to continuously adapt from a short human demonstration in the field, only using onboard sensing and computing. One of the key ideas to achieve this is the use of high-dimensional features from pre-trained self-supervised models, which implicitly encode semantic information that massively simplifies the learning task. Further, the development of an online scheme for supervision generator enables concurrent training and inference of the learned model in the wild. We demonstrate our approach through diverse real-world deployments in forests, parks, and grasslands. Our system is able to bootstrap the traversable terrain segmentation in less than 5 min of in-field training time, enabling the robot to navigate in complex, previously unseen outdoor terrains. Code: https://bit.ly/498b0CV - Project page:https://bit.ly/3M6nMHH
Authors: Sara Kangaslahti, David Alvarez-Melis
Abstract: As large language models (LLMs) have gained popularity for a variety of use cases, making them adaptable and controllable has become increasingly important, especially for user-facing applications. While the existing literature on LLM adaptation primarily focuses on finding a model (or models) that optimizes a single predefined objective, here we focus on the challenging case where the model must dynamically adapt to diverse -- and often changing -- user preferences. For this, we leverage adaptation methods based on linear weight interpolation, casting them as continuous multi-domain interpolators that produce models with specific prescribed generation characteristics on-the-fly. Specifically, we use low-rank updates to fine-tune a base model to various different domains, yielding a set of anchor models with distinct generation profiles. Then, we use the weight updates of these anchor models to parametrize the entire (infinite) class of models contained within their convex hull. We empirically show that varying the interpolation weights yields predictable and consistent change in the model outputs with respect to all of the controlled attributes. We find that there is little entanglement between most attributes and identify and discuss the pairs of attributes for which this is not the case. Our results suggest that linearly interpolating between the weights of fine-tuned models facilitates predictable, fine-grained control of model outputs with respect to multiple stylistic characteristics simultaneously.
Authors: Thomas F Burns
Abstract: I introduce a novel associative memory model named Correlated Dense Associative Memory (CDAM), which integrates both auto- and hetero-association in a unified framework for continuous-valued memory patterns. Employing an arbitrary graph structure to semantically link memory patterns, CDAM is theoretically and numerically analysed, revealing four distinct dynamical modes: auto-association, narrow hetero-association, wide hetero-association, and neutral quiescence. Drawing inspiration from inhibitory modulation studies, I employ anti-Hebbian learning rules to control the range of hetero-association, extract multi-scale representations of community structures in graphs, and stabilise the recall of temporal sequences. Experimental demonstrations showcase CDAM's efficacy in handling real-world data, replicating a classical neuroscience experiment, performing image retrieval, and simulating arbitrary finite automata.
Authors: Tsendsuren Munkhdalai, Manaal Faruqui, Siddharth Gopal
Abstract: This work introduces an efficient method to scale Transformer-based Large Language Models (LLMs) to infinitely long inputs with bounded memory and computation. A key component in our proposed approach is a new attention technique dubbed Infini-attention. The Infini-attention incorporates a compressive memory into the vanilla attention mechanism and builds in both masked local attention and long-term linear attention mechanisms in a single Transformer block. We demonstrate the effectiveness of our approach on long-context language modeling benchmarks, 1M sequence length passkey context block retrieval and 500K length book summarization tasks with 1B and 8B LLMs. Our approach introduces minimal bounded memory parameters and enables fast streaming inference for LLMs.
Authors: Gianpaolo Alvari, Ersilia Vallefuoco, Melanie Cristofolini, Elio Salvadori, Marco Dianti, Alessia Moltani, Davide Dal Castello, Paola Venuti, Cesare Furlanello
Abstract: Virtual Reality (VR) has emerged as a promising tool for enhancing social skills and emotional well-being in individuals with Autism Spectrum Disorder (ASD). Through a technical exploration, this study employs a multiplayer serious gaming environment within VR, engaging 34 individuals diagnosed with ASD and employing high-precision biosensors for a comprehensive view of the participants' arousal and responses during the VR sessions. Participants were subjected to a series of 3 virtual scenarios designed in collaboration with stakeholders and clinical experts to promote socio-cognitive skills and emotional regulation in a controlled and structured virtual environment. We combined the framework with wearable non-invasive sensors for bio-signal acquisition, focusing on the collection of heart rate variability, and respiratory patterns to monitor participants behaviors. Further, behavioral assessments were conducted using observation and semi-structured interviews, with the data analyzed in conjunction with physiological measures to identify correlations and explore digital-intervention efficacy. Preliminary analysis revealed significant correlations between physiological responses and behavioral outcomes, indicating the potential of physiological feedback to enhance VR-based interventions for ASD. The study demonstrated the feasibility of using real-time data to adapt virtual scenarios, suggesting a promising avenue to support personalized therapy. The integration of quantitative physiological feedback into digital platforms represents a forward step in the personalized intervention for ASD. By leveraging real-time data to adjust therapeutic content, this approach promises to enhance the efficacy and engagement of digital-based therapies.
Authors: Steve Rhyner, Haocong Luo, Juan G\'omez-Luna, Mohammad Sadrosadati, Jiawei Jiang, Ataberk Olgun, Harshita Gupta, Ce Zhang, Onur Mutlu
Abstract: Machine Learning (ML) training on large-scale datasets is a very expensive and time-consuming workload. Processor-centric architectures (e.g., CPU, GPU) commonly used for modern ML training workloads are limited by the data movement bottleneck, i.e., due to repeatedly accessing the training dataset. As a result, processor-centric systems suffer from performance degradation and high energy consumption. Processing-In-Memory (PIM) is a promising solution to alleviate the data movement bottleneck by placing the computation mechanisms inside or near memory. Our goal is to understand the capabilities and characteristics of popular distributed optimization algorithms on real-world PIM architectures to accelerate data-intensive ML training workloads. To this end, we 1) implement several representative centralized distributed optimization algorithms on UPMEM's real-world general-purpose PIM system, 2) rigorously evaluate these algorithms for ML training on large-scale datasets in terms of performance, accuracy, and scalability, 3) compare to conventional CPU and GPU baselines, and 4) discuss implications for future PIM hardware and the need to shift to an algorithm-hardware codesign perspective to accommodate decentralized distributed optimization algorithms. Our results demonstrate three major findings: 1) Modern general-purpose PIM architectures can be a viable alternative to state-of-the-art CPUs and GPUs for many memory-bound ML training workloads, when operations and datatypes are natively supported by PIM hardware, 2) the importance of carefully choosing the optimization algorithm that best fit PIM, and 3) contrary to popular belief, contemporary PIM architectures do not scale approximately linearly with the number of nodes for many data-intensive ML training workloads. To facilitate future research, we aim to open-source our complete codebase.
Authors: Saeid Tizpaz-Niari, Sriram Sankaranarayanan
Abstract: This paper leverages the statistics of extreme values to predict the worst-case convergence times of machine learning algorithms. Timing is a critical non-functional property of ML systems, and providing the worst-case converge times is essential to guarantee the availability of ML and its services. However, timing properties such as worst-case convergence times (WCCT) are difficult to verify since (1) they are not encoded in the syntax or semantics of underlying programming languages of AI, (2) their evaluations depend on both algorithmic implementations and underlying systems, and (3) their measurements involve uncertainty and noise. Therefore, prevalent formal methods and statistical models fail to provide rich information on the amounts and likelihood of WCCT. Our key observation is that the timing information we seek represents the extreme tail of execution times. Therefore, extreme value theory (EVT), a statistical discipline that focuses on understanding and predicting the distribution of extreme values in the tail of outcomes, provides an ideal framework to model and analyze WCCT in the training and inference phases of ML paradigm. Building upon the mathematical tools from EVT, we propose a practical framework to predict the worst-case timing properties of ML. Over a set of linear ML training algorithms, we show that EVT achieves a better accuracy for predicting WCCTs than relevant statistical methods such as the Bayesian factor. On the set of larger machine learning training algorithms and deep neural network inference, we show the feasibility and usefulness of EVT models to accurately predict WCCTs, their expected return periods, and their likelihood.
Authors: Sheng Gong, Yumin Zhang, Zhenliang Mu, Zhichen Pu, Hongyi Wang, Zhiao Yu, Mengyi Chen, Tianze Zheng, Zhi Wang, Lifei Chen, Xiaojie Wu, Shaochen Shi, Weihao Gao, Wen Yan, Liang Xiang
Abstract: Despite the widespread applications of machine learning force field (MLFF) on solids and small molecules, there is a notable gap in applying MLFF to complex liquid electrolytes. In this work, we introduce BAMBOO (ByteDance AI Molecular Simulation Booster), a novel framework for molecular dynamics (MD) simulations, with a demonstration of its capabilities in the context of liquid electrolytes for lithium batteries. We design a physics-inspired graph equivariant transformer architecture as the backbone of BAMBOO to learn from quantum mechanical simulations. Additionally, we pioneer an ensemble knowledge distillation approach and apply it on MLFFs to improve the stability of MD simulations. Finally, we propose the density alignment algorithm to align BAMBOO with experimental measurements. BAMBOO demonstrates state-of-the-art accuracy in predicting key electrolyte properties such as density, viscosity, and ionic conductivity across various solvents and salt combinations. Our current model, trained on more than 15 chemical species, achieves the average density error of 0.01 g/cm^3 on various compositions compared with experimental data. Moreover, our model demonstrates transferability to molecules not included in the quantum mechanical dataset. We envision this work as paving the way to a ''universal MLFF'' capable of simulating properties of common organic liquids.
Authors: Zohre Karimi, Shing-Hei Ho, Bao Thach, Alan Kuntz, Daniel S. Brown
Abstract: Automating robotic surgery via learning from demonstration (LfD) techniques is extremely challenging. This is because surgical tasks often involve sequential decision-making processes with complex interactions of physical objects and have low tolerance for mistakes. Prior works assume that all demonstrations are fully observable and optimal, which might not be practical in the real world. This paper introduces a sample-efficient method that learns a robust reward function from a limited amount of ranked suboptimal demonstrations consisting of partial-view point cloud observations. The method then learns a policy by optimizing the learned reward function using reinforcement learning (RL). We show that using a learned reward function to obtain a policy is more robust than pure imitation learning. We apply our approach on a physical surgical electrocautery task and demonstrate that our method can perform well even when the provided demonstrations are suboptimal and the observations are high-dimensional point clouds.
Authors: Mikhail Galkin, Jincheng Zhou, Bruno Ribeiro, Jian Tang, Zhaocheng Zhu
Abstract: Complex logical query answering (CLQA) in knowledge graphs (KGs) goes beyond simple KG completion and aims at answering compositional queries comprised of multiple projections and logical operations. Existing CLQA methods that learn parameters bound to certain entity or relation vocabularies can only be applied to the graph they are trained on which requires substantial training time before being deployed on a new graph. Here we present UltraQuery, an inductive reasoning model that can zero-shot answer logical queries on any KG. The core idea of UltraQuery is to derive both projections and logical operations as vocabulary-independent functions which generalize to new entities and relations in any KG. With the projection operation initialized from a pre-trained inductive KG reasoning model, UltraQuery can solve CLQA on any KG even if it is only finetuned on a single dataset. Experimenting on 23 datasets, UltraQuery in the zero-shot inference mode shows competitive or better query answering performance than best available baselines and sets a new state of the art on 14 of them.
Authors: Jaidev Shriram, Alex Trevithick, Lingjie Liu, Ravi Ramamoorthi
Abstract: We introduce RealmDreamer, a technique for generation of general forward-facing 3D scenes from text descriptions. Our technique optimizes a 3D Gaussian Splatting representation to match complex text prompts. We initialize these splats by utilizing the state-of-the-art text-to-image generators, lifting their samples into 3D, and computing the occlusion volume. We then optimize this representation across multiple views as a 3D inpainting task with image-conditional diffusion models. To learn correct geometric structure, we incorporate a depth diffusion model by conditioning on the samples from the inpainting model, giving rich geometric structure. Finally, we finetune the model using sharpened samples from image generators. Notably, our technique does not require video or multi-view data and can synthesize a variety of high-quality 3D scenes in different styles, consisting of multiple objects. Its generality additionally allows 3D synthesis from a single image.
Authors: O\u{g}uzhan Fatih Kar, Alessio Tonioni, Petra Poklukar, Achin Kulshrestha, Amir Zamir, Federico Tombari
Abstract: Vision-language models (VLMs) are typically composed of a vision encoder, e.g. CLIP, and a language model (LM) that interprets the encoded features to solve downstream tasks. Despite remarkable progress, VLMs are subject to several shortcomings due to the limited capabilities of vision encoders, e.g. "blindness" to certain image features, visual hallucination, etc. To address these issues, we study broadening the visual encoding capabilities of VLMs. We first comprehensively benchmark several vision encoders with different inductive biases for solving VLM tasks. We observe that there is no single encoding configuration that consistently achieves top performance across different tasks, and encoders with different biases can perform surprisingly similarly. Motivated by this, we introduce a method, named BRAVE, that consolidates features from multiple frozen encoders into a more versatile representation that can be directly fed as the input to a frozen LM. BRAVE achieves state-of-the-art performance on a broad range of captioning and VQA benchmarks and significantly reduces the aforementioned issues of VLMs, while requiring a smaller number of trainable parameters than existing methods and having a more compressed representation. Our results highlight the potential of incorporating different visual biases for a more broad and contextualized visual understanding of VLMs.
Authors: Zewei Zhang, Huan Liu, Jun Chen, Xiangyu Xu
Abstract: In this paper, we introduce GoodDrag, a novel approach to improve the stability and image quality of drag editing. Unlike existing methods that struggle with accumulated perturbations and often result in distortions, GoodDrag introduces an AlDD framework that alternates between drag and denoising operations within the diffusion process, effectively improving the fidelity of the result. We also propose an information-preserving motion supervision operation that maintains the original features of the starting point for precise manipulation and artifact reduction. In addition, we contribute to the benchmarking of drag editing by introducing a new dataset, Drag100, and developing dedicated quality assessment metrics, Dragging Accuracy Index and Gemini Score, utilizing Large Multimodal Models. Extensive experiments demonstrate that the proposed GoodDrag compares favorably against the state-of-the-art approaches both qualitatively and quantitatively. The project page is https://gooddrag.github.io.
Authors: Dedi Wang, Yihang Wang, Luke Evans, Pratyush Tiwary
Abstract: While representation learning has been central to the rise of machine learning and artificial intelligence, a key problem remains in making the learned representations meaningful. For this, the typical approach is to regularize the learned representation through prior probability distributions. However, such priors are usually unavailable or are ad hoc. To deal with this, recent efforts have shifted towards leveraging the insights from physical principles to guide the learning process. In this spirit, we propose a purely dynamics-constrained representation learning framework. Instead of relying on predefined probabilities, we restrict the latent representation to follow overdamped Langevin dynamics with a learnable transition density - a prior driven by statistical mechanics. We show this is a more natural constraint for representation learning in stochastic dynamical systems, with the crucial ability to uniquely identify the ground truth representation. We validate our framework for different systems including a real-world fluorescent DNA movie dataset. We show that our algorithm can uniquely identify orthogonal, isometric and meaningful latent representations.
Authors: Taoran Fang, Yunchao Zhang, Yang Yang, Chunping Wang, Lei Chen
Abstract: In recent years, prompt tuning has sparked a research surge in adapting pre-trained models. Unlike the unified pre-training strategy employed in the language field, the graph field exhibits diverse pre-training strategies, posing challenges in designing appropriate prompt-based tuning methods for graph neural networks. While some pioneering work has devised specialized prompting functions for models that employ edge prediction as their pre-training tasks, these methods are limited to specific pre-trained GNN models and lack broader applicability. In this paper, we introduce a universal prompt-based tuning method called Graph Prompt Feature (GPF) for pre-trained GNN models under any pre-training strategy. GPF operates on the input graph's feature space and can theoretically achieve an equivalent effect to any form of prompting function. Consequently, we no longer need to illustrate the prompting function corresponding to each pre-training strategy explicitly. Instead, we employ GPF to obtain the prompted graph for the downstream task in an adaptive manner. We provide rigorous derivations to demonstrate the universality of GPF and make guarantee of its effectiveness. The experimental results under various pre-training strategies indicate that our method performs better than fine-tuning, with an average improvement of about 1.4% in full-shot scenarios and about 3.2% in few-shot scenarios. Moreover, our method significantly outperforms existing specialized prompt-based tuning methods when applied to models utilizing the pre-training strategy they specialize in. These numerous advantages position our method as a compelling alternative to fine-tuning for downstream adaptations.
Authors: Darius Muglich, Christian Schroeder de Witt, Elise van der Pol, Shimon Whiteson, Jakob Foerster
Abstract: Successful coordination in Dec-POMDPs requires agents to adopt robust strategies and interpretable styles of play for their partner. A common failure mode is symmetry breaking, when agents arbitrarily converge on one out of many equivalent but mutually incompatible policies. Commonly these examples include partial observability, e.g. waving your right hand vs. left hand to convey a covert message. In this paper, we present a novel equivariant network architecture for use in Dec-POMDPs that effectively leverages environmental symmetry for improving zero-shot coordination, doing so more effectively than prior methods. Our method also acts as a ``coordination-improvement operator'' for generic, pre-trained policies, and thus may be applied at test-time in conjunction with any self-play algorithm. We provide theoretical guarantees of our work and test on the AI benchmark task of Hanabi, where we demonstrate our methods outperforming other symmetry-aware baselines in zero-shot coordination, as well as able to improve the coordination ability of a variety of pre-trained policies. In particular, we show our method can be used to improve on the state of the art for zero-shot coordination on the Hanabi benchmark.
Authors: Fan Mo, Mohammad Malekzadeh, Soumyajit Chatterjee, Fahim Kawsar, Akhil Mathur
Abstract: Federated learning (FL) in multidevice environments creates new opportunities to learn from a vast and diverse amount of private data. Although personal devices capture valuable data, their memory, computing, connectivity, and battery resources are often limited. Since deep neural networks (DNNs) are the typical machine learning models employed in FL, there are demands for integrating ubiquitous constrained devices into the training process of DNNs. In this paper, we develop an FL framework to incorporate on-device data selection on such constrained devices, which allows partition-based training of a DNN through collaboration between constrained devices and resourceful devices of the same client. Evaluations on five benchmark DNNs and six benchmark datasets across different modalities show that, on average, our framework achieves ~19% higher accuracy and ~58% lower latency; compared to the baseline FL without our implemented strategies. We demonstrate the effectiveness of our FL framework when dealing with imbalanced data, client participation heterogeneity, and various mobility patterns. As a benchmark for the community, our code is available at https://github.com/dr-bell/data-centric-federated-learning
URLs: https://github.com/dr-bell/data-centric-federated-learning
Authors: Pattarawat Chormai, Jan Herrmann, Klaus-Robert M\"uller, Gr\'egoire Montavon
Abstract: Explainable AI aims to overcome the black-box nature of complex ML models like neural networks by generating explanations for their predictions. Explanations often take the form of a heatmap identifying input features (e.g. pixels) that are relevant to the model's decision. These explanations, however, entangle the potentially multiple factors that enter into the overall complex decision strategy. We propose to disentangle explanations by extracting at some intermediate layer of a neural network, subspaces that capture the multiple and distinct activation patterns (e.g. visual concepts) that are relevant to the prediction. To automatically extract these subspaces, we propose two new analyses, extending principles found in PCA or ICA to explanations. These novel analyses, which we call principal relevant component analysis (PRCA) and disentangled relevant subspace analysis (DRSA), maximize relevance instead of e.g. variance or kurtosis. This allows for a much stronger focus of the analysis on what the ML model actually uses for predicting, ignoring activations or concepts to which the model is invariant. Our approach is general enough to work alongside common attribution techniques such as Shapley Value, Integrated Gradients, or LRP. Our proposed methods show to be practically useful and compare favorably to the state of the art as demonstrated on benchmarks and three use cases.
Authors: Yuhta Takida, Masaaki Imaizumi, Takashi Shibuya, Chieh-Hsin Lai, Toshimitsu Uesaka, Naoki Murata, Yuki Mitsufuji
Abstract: Generative adversarial networks (GANs) learn a target probability distribution by optimizing a generator and a discriminator with minimax objectives. This paper addresses the question of whether such optimization actually provides the generator with gradients that make its distribution close to the target distribution. We derive metrizable conditions, sufficient conditions for the discriminator to serve as the distance between the distributions by connecting the GAN formulation with the concept of sliced optimal transport. Furthermore, by leveraging these theoretical results, we propose a novel GAN training scheme, called slicing adversarial network (SAN). With only simple modifications, a broad class of existing GANs can be converted to SANs. Experiments on synthetic and image datasets support our theoretical results and the SAN's effectiveness as compared to usual GANs. Furthermore, we also apply SAN to StyleGAN-XL, which leads to state-of-the-art FID score amongst GANs for class conditional generation on ImageNet 256$\times$256. Our implementation is available on https://ytakida.github.io/san.
Authors: Ekaterina Gracheva
Abstract: In recent years, zero-cost metrics are gaining ground in neural architecture search (NAS). There metrics allow finding the optimal neural network for a given task faster and with a lesser computational load than conventional NAS methods. Equally important is that they also shed some light on the internal workings of neural architectures. This paper presents a zero-cost metric that highly correlated with the train set accuracy across the NAS-Bench-101, NAS-Bench-201 and NAS-Bench-NLP benchmark datasets. We evaluate a neural achitecture's potential based on the outputs' statistics after two constant shared weights initialisations. For this, we only use an unlabelled mini-batch of data. We observe that the dispersion of the outputs between two initialisations positively correlates with trained accuracy. The correlation further improves when we normalise dispersion by average output magnitude. The resulting metric, epsilon, does not require gradients computation and unbinds the NAS procedure from training hyperparameters, loss metrics and human-labelled data. Our method is easy to integrate within existing NAS algorithms and takes a fraction of a second to evaluate a single network. The code supporting this study can be found on GitHub at https://github.com/egracheva/epsinas.
Authors: Yizhou Wang, Dongliang Guo, Sheng Li, Octavia Camps, Yun Fu
Abstract: Anomaly detection and localization of visual data, including images and videos, are of great significance in both machine learning academia and applied real-world scenarios. Despite the rapid development of visual anomaly detection techniques in recent years, the interpretations of these black-box models and reasonable explanations of why anomalies can be distinguished out are scarce. This paper provides the first survey concentrated on explainable visual anomaly detection methods. We first introduce the basic background of image-level and video-level anomaly detection. Then, as the main content of this survey, a comprehensive and exhaustive literature review of explainable anomaly detection methods for both images and videos is presented. Next, we analyze why some explainable anomaly detection methods can be applied to both images and videos and why others can be only applied to one modality. Additionally, we provide summaries of current 2D visual anomaly detection datasets and evaluation metrics. Finally, we discuss several promising future directions and open problems to explore the explainability of 2D visual anomaly detection. The related resource collection is given at https://github.com/wyzjack/Awesome-XAD.
Authors: Shantanu Gupta, David Childers, Zachary C. Lipton
Abstract: Even when the causal graph underlying our data is unknown, we can use observational data to narrow down the possible values that an average treatment effect (ATE) can take by (1) identifying the graph up to a Markov equivalence class; and (2) estimating that ATE for each graph in the class. While the PC algorithm can identify this class under strong faithfulness assumptions, it can be computationally prohibitive. Fortunately, only the local graph structure around the treatment is required to identify the set of possible ATE values, a fact exploited by local discovery algorithms to improve computational efficiency. In this paper, we introduce Local Discovery using Eager Collider Checks (LDECC), a new local causal discovery algorithm that leverages unshielded colliders to orient the treatment's parents differently from existing methods. We show that there exist graphs where LDECC exponentially outperforms existing local discovery algorithms and vice versa. Moreover, we show that LDECC and existing algorithms rely on different faithfulness assumptions, leveraging this insight to weaken the assumptions for identifying the set of possible ATE values.
Authors: Wenchong He, Zhe Jiang
Abstract: Deep neural networks (DNNs) have achieved tremendous success in making accurate predictions for computer vision, natural language processing, as well as science and engineering domains. However, it is also well-recognized that DNNs sometimes make unexpected, incorrect, but overconfident predictions. This can cause serious consequences in high-stake applications, such as autonomous driving, medical diagnosis, and disaster response. Uncertainty quantification (UQ) aims to estimate the confidence of DNN predictions beyond prediction accuracy. In recent years, many UQ methods have been developed for DNNs. It is of great practical value to systematically categorize these UQ methods and compare their advantages and disadvantages. However, existing surveys mostly focus on categorizing UQ methodologies from a neural network architecture perspective or a Bayesian perspective and ignore the source of uncertainty that each methodology can incorporate, making it difficult to select an appropriate UQ method in practice. To fill the gap, this paper presents a systematic taxonomy of UQ methods for DNNs based on the types of uncertainty sources (data uncertainty versus model uncertainty). We summarize the advantages and disadvantages of methods in each category. We show how our taxonomy of UQ methodologies can potentially help guide the choice of UQ method in different machine learning problems (e.g., active learning, robustness, and reinforcement learning). We also identify current research gaps and propose several future research directions.
Authors: Haiquan Qiu, Yongqi Zhang, Yong Li, Quanming Yao
Abstract: Rule learning is critical to improving knowledge graph (KG) reasoning due to their ability to provide logical and interpretable explanations. Recently, Graph Neural Networks (GNNs) with tail entity scoring achieve the state-of-the-art performance on KG reasoning. However, the theoretical understandings for these GNNs are either lacking or focusing on single-relational graphs, leaving what the kind of rules these GNNs can learn an open problem. We propose to fill the above gap in this paper. Specifically, GNNs with tail entity scoring are unified into a common framework. Then, we analyze their expressivity by formally describing the rule structures they can learn and theoretically demonstrating their superiority. These results further inspire us to propose a novel labeling strategy to learn more rules in KG reasoning. Experimental results are consistent with our theoretical findings and verify the effectiveness of our proposed method. The code is publicly available at https://github.com/LARS-research/Rule-learning-expressivity.
URLs: https://github.com/LARS-research/Rule-learning-expressivity.
Authors: Fan Dong, Ali Abbasi, Steve Drew, Henry Leung, Xin Wang, Jiayu Zhou
Abstract: Federated learning offers a promising approach under the constraints of networking and data privacy constraints in aerial and space networks (ASNs), utilizing large-scale private edge data from drones, balloons, and satellites. Existing research has extensively studied the optimization of the learning process, computing efficiency, and communication overhead. An important yet often overlooked aspect is that participants contribute predictive knowledge with varying diversity of knowledge, affecting the quality of the learned federated models. In this paper, we propose a novel approach to address this issue by introducing a Weighted Averaging and Client Selection (WeiAvgCS) framework that emphasizes updates from high-diversity clients and diminishes the influence of those from low-diversity clients. Direct sharing of the data distribution may be prohibitive due to the additional private information that is sent from the clients. As such, we introduce an estimation for the diversity using a projection-based method. Extensive experiments have been performed to show WeiAvgCS's effectiveness. WeiAvgCS could converge 46% faster on FashionMNIST and 38% faster on CIFAR10 than its benchmarks on average in our experiments.
Authors: Shibhansh Dohare, J. Fernando Hernandez-Garcia, Parash Rahman, A. Rupam Mahmood, Richard S. Sutton
Abstract: Modern deep-learning systems are specialized to problem settings in which training occurs once and then never again, as opposed to continual-learning settings in which training occurs continually. If deep-learning systems are applied in a continual learning setting, then it is well known that they may fail to remember earlier examples. More fundamental, but less well known, is that they may also lose their ability to learn on new examples, a phenomenon called loss of plasticity. We provide direct demonstrations of loss of plasticity using the MNIST and ImageNet datasets repurposed for continual learning as sequences of tasks. In ImageNet, binary classification performance dropped from 89% accuracy on an early task down to 77%, about the level of a linear network, on the 2000th task. Loss of plasticity occurred with a wide range of deep network architectures, optimizers, activation functions, batch normalization, dropout, but was substantially eased by L2-regularization, particularly when combined with weight perturbation. Further, we introduce a new algorithm -- continual backpropagation -- which slightly modifies conventional backpropagation to reinitialize a small fraction of less-used units after each example and appears to maintain plasticity indefinitely.
Authors: Ming Chen, Sareh Nabi, Marciano Siniscalchi
Abstract: Contemporary real-world online ad auctions differ from canonical models [Edelman et al., 2007; Varian, 2009] in at least four ways: (1) values and click-through rates can depend upon users' search queries, but advertisers can only partially "tune" their bids to specific queries; (2) advertisers do not know the number, identity, and precise value distribution of competing bidders; (3) advertisers only receive partial, aggregated feedback, and (4) payment rules are only partially known to bidders. These features make it virtually impossible to fully characterize equilibrium bidding behavior. This paper shows that, nevertheless, one can still gain useful insight into modern ad auctions by modeling advertisers as agents governed by an adversarial bandit algorithm, independent of auction mechanism intricacies. To demonstrate our approach, we first simulate "soft-floor" auctions [Zeithammer, 2019], a complex, real-world pricing rule for which no complete equilibrium characterization is known. We find that (i) when values and click-through rates are query-dependent, soft floors can improve revenues relative to standard auction formats even if bidder types are drawn from the same distribution; and (ii) with distributional asymmetries that reflect relevant real-world scenario, we find that soft floors yield lower revenues than suitably chosen reserve prices, even restricting attention to a single query. We then demonstrate how to infer advertiser value distributions from observed bids for a variety of pricing rules, and illustrate our approach with aggregate data from an e-commerce website.
Authors: Guoyizhe Wei, Feng Wang, Anshul Shah, Rama Chellappa
Abstract: Federated learning is a distributed machine learning paradigm that allows multiple clients to collaboratively train a shared model with their local data. Nonetheless, conventional federated learning algorithms often struggle to generalize well due to the ubiquitous domain shift across clients. In this work, we consider a challenging yet realistic federated learning scenario where the training data of each client originates from different domains. We address the challenges of domain shift by leveraging the technique of prompt learning, and propose a novel method called Federated Dual Prompt Tuning (Fed-DPT). Specifically, Fed-DPT employs a pre-trained vision-language model and then applies both visual and textual prompt tuning to facilitate domain adaptation over decentralized data. Extensive experiments of Fed-DPT demonstrate its significant effectiveness in domain-aware federated learning. With a pre-trained CLIP model (ViT-Base as image encoder), the proposed Fed-DPT attains 68.4% average accuracy over six domains in the DomainNet dataset, which improves the original CLIP by a large margin of 14.8%.
Authors: Maarten Buyl, MaryBeth Defrance, Tijl De Bie
Abstract: Current fairness toolkits in machine learning only admit a limited range of fairness definitions and have seen little integration with automatic differentiation libraries, despite the central role these libraries play in modern machine learning pipelines. We introduce a framework of fairness regularization terms (fairrets) which quantify bias as modular, flexible objectives that are easily integrated in automatic differentiation pipelines. By employing a general definition of fairness in terms of linear-fractional statistics, a wide class of fairrets can be computed efficiently. Experiments show the behavior of their gradients and their utility in enforcing fairness with minimal loss of predictive power compared to baselines. Our contribution includes a PyTorch implementation of the fairret framework.
Authors: Boumediene Hamzi, Marcus Hutter, Houman Owhadi
Abstract: Machine Learning (ML) and Algorithmic Information Theory (AIT) look at Complexity from different points of view. We explore the interface between AIT and Kernel Methods (that are prevalent in ML) by adopting an AIT perspective on the problem of learning kernels from data, in kernel ridge regression, through the method of Sparse Kernel Flows. In particular, by looking at the differences and commonalities between Minimal Description Length (MDL) and Regularization in Machine Learning (RML), we prove that the method of Sparse Kernel Flows is the natural approach to adopt to learn kernels from data. This approach aligns naturally with the MDL principle, offering a more robust theoretical basis than the existing reliance on cross-validation. The study reveals that deriving Sparse Kernel Flows does not require a statistical approach; instead, one can directly engage with code-lengths and complexities, concepts central to AIT. Thereby, this approach opens the door to reformulating algorithms in machine learning using tools from AIT, with the aim of providing them a more solid theoretical foundation.
Authors: Thomas Chen
Abstract: We consider the scenario of supervised learning in Deep Learning (DL) networks, and exploit the arbitrariness of choice in the Riemannian metric relative to which the gradient descent flow can be defined (a general fact of differential geometry). In the standard approach to DL, the gradient flow on the space of parameters (weights and biases) is defined with respect to the Euclidean metric. Here instead, we choose the gradient flow with respect to the Euclidean metric in the output layer of the DL network. This naturally induces two modified versions of the gradient descent flow in the parameter space, one adapted for the overparametrized setting, and the other for the underparametrized setting. In the overparametrized case, we prove that, provided that a rank condition holds, all orbits of the modified gradient descent drive the ${\mathcal L}^2$ cost to its global minimum at a uniform exponential convergence rate; one thereby obtains an a priori stopping time for any prescribed proximity to the global minimum. We point out relations of the latter to sub-Riemannian geometry. Moreover, we generalize the above framework to the situation in which the rank condition does not hold; in particular, we show that local equilibria can only exist if a rank loss occurs, and that generically, they are not isolated points, but elements of a critical submanifold of parameter space.
Authors: Lanxin Zhang, Yongqi Dong, Haneen Farah, Arkady Zgonnikov, Bart van Arem
Abstract: Detecting abnormal driving behavior is critical for road traffic safety and the evaluation of drivers' behavior. With the advancement of machine learning (ML) algorithms and the accumulation of naturalistic driving data, many ML models have been adopted for abnormal driving behavior detection. Most existing ML-based detectors rely on (fully) supervised ML methods, which require substantial labeled data. However, ground truth labels are not always available in the real world, and labeling large amounts of data is tedious. Thus, there is a need to explore unsupervised or semi-supervised methods to make the anomaly detection process more feasible and efficient. To fill this research gap, this study analyzes large-scale real-world data revealing several abnormal driving behaviors (e.g., sudden acceleration, rapid lane-changing) and develops a Hierarchical Extreme Learning Machines (HELM) based semi-supervised ML method using partly labeled data to accurately detect the identified abnormal driving behaviors. Moreover, previous ML-based approaches predominantly utilize basic vehicle motion features (such as velocity and acceleration) to label and detect abnormal driving behaviors, while this study seeks to introduce Surrogate Safety Measures (SSMs) as the input features for ML models to improve the detection performance. Results from extensive experiments demonstrate the effectiveness of the proposed semi-supervised ML model with the introduced SSMs serving as important features. The proposed semi-supervised ML method outperforms other baseline semi-supervised or unsupervised methods regarding various metrics, e.g., delivering the best accuracy at 99.58% and the best F-1 measure at 0.9913. The ablation study further highlights the significance of SSMs for advancing detection performance.
Authors: No\"el Vouitsis, Zhaoyan Liu, Satya Krishna Gorti, Valentin Villecroze, Jesse C. Cresswell, Guangwei Yu, Gabriel Loaiza-Ganem, Maksims Volkovs
Abstract: The goal of multimodal alignment is to learn a single latent space that is shared between multimodal inputs. The most powerful models in this space have been trained using massive datasets of paired inputs and large-scale computational resources, making them prohibitively expensive to train in many practical scenarios. We surmise that existing unimodal encoders pre-trained on large amounts of unimodal data should provide an effective bootstrap to create multimodal models from unimodal ones at much lower costs. We therefore propose FuseMix, a multimodal augmentation scheme that operates on the latent spaces of arbitrary pre-trained unimodal encoders. Using FuseMix for multimodal alignment, we achieve competitive performance -- and in certain cases outperform state-of-the art methods -- in both image-text and audio-text retrieval, with orders of magnitude less compute and data: for example, we outperform CLIP on the Flickr30K text-to-image retrieval task with $\sim \! 600\times$ fewer GPU days and $\sim \! 80\times$ fewer image-text pairs. Additionally, we show how our method can be applied to convert pre-trained text-to-image generative models into audio-to-image ones. Code is available at: https://github.com/layer6ai-labs/fusemix.
Authors: Guojian Wang, Faguo Wu, Xiao Zhang, Tianyuan Chen, Zhiming Zheng
Abstract: The sparsity of reward feedback remains a challenging problem in online deep reinforcement learning (DRL). Previous approaches have utilized offline demonstrations to achieve impressive results in multiple hard tasks. However, these approaches place high demands on demonstration quality, and obtaining expert-like actions is often costly and unrealistic. To tackle these problems, we propose a simple and efficient algorithm called Policy Optimization with Smooth Guidance (POSG), which leverages a small set of state-only demonstrations (where only state information is included in demonstrations) to indirectly make approximate and feasible long-term credit assignments and facilitate exploration. Specifically, we first design a trajectory-importance evaluation mechanism to determine the quality of the current trajectory against demonstrations. Then, we introduce a guidance reward computation technology based on trajectory importance to measure the impact of each state-action pair. We theoretically analyze the performance improvement caused by smooth guidance rewards and derive a new worst-case lower bound on the performance improvement. Extensive results demonstrate POSG's significant advantages in control performance and convergence speed in four sparse-reward environments, including the grid-world maze, Hopper-v4, HalfCheetah-v4, and Ant maze. Notably, the specific metrics and quantifiable results are investigated to demonstrate the superiority of POSG.
Authors: Guojian Wang, Faguo Wu, Xiao Zhang
Abstract: Mastering deep reinforcement learning (DRL) proves challenging in tasks featuring scant rewards. These limited rewards merely signify whether the task is partially or entirely accomplished, necessitating various exploration actions before the agent garners meaningful feedback. Consequently, the majority of existing DRL exploration algorithms struggle to acquire practical policies within a reasonable timeframe. To address this challenge, we introduce an approach leveraging offline demonstration trajectories for swifter and more efficient online RL in environments with sparse rewards. Our pivotal insight involves treating offline demonstration trajectories as guidance, rather than mere imitation, allowing our method to learn a policy whose distribution of state-action visitation marginally matches that of offline demonstrations. We specifically introduce a novel trajectory distance relying on maximum mean discrepancy (MMD) and cast policy optimization as a distance-constrained optimization problem. We then illustrate that this optimization problem can be streamlined into a policy-gradient algorithm, integrating rewards shaped by insights from offline demonstrations. The proposed algorithm undergoes evaluation across extensive discrete and continuous control tasks with sparse and misleading rewards. The experimental findings demonstrate the significant superiority of our proposed algorithm over baseline methods concerning diverse exploration and the acquisition of an optimal policy.
Authors: Antonio Manjavacas, Alejandro Campoy-Nieves, Javier Jim\'enez-Raboso, Miguel Molina-Solana, Juan G\'omez-Romero
Abstract: Heating, Ventilation, and Air Conditioning (HVAC) systems are a major driver of energy consumption in commercial and residential buildings. Recent studies have shown that Deep Reinforcement Learning (DRL) algorithms can outperform traditional reactive controllers. However, DRL-based solutions are generally designed for ad hoc setups and lack standardization for comparison. To fill this gap, this paper provides a critical and reproducible evaluation, in terms of comfort and energy consumption, of several state-of-the-art DRL algorithms for HVAC control. The study examines the controllers' robustness, adaptability, and trade-off between optimization goals by using the Sinergym framework. The results obtained confirm the potential of DRL algorithms, such as SAC and TD3, in complex scenarios and reveal several challenges related to generalization and incremental learning.
Authors: Jiabin Lin, Shana Moothedath
Abstract: We present the problem of conservative distributed multi-task learning in stochastic linear contextual bandits with heterogeneous agents. This extends conservative linear bandits to a distributed setting where M agents tackle different but related tasks while adhering to stage-wise performance constraints. The exact context is unknown, and only a context distribution is available to the agents as in many practical applications that involve a prediction mechanism to infer context, such as stock market prediction and weather forecast. We propose a distributed upper confidence bound (UCB) algorithm, DiSC-UCB. Our algorithm constructs a pruned action set during each round to ensure the constraints are met. Additionally, it includes synchronized sharing of estimates among agents via a central server using well-structured synchronization steps. We prove the regret and communication bounds on the algorithm. We extend the problem to a setting where the agents are unaware of the baseline reward. For this setting, we provide a modified algorithm, DiSC-UCB2, and we show that the modified algorithm achieves the same regret and communication bounds. We empirically validated the performance of our algorithm on synthetic data and real-world Movielens-100K data.
Authors: Yatong Bai, Mo Zhou, Vishal M. Patel, Somayeh Sojoudi
Abstract: Adversarial robustness often comes at the cost of degraded accuracy, impeding the real-life application of robust classification models. Training-based solutions for better trade-offs are limited by incompatibilities with already-trained high-performance large models, necessitating the exploration of training-free ensemble approaches. Observing that robust models are more confident in correct predictions than in incorrect ones on clean and adversarial data alike, we speculate amplifying this "benign confidence property" can reconcile accuracy and robustness in an ensemble setting. To achieve so, we propose "MixedNUTS", a training-free method where the output logits of a robust classifier and a standard non-robust classifier are processed by nonlinear transformations with only three parameters, which are optimized through an efficient algorithm. MixedNUTS then converts the transformed logits into probabilities and mixes them as the overall output. On CIFAR-10, CIFAR-100, and ImageNet datasets, experimental results with custom strong adaptive attacks demonstrate MixedNUTS's vastly improved accuracy and near-SOTA robustness -- it boosts CIFAR-100 clean accuracy by 7.86 points, sacrificing merely 0.87 points in robust accuracy.
Authors: Kun Zhang, Shaoan Xie, Ignavier Ng, Yujia Zheng
Abstract: In many problems, the measured variables (e.g., image pixels) are just mathematical functions of the hidden causal variables (e.g., the underlying concepts or objects). For the purpose of making predictions in changing environments or making proper changes to the system, it is helpful to recover the hidden causal variables $Z_i$ and their causal relations represented by graph $\mathcal{G}_Z$. This problem has recently been known as causal representation learning. This paper is concerned with a general, completely nonparametric setting of causal representation learning from multiple distributions (arising from heterogeneous data or nonstationary time series), without assuming hard interventions behind distribution changes. We aim to develop general solutions in this fundamental case; as a by product, this helps see the unique benefit offered by other assumptions such as parametric causal models or hard interventions. We show that under the sparsity constraint on the recovered graph over the latent variables and suitable sufficient change conditions on the causal influences, interestingly, one can recover the moralized graph of the underlying directed acyclic graph, and the recovered latent variables and their relations are related to the underlying causal model in a specific, nontrivial way. In some cases, each latent variable can even be recovered up to component-wise transformations. Experimental results verify our theoretical claims.
Authors: Jared M. Ping, Ken J. Nixon
Abstract: Advances in Tiny Machine Learning (TinyML) have bolstered the creation of smart industry solutions, including smart agriculture, healthcare and smart cities. Whilst related research contributes to enabling TinyML solutions on constrained hardware, there is a need to amplify real-world applications by optimising energy consumption in battery-powered systems. The work presented extends and contributes to TinyML research by optimising battery-powered image-based anomaly detection Internet of Things (IoT) systems. Whilst previous work in this area has yielded the capabilities of on-device inferencing and training, there has yet to be an investigation into optimising the management of such capabilities using machine learning approaches, such as Reinforcement Learning (RL), to improve the deployment battery life of such systems. Using modelled simulations, the battery life effects of an RL algorithm are benchmarked against static and dynamic optimisation approaches, with the foundation laid for a hardware benchmark to follow. It is shown that using RL within a TinyML-enabled IoT system to optimise the system operations, including cloud anomaly processing and on-device training, yields an improved battery life of 22.86% and 10.86% compared to static and dynamic optimisation approaches respectively. The proposed solution can be deployed to resource-constrained hardware, given its low memory footprint of 800 B, which could be further reduced. This further facilitates the real-world deployment of such systems, including key sectors such as smart agriculture.
Authors: Alessio Benavoli, Dario Azzimonti
Abstract: Preference modelling lies at the intersection of economics, decision theory, machine learning and statistics. By understanding individuals' preferences and how they make choices, we can build products that closely match their expectations, paving the way for more efficient and personalised applications across a wide range of domains. The objective of this tutorial is to present a cohesive and comprehensive framework for preference learning with Gaussian Processes (GPs), demonstrating how to seamlessly incorporate rationality principles (from economics and decision theory) into the learning process. By suitably tailoring the likelihood function, this framework enables the construction of preference learning models that encompass random utility models, limits of discernment, and scenarios with multiple conflicting utilities for both object- and label-preference. This tutorial builds upon established research while simultaneously introducing some novel GP-based models to address specific gaps in the existing literature.
Authors: Xudong Sun, Nutan Chen, Alexej Gossmann, Yu Xing, Carla Feistner, Emilio Dorigatt, Felix Drost, Daniele Scarcella, Lisa Beer, Carsten Marr
Abstract: We address the online combinatorial choice of weight multipliers for multi-objective optimization of many loss terms parameterized by neural works via a probabilistic graphical model (PGM) for the joint model parameter and multiplier evolution process, with a hypervolume based likelihood promoting multi-objective descent. The corresponding parameter and multiplier estimation as a sequential decision process is then cast into an optimal control problem, where the multi-objective descent goal is dispatched hierarchically into a series of constraint optimization sub-problems. The subproblem constraint automatically adapts itself according to Pareto dominance and serves as the setpoint for the low level multiplier controller to schedule loss landscapes via output feedback of each loss term. Our method is multiplier-free and operates at the timescale of epochs, thus saves tremendous computational resources compared to full training cycle multiplier tuning. It also circumvents the excessive memory requirements and heavy computational burden of existing multi-objective deep learning methods. We applied it to domain invariant variational auto-encoding with 6 loss terms on the PACS domain generalization task, and observed robust performance across a range of controller hyperparameters, as well as different multiplier initial conditions, outperforming other multiplier scheduling methods. We offered modular implementation of our method, admitting extension to custom definition of many loss terms.
Authors: Mattia Jacopo Villani, Peter McBurney
Abstract: The transformer neural network has significantly out-shined all other neural network architectures as the engine behind large language models. We provide a theoretical analysis of the expressivity of the transformer architecture through the lens of topos theory. From this viewpoint, we show that many common neural network architectures, such as the convolutional, recurrent and graph convolutional networks, can be embedded in a pretopos of piecewise-linear functions, but that the transformer necessarily lives in its topos completion. In particular, this suggests that the two network families instantiate different fragments of logic: the former are first order, whereas transformers are higher-order reasoners. Furthermore, we draw parallels with architecture search and gradient descent, integrating our analysis in the framework of cybernetic agents.
Authors: Lucas Lingle
Abstract: Large neural network models have become a mainstay of natural language processing and computer vision, yet their initialization and learning rates are set in a largely heuristic fashion, potentially varying from paper to paper and one model size to the next. The $\mu$-Parameterization ($\mu$P) offers a potential solution to these challenges, yielding scaling rules for model initialization and learning rates, and reportedly enabling zero-shot hyperparameter transfer from small to large models in a variety of cases. Despite the evident promise, the $\mu$P scaling rules are not yet widely adopted, perhaps due to higher implementation complexity, many variations, or complex theoretical background. This work investigates $\mu$P empirically, focusing on the ubiquitous transformer architecture, and aims to answer a simple question: does $\mu$-Transfer yield optimal learning rates in practice? From models with 2M to 10B parameters, we show that $\mu$-Transfer works as intended for the majority of important cases, but also identify some surprising cases where it may not. Our experiment codebase is available at https://github.com/lucaslingle/mu_transformer/
Authors: Yixuan Sun, Ololade Sowunmi, Romain Egele, Sri Hari Krishna Narayanan, Luke Van Roekel, Prasanna Balaprakash
Abstract: Training an effective deep learning model to learn ocean processes involves careful choices of various hyperparameters. We leverage the advanced search algorithms for multiobjective optimization in DeepHyper, a scalable hyperparameter optimization software, to streamline the development of neural networks tailored for ocean modeling. The focus is on optimizing Fourier neural operators (FNOs), a data-driven model capable of simulating complex ocean behaviors. Selecting the correct model and tuning the hyperparameters are challenging tasks, requiring much effort to ensure model accuracy. DeepHyper allows efficient exploration of hyperparameters associated with data preprocessing, FNO architecture-related hyperparameters, and various model training strategies. We aim to obtain an optimal set of hyperparameters leading to the most performant model. Moreover, on top of the commonly used mean squared error for model training, we propose adopting the negative anomaly correlation coefficient as the additional loss term to improve model performance and investigate the potential trade-off between the two terms. The experimental results show that the optimal set of hyperparameters enhanced model performance in single timestepping forecasting and greatly exceeded the baseline configuration in the autoregressive rollout for long-horizon forecasting up to 30 days. Utilizing DeepHyper, we demonstrate an approach to enhance the use of FNOs in ocean dynamics forecasting, offering a scalable solution with improved precision.
Authors: Karim Abdel Sadek, Marek Elias
Abstract: ML-augmented algorithms utilize predictions to achieve performance beyond their worst-case bounds. Producing these predictions might be a costly operation -- this motivated Im et al. '22 to introduce the study of algorithms which use predictions parsimoniously. We design parsimonious algorithms for caching and MTS with action predictions, proposed by Antoniadis et al. '20, focusing on the parameters of consistency (performance with perfect predictions) and smoothness (dependence of their performance on the prediction error). Our algorithm for caching is 1-consistent, robust, and its smoothness deteriorates with the decreasing number of available predictions. We propose an algorithm for general MTS whose consistency and smoothness both scale linearly with the decreasing number of predictions. Without the restriction on the number of available predictions, both algorithms match the earlier guarantees achieved by Antoniadis et al. '20.
Authors: Zhuoqing Song, Lei Shi, Shi Pu, Ming Yan
Abstract: In this paper, we propose two communication efficient decentralized optimization algorithms over a general directed multi-agent network. The first algorithm, termed Compressed Push-Pull (CPP), combines the gradient tracking Push-Pull method with communication compression. We show that CPP is applicable to a general class of unbiased compression operators and achieves linear convergence rate for strongly convex and smooth objective functions. The second algorithm is a broadcast-like version of CPP (B-CPP), and it also achieves linear convergence rate under the same conditions on the objective functions. B-CPP can be applied in an asynchronous broadcast setting and further reduce communication costs compared to CPP. Numerical experiments complement the theoretical analysis and confirm the effectiveness of the proposed methods.
Authors: Micha Horlboge, Erwin Quiring, Roland Meyer, Konrad Rieck
Abstract: The source code of a program not only defines its semantics but also contains subtle clues that can identify its author. Several studies have shown that these clues can be automatically extracted using machine learning and allow for determining a program's author among hundreds of programmers. This attribution poses a significant threat to developers of anti-censorship and privacy-enhancing technologies, as they become identifiable and may be prosecuted. An ideal protection from this threat would be the anonymization of source code. However, neither theoretical nor practical principles of such an anonymization have been explored so far. In this paper, we tackle this problem and develop a framework for reasoning about code anonymization. We prove that the task of generating a $k$-anonymous program -- a program that cannot be attributed to one of $k$ authors -- is not computable in the general case. As a remedy, we introduce a relaxed concept called $k$-uncertainty, which enables us to measure the protection of developers. Based on this concept, we empirically study candidate techniques for anonymization, such as code normalization, coding style imitation, and code obfuscation. We find that none of the techniques provides sufficient protection when the attacker is aware of the anonymization. While we observe a notable reduction in attribution performance on real-world code, a reliable protection is not achieved for all developers. We conclude that code anonymization is a hard problem that requires further attention from the research community.
Authors: Yoichi Ishibashi, Sho Yokoi, Katsuhito Sudoh, Satoshi Nakamura
Abstract: In the field of natural language processing (NLP), continuous vector representations are crucial for capturing the semantic meanings of individual words. Yet, when it comes to the representations of sets of words, the conventional vector-based approaches often struggle with expressiveness and lack the essential set operations such as union, intersection, and complement. Inspired by quantum logic, we realize the representation of word sets and corresponding set operations within pre-trained word embedding spaces. By grounding our approach in the linear subspaces, we enable efficient computation of various set operations and facilitate the soft computation of membership functions within continuous spaces. Moreover, we allow for the computation of the F-score directly within word vectors, thereby establishing a direct link to the assessment of sentence similarity. In experiments with widely-used pre-trained embeddings and benchmarks, we show that our subspace-based set operations consistently outperform vector-based ones in both sentence similarity and set retrieval tasks.
Authors: Kaustav Chakraborty, Somil Bansal
Abstract: Machine learning driven image-based controllers allow robotic systems to take intelligent actions based on the visual feedback from their environment. Understanding when these controllers might lead to system safety violations is important for their integration in safety-critical applications and engineering corrective safety measures for the system. Existing methods leverage simulation-based testing (or falsification) to find the failures of vision-based controllers, i.e., the visual inputs that lead to closed-loop safety violations. However, these techniques do not scale well to the scenarios involving high-dimensional and complex visual inputs, such as RGB images. In this work, we cast the problem of finding closed-loop vision failures as a Hamilton-Jacobi (HJ) reachability problem. Our approach blends simulation-based analysis with HJ reachability methods to compute an approximation of the backward reachable tube (BRT) of the system, i.e., the set of unsafe states for the system under vision-based controllers. Utilizing the BRT, we can tractably and systematically find the system states and corresponding visual inputs that lead to closed-loop failures. These visual inputs can be subsequently analyzed to find the input characteristics that might have caused the failure. Besides its scalability to high-dimensional visual inputs, an explicit computation of BRT allows the proposed approach to capture non-trivial system failures that are difficult to expose via random simulations. We demonstrate our framework on two case studies involving an RGB image-based neural network controller for (a) autonomous indoor navigation, and (b) autonomous aircraft taxiing.
Authors: Danial Kamali, Joseph Romain, Huiyi Liu, Wei Peng, Jingbo Meng, Parisa Kordjamshidi
Abstract: Nowadays, the spread of misinformation is a prominent problem in society. Our research focuses on aiding the automatic identification of misinformation by analyzing the persuasive strategies employed in textual documents. We introduce a novel annotation scheme encompassing common persuasive writing tactics to achieve our objective. Additionally, we provide a dataset on health misinformation, thoroughly annotated by experts utilizing our proposed scheme. Our contribution includes proposing a new task of annotating pieces of text with their persuasive writing strategy types. We evaluate fine-tuning and prompt-engineering techniques with pre-trained language models of the BERT family and the generative large language models of the GPT family using persuasive strategies as an additional source of information. We evaluate the effects of employing persuasive strategies as intermediate labels in the context of misinformation detection. Our results show that those strategies enhance accuracy and improve the explainability of misinformation detection models. The persuasive strategies can serve as valuable insights and explanations, enabling other models or even humans to make more informed decisions regarding the trustworthiness of the information.
Authors: Maxim Freydin, Niv Sfaradi, Nimrod Segol, Areej Eweida, Barak Or
Abstract: Accurate alignment of a fixed mobile device equipped with inertial sensors inside a moving vehicle is important for navigation, activity recognition, and other applications. Accurate estimation of the device mounting angle is required to rotate the inertial measurement from the sensor frame to the moving platform frame to standardize measurements and improve the performance of the target task. In this work, a data-driven approach using deep neural networks (DNNs) is proposed to learn the yaw mounting angle of a smartphone equipped with an inertial measurement unit (IMU) and strapped to a car. The proposed model uses only the accelerometer and gyroscope readings from an IMU as input and, in contrast to existing solutions, does not require global position inputs from global navigation satellite systems (GNSS). To train the model in a supervised manner, IMU data is collected for training and validation with the sensor mounted at a known yaw mounting angle, and a range of ground truth labels is generated by applying a random rotation in a bounded range to the measurements. The trained model is tested on data with real rotations showing similar performance as with synthetic rotations. The trained model is deployed on an Android device and evaluated in real-time to test the accuracy of the estimated yaw mounting angle. The model is shown to find the mounting angle at an accuracy of 8 degrees within 5 seconds, and 4 degrees within 27 seconds. An experiment is conducted to compare the proposed model with an existing off-the-shelf solution.
Authors: Zander W. Blasingame, Chen Liu
Abstract: Face morphing attacks seek to deceive a Face Recognition (FR) system by presenting a morphed image consisting of the biometric qualities from two different identities with the aim of triggering a false acceptance with one of the two identities, thereby presenting a significant threat to biometric systems. The success of a morphing attack is dependent on the ability of the morphed image to represent the biometric characteristics of both identities that were used to create the image. We present a novel morphing attack that uses a Diffusion-based architecture to improve the visual fidelity of the image and the ability of the morphing attack to represent characteristics from both identities. We demonstrate the effectiveness of the proposed attack by evaluating its visual fidelity via the Frechet Inception Distance (FID). Also, extensive experiments are conducted to measure the vulnerability of FR systems to the proposed attack. The ability of a morphing attack detector to detect the proposed attack is measured and compared against two state-of-the-art GAN-based morphing attacks along with two Landmark-based attacks. Additionally, a novel metric to measure the relative strength between different morphing attacks is introduced and evaluated.
Authors: Nathan Huet, Stephan Cl\'emen\c{c}on, Anne Sabourin
Abstract: The statistical learning problem consists in building a predictive function $\hat{f}$ based on independent copies of $(X,Y)$ so that $Y$ is approximated by $\hat{f}(X)$ with minimum (squared) error. Motivated by various applications, special attention is paid here to the case of extreme (i.e. very large) observations $X$. Because of their rarity, the contributions of such observations to the (empirical) error is negligible, and the predictive performance of empirical risk minimizers can be consequently very poor in extreme regions. In this paper, we develop a general framework for regression on extremes. Under appropriate regular variation assumptions regarding the pair $(X,Y)$, we show that an asymptotic notion of risk can be tailored to summarize appropriately predictive performance in extreme regions. It is also proved that minimization of an empirical and nonasymptotic version of this 'extreme risk', based on a fraction of the largest observations solely, yields good generalization capacity. In addition, numerical results providing strong empirical evidence of the relevance of the approach proposed are displayed.
Authors: Yimeng Min, Yiwei Bai, Carla P. Gomes
Abstract: We propose UTSP, an unsupervised learning (UL) framework for solving the Travelling Salesman Problem (TSP). We train a Graph Neural Network (GNN) using a surrogate loss. The GNN outputs a heat map representing the probability for each edge to be part of the optimal path. We then apply local search to generate our final prediction based on the heat map. Our loss function consists of two parts: one pushes the model to find the shortest path and the other serves as a surrogate for the constraint that the route should form a Hamiltonian Cycle. Experimental results show that UTSP outperforms the existing data-driven TSP heuristics. Our approach is parameter efficient as well as data efficient: the model takes $\sim$ 10\% of the number of parameters and $\sim$ 0.2\% of training samples compared with reinforcement learning or supervised learning methods.
Authors: Chen Li, Yang Cao, Ye Zhu, Debo Cheng, Chengyuan Li, Yasuhiko Morimoto
Abstract: Using knowledge graphs to assist deep learning models in making recommendation decisions has recently been proven to effectively improve the model's interpretability and accuracy. This paper introduces an end-to-end deep learning model, named RKGCN, which dynamically analyses each user's preferences and makes a recommendation of suitable items. It combines knowledge graphs on both the item side and user side to enrich their representations to maximize the utilization of the abundant information in knowledge graphs. RKGCN is able to offer more personalized and relevant recommendations in three different scenarios. The experimental results show the superior effectiveness of our model over 5 baseline models on three real-world datasets including movies, books, and music.
Authors: Martin Aum\"uller, Christian Janos Lebeda, Boel Nelson, Rasmus Pagh
Abstract: Differentially private mean estimation is an important building block in privacy-preserving algorithms for data analysis and machine learning. Though the trade-off between privacy and utility is well understood in the worst case, many datasets exhibit structure that could potentially be exploited to yield better algorithms. In this paper we present $\textit{Private Limit Adapted Noise}$ (PLAN), a family of differentially private algorithms for mean estimation in the setting where inputs are independently sampled from a distribution $\mathcal{D}$ over $\mathbf{R}^d$, with coordinate-wise standard deviations $\boldsymbol{\sigma} \in \mathbf{R}^d$. Similar to mean estimation under Mahalanobis distance, PLAN tailors the shape of the noise to the shape of the data, but unlike previous algorithms the privacy budget is spent non-uniformly over the coordinates. Under a concentration assumption on $\mathcal{D}$, we show how to exploit skew in the vector $\boldsymbol{\sigma}$, obtaining a (zero-concentrated) differentially private mean estimate with $\ell_2$ error proportional to $\|\boldsymbol{\sigma}\|_1$. Previous work has either not taken $\boldsymbol{\sigma}$ into account, or measured error in Mahalanobis distance $\unicode{x2013}$ in both cases resulting in $\ell_2$ error proportional to $\sqrt{d}\|\boldsymbol{\sigma}\|_2$, which can be up to a factor $\sqrt{d}$ larger. To verify the effectiveness of PLAN, we empirically evaluate accuracy on both synthetic and real world data.
Authors: Ioannis Romanelis, Vlassis Fotis, Konstantinos Moustakas, Adrian Munteanu
Abstract: In this paper we delve into the properties of transformers, attained through self-supervision, in the point cloud domain. Specifically, we evaluate the effectiveness of Masked Autoencoding as a pretraining scheme, and explore Momentum Contrast as an alternative. In our study we investigate the impact of data quantity on the learned features, and uncover similarities in the transformer's behavior across domains. Through comprehensive visualiations, we observe that the transformer learns to attend to semantically meaningful regions, indicating that pretraining leads to a better understanding of the underlying geometry. Moreover, we examine the finetuning process and its effect on the learned representations. Based on that, we devise an unfreezing strategy which consistently outperforms our baseline without introducing any other modifications to the model or the training pipeline, and achieve state-of-the-art results in the classification task among transformer models.
Authors: S\"oren Christensen, Jan Kallsen
Abstract: In recent years, there has been an intense debate about how learning in biological neural networks (BNNs) differs from learning in artificial neural networks. It is often argued that the updating of connections in the brain relies only on local information, and therefore a stochastic gradient-descent type optimization method cannot be used. In this paper, we study a stochastic model for supervised learning in BNNs. We show that a (continuous) gradient step occurs approximately when each learning opportunity is processed by many local updates. This result suggests that stochastic gradient descent may indeed play a role in optimizing BNNs.
Authors: Samuel Holt, Max Ruiz Luyten, Mihaela van der Schaar
Abstract: Transformer-based large language models (LLMs) are constrained by the fixed context window of the underlying transformer architecture, hindering their ability to produce long and coherent outputs. Memory-augmented LLMs are a promising solution, but current approaches cannot handle long output generation tasks since they (1) only focus on reading memory and reduce its evolution to the concatenation of new memories or (2) use very specialized memories that cannot adapt to other domains. This paper presents L2MAC, the first practical LLM-based general-purpose stored-program automatic computer (von Neumann architecture) framework, an LLM-based multi-agent system, for long and consistent output generation. Its memory has two components: the instruction registry, which is populated with a prompt program to solve the user-given task, and a file store, which will contain the final and intermediate outputs. Each instruction in turn is executed by a separate LLM agent, whose context is managed by a control unit capable of precise memory reading and writing to ensure effective interaction with the file store. These components enable L2MAC to generate extensive outputs, bypassing the constraints of the finite context window while producing outputs that fulfill a complex user-specified task. We empirically demonstrate that L2MAC achieves state-of-the-art performance in generating large codebases for system design tasks, significantly outperforming other coding methods in implementing the detailed user-specified task; we show that L2MAC works for general-purpose extensive text-based tasks, such as writing an entire book; and we provide valuable insights into L2MAC's performance improvement over existing methods.
Authors: Weihao Xia, Raoul de Charette, Cengiz \"Oztireli, Jing-Hao Xue
Abstract: In this work we present DREAM, an fMRI-to-image method for reconstructing viewed images from brain activities, grounded on fundamental knowledge of the human visual system. We craft reverse pathways that emulate the hierarchical and parallel nature of how humans perceive the visual world. These tailored pathways are specialized to decipher semantics, color, and depth cues from fMRI data, mirroring the forward pathways from visual stimuli to fMRI recordings. To do so, two components mimic the inverse processes within the human visual system: the Reverse Visual Association Cortex (R-VAC) which reverses pathways of this brain region, extracting semantics from fMRI data; the Reverse Parallel PKM (R-PKM) component simultaneously predicting color and depth from fMRI signals. The experiments indicate that our method outperforms the current state-of-the-art models in terms of the consistency of appearance, structure, and semantics. Code will be made publicly available to facilitate further research in this field.
Authors: Zhiqing Sun, Yikang Shen, Hongxin Zhang, Qinhong Zhou, Zhenfang Chen, David Cox, Yiming Yang, Chuang Gan
Abstract: Supervised Fine-Tuning (SFT) on response demonstrations combined with Reinforcement Learning from Human Feedback (RLHF) constitutes a powerful paradigm for aligning LLM-based AI agents. However, a significant limitation of such an approach is its dependency on high-quality human annotations, making its application to intricate tasks challenging due to difficulties in obtaining consistent response demonstrations and in-distribution response preferences. This paper presents a novel approach, namely SALMON, to align base language models with minimal human supervision, using only a small set of human-defined principles, yet achieving superior performance. Central to our approach is an instructable reward model. Trained on synthetic preference data, this model can generate reward scores based on arbitrary human-defined principles. By merely adjusting these principles during the RL training phase, we gain full control over the preferences with the instructable reward model, subsequently influencing the behavior of the RL-trained policy models, and reducing the reliance on the collection of online human preferences. Applying our method to the LLaMA-2-70b base language model, we developed an AI assistant named Dromedary-2. With only 6 exemplars for in-context learning and 31 human-defined principles, Dromedary-2 significantly surpasses the performance of several state-of-the-art AI systems, including LLaMA-2-Chat-70b, on various benchmark datasets. We have open-sourced the code and model weights to encourage further research into aligning LLM-based AI agents with enhanced supervision efficiency, improved controllability, and scalable oversight.
Authors: Jeremy Goldwasser, Giles Hooker
Abstract: Shapley values are among the most popular tools for explaining predictions of blackbox machine learning models. However, their high computational cost motivates the use of sampling approximations, inducing a considerable degree of uncertainty. To stabilize these model explanations, we propose ControlSHAP, an approach based on the Monte Carlo technique of control variates. Our methodology is applicable to any machine learning model and requires virtually no extra computation or modeling effort. On several high-dimensional datasets, we find it can produce dramatic reductions in the Monte Carlo variability of Shapley estimates.
Authors: Lingdong Wang, Simran Singh, Jacob Chakareski, Mohammad Hajiesmaili, Ramesh K. Sitaraman
Abstract: Accessing high-quality video content can be challenging due to insufficient and unstable network bandwidth. Recent advances in neural enhancement have shown promising results in improving the quality of degraded videos through deep learning. Neural-Enhanced Streaming (NES) incorporates this new approach into video streaming, allowing users to download low-quality video segments and then enhance them to obtain high-quality content without violating the playback of the video stream. We introduce BONES, an NES control algorithm that jointly manages the network and computational resources to maximize the quality of experience (QoE) of the user. BONES formulates NES as a Lyapunov optimization problem and solves it in an online manner with near-optimal performance, making it the first NES algorithm to provide a theoretical performance guarantee. Comprehensive experimental results indicate that BONES increases QoE by 5\% to 20\% over state-of-the-art algorithms with minimal overhead. Our code is available at https://github.com/UMass-LIDS/bones.
Authors: Zengwei Yao, Liyong Guo, Xiaoyu Yang, Wei Kang, Fangjun Kuang, Yifan Yang, Zengrui Jin, Long Lin, Daniel Povey
Abstract: The Conformer has become the most popular encoder model for automatic speech recognition (ASR). It adds convolution modules to a transformer to learn both local and global dependencies. In this work we describe a faster, more memory-efficient, and better-performing transformer, called Zipformer. Modeling changes include: 1) a U-Net-like encoder structure where middle stacks operate at lower frame rates; 2) reorganized block structure with more modules, within which we re-use attention weights for efficiency; 3) a modified form of LayerNorm called BiasNorm allows us to retain some length information; 4) new activation functions SwooshR and SwooshL work better than Swish. We also propose a new optimizer, called ScaledAdam, which scales the update by each tensor's current scale to keep the relative change about the same, and also explictly learns the parameter scale. It achieves faster convergence and better performance than Adam. Extensive experiments on LibriSpeech, Aishell-1, and WenetSpeech datasets demonstrate the effectiveness of our proposed Zipformer over other state-of-the-art ASR models. Our code is publicly available at https://github.com/k2-fsa/icefall.
Authors: Yuping Wang, Jier Chen
Abstract: Forecasting vehicular motions in autonomous driving requires a deep understanding of agent interactions and the preservation of motion equivariance under Euclidean geometric transformations. Traditional models often lack the sophistication needed to handle the intricate dynamics inherent to autonomous vehicles and the interaction relationships among agents in the scene. As a result, these models have a lower model capacity, which then leads to higher prediction errors and lower training efficiency. In our research, we employ EqMotion, a leading equivariant particle, and human prediction model that also accounts for invariant agent interactions, for the task of multi-agent vehicle motion forecasting. In addition, we use a multi-modal prediction mechanism to account for multiple possible future paths in a probabilistic manner. By leveraging EqMotion, our model achieves state-of-the-art (SOTA) performance with fewer parameters (1.2 million) and a significantly reduced training time (less than 2 hours).
Authors: Dmytro Velychko, Simon Damm, Asja Fischer, J\"org L\"ucke
Abstract: Standard probabilistic sparse coding assumes a Laplace prior, a linear mapping from latents to observables, and Gaussian observable distributions. We here derive a solely entropy-based learning objective for the parameters of standard sparse coding. The novel variational objective has the following features: (A) unlike MAP approximations, it uses non-trivial posterior approximations for probabilistic inference; (B) unlike for previous non-trivial approximations, the novel objective is fully analytical; and (C) the objective allows for a novel principled form of annealing. The objective is derived by first showing that the standard ELBO objective converges to a sum of entropies, which matches similar recent results for generative models with Gaussian priors. The conditions under which the ELBO becomes equal to entropies are then shown to have analytical solutions, which leads to the fully analytical objective. Numerical experiments are used to demonstrate the feasibility of learning with such entropy-based ELBOs. We investigate different posterior approximations including Gaussians with correlated latents and deep amortized approximations. Furthermore, we numerically investigate entropy-based annealing which results in improved learning. Our main contributions are theoretical, however, and they are twofold: (1) for non-trivial posterior approximations, we provide the (to the knowledge of the authors) first analytical ELBO objective for standard probabilistic sparse coding; and (2) we provide the first demonstration on how a recently shown convergence of the ELBO to entropy sums can be used for learning.
Authors: Madi Arabi, Xiaolei Fang
Abstract: Most prognostic methods require a decent amount of data for model training. In reality, however, the amount of historical data owned by a single organization might be small or not large enough to train a reliable prognostic model. To address this challenge, this article proposes a federated prognostic model that allows multiple users to jointly construct a failure time prediction model using their multi-stream, high-dimensional, and incomplete data while keeping each user's data local and confidential. The prognostic model first employs multivariate functional principal component analysis to fuse the multi-stream degradation signals. Then, the fused features coupled with the times-to-failure are utilized to build a (log)-location-scale regression model for failure prediction. To estimate parameters using distributed datasets and keep the data privacy of all participants, we propose a new federated algorithm for feature extraction. Numerical studies indicate that the performance of the proposed model is the same as that of classic non-federated prognostic models and is better than that of the models constructed by each user itself.
Authors: Chadi Helwe, Tom Calamai, Pierre-Henri Paris, Chlo\'e Clavel, Fabian Suchanek
Abstract: We introduce MAFALDA, a benchmark for fallacy classification that merges and unites previous fallacy datasets. It comes with a taxonomy that aligns, refines, and unifies existing classifications of fallacies. We further provide a manual annotation of a part of the dataset together with manual explanations for each annotation. We propose a new annotation scheme tailored for subjective NLP tasks, and a new evaluation method designed to handle subjectivity. We then evaluate several language models under a zero-shot learning setting and human performances on MAFALDA to assess their capability to detect and classify fallacies.
Authors: Elham Nasarian, Roohallah Alizadehsani, U. Rajendra Acharya, Kwok-Leung Tsui
Abstract: This paper explores the significant impact of AI-based medical devices, including wearables, telemedicine, large language models, and digital twins, on clinical decision support systems. It emphasizes the importance of producing outcomes that are not only accurate but also interpretable and understandable to clinicians, addressing the risk that lack of interpretability poses in terms of mistrust and reluctance to adopt these technologies in healthcare. The paper reviews interpretable AI processes, methods, applications, and the challenges of implementation in healthcare, focusing on quality control to facilitate responsible communication between AI systems and clinicians. It breaks down the interpretability process into data pre-processing, model selection, and post-processing, aiming to foster a comprehensive understanding of the crucial role of a robust interpretability approach in healthcare and to guide future research in this area. with insights for creating responsible clinician-AI tools for healthcare, as well as to offer a deeper understanding of the challenges they might face. Our research questions, eligibility criteria and primary goals were identified using Preferred Reporting Items for Systematic reviews and Meta-Analyses guideline and PICO method; PubMed, Scopus and Web of Science databases were systematically searched using sensitive and specific search strings. In the end, 52 publications were selected for data extraction which included 8 existing reviews and 44 related experimental studies. The paper offers general concepts of interpretable AI in healthcare and discuss three-levels interpretability process. Additionally, it provides a comprehensive discussion of evaluating robust interpretability AI in healthcare. Moreover, this survey introduces a step-by-step roadmap for implementing responsible AI in healthcare.
Authors: David Stotko, Nils Wandel, Reinhard Klein
Abstract: 3D reconstruction of dynamic scenes is a long-standing problem in computer graphics and increasingly difficult the less information is available. Shape-from-Template (SfT) methods aim to reconstruct a template-based geometry from RGB images or video sequences, often leveraging just a single monocular camera without depth information, such as regular smartphone recordings. Unfortunately, existing reconstruction methods are either unphysical and noisy or slow in optimization. To solve this problem, we propose a novel SfT reconstruction algorithm for cloth using a pre-trained neural surrogate model that is fast to evaluate, stable, and produces smooth reconstructions due to a regularizing physics simulation. Differentiable rendering of the simulated mesh enables pixel-wise comparisons between the reconstruction and a target video sequence that can be used for a gradient-based optimization procedure to extract not only shape information but also physical parameters such as stretching, shearing, or bending stiffness of the cloth. This allows to retain a precise, stable, and smooth reconstructed geometry while reducing the runtime by a factor of 400-500 compared to $\phi$-SfT, a state-of-the-art physics-based SfT approach.
Authors: Christian Weihsbach, Christian N. Kruse, Alexander Bigalke, Mattias P. Heinrich
Abstract: Applying pre-trained medical segmentation models on out-of-domain images often yields predictions of insufficient quality. Several strategies have been proposed to maintain model performance, such as finetuning or unsupervised- and source-free domain adaptation. These strategies set restrictive requirements for data availability. In this study, we propose to combine domain generalization and test-time adaptation to create a highly effective approach for reusing pre-trained models in unseen target domains. Domain-generalized pre-training on source data is used to obtain the best initial performance in the target domain. We introduce the MIND descriptor previously used in image registration tasks as a further technique to achieve generalization and present superior performance for small-scale datasets compared to existing approaches. At test-time, high-quality segmentation for every single unseen scan is ensured by optimizing the model weights for consistency given different image augmentations. That way, our method enables separate use of source and target data and thus removes current data availability barriers. Moreover, the presented method is highly modular as it does not require specific model architectures or prior knowledge of involved domains and labels. We demonstrate this by integrating it into the nnUNet, which is currently the most popular and accurate framework for medical image segmentation. We employ multiple datasets covering abdominal, cardiac, and lumbar spine scans and compose several out-of-domain scenarios in this study. We demonstrate that our method, combined with pre-trained whole-body CT models, can effectively segment MR images with high accuracy in all of the aforementioned scenarios. Open-source code can be found here: https://github.com/multimodallearning/DG-TTA
Authors: Albert Lin, Somil Bansal
Abstract: Learning-based approaches for controlling safety-critical systems are rapidly growing in popularity; thus, it is important to assure their performance and safety. Hamilton-Jacobi (HJ) reachability analysis is a popular formal verification tool for providing such guarantees, since it can handle general nonlinear system dynamics, bounded adversarial system disturbances, and state and input constraints. However, its computational and memory complexity scales exponentially with the state dimension, making it intractable for large-scale systems. To overcome this challenge, neural approaches, such as DeepReach, have been used to synthesize reachable tubes and safety controllers for high-dimensional systems. However, verifying these neural reachable tubes remains challenging. In this work, we propose two verification methods, based on robust scenario optimization and conformal prediction, to provide probabilistic safety guarantees for neural reachable tubes. Our methods allow a direct trade-off between resilience to outlier errors in the neural tube, which are inevitable in a learning-based approach, and the strength of the probabilistic safety guarantee. Furthermore, we show that split conformal prediction, a widely used method in the machine learning community for uncertainty quantification, reduces to a scenario-based approach, making the two methods equivalent not only for verification of neural reachable tubes but also more generally. To our knowledge, our proof is the first in the literature to show a strong relationship between conformal prediction and scenario optimization. Finally, we propose an outlier-adjusted verification approach that uses the error distribution in neural reachable tubes to recover greater safe volumes. We demonstrate the efficacy of the proposed approaches for the high-dimensional problems of multi-vehicle collision avoidance and rocket landing with no-go zones.
Authors: P. Rodriguez-Fernandez, N. T. Howard, A. Saltzman, S. Kantamneni, J. Candy, C. Holland, M. Balandat, S. Ament, A. E. White
Abstract: This work presents the PORTALS framework, which leverages surrogate modeling and optimization techniques to enable the prediction of core plasma profiles and performance with nonlinear gyrokinetic simulations at significantly reduced cost, with no loss of accuracy. The efficiency of PORTALS is benchmarked against standard methods, and its full potential is demonstrated on a unique, simultaneous 5-channel (electron temperature, ion temperature, electron density, impurity density and angular rotation) prediction of steady-state profiles in a DIII-D ITER Similar Shape plasma with GPU-accelerated, nonlinear CGYRO. This paper also provides general guidelines for accurate performance predictions in burning plasmas and the impact of transport modeling in fusion pilot plants studies.
Authors: Xingfang Wu, Eric Laufer, Heng Li, Foutse Khomh, Santhosh Srinivasan, Jayden Luo
Abstract: With the rapid growth of the developer community, the amount of posts on online technical forums has been growing rapidly, which poses difficulties for users to filter useful posts and find important information. Tags provide a concise feature dimension for users to locate their interested posts and for search engines to index the most relevant posts according to the queries. However, most tags are only focused on the technical perspective (e.g., program language, platform, tool). In most cases, forum posts in online developer communities reveal the author's intentions to solve a problem, ask for advice, share information, etc. The modeling of the intentions of posts can provide an extra dimension to the current tag taxonomy. By referencing previous studies and learning from industrial perspectives, we create a refined taxonomy for the intentions of technical forum posts. Through manual labeling and analysis on a sampled post dataset extracted from online forums, we understand the relevance between the constitution of posts (code, error messages) and their intentions. Furthermore, inspired by our manual study, we design a pre-trained transformer-based model to automatically predict post intentions. The best variant of our intention prediction framework, which achieves a Micro F1-score of 0.589, Top 1-3 accuracy of 62.6% to 87.8%, and an average AUC of 0.787, outperforms the state-of-the-art baseline approach. Our characterization and automated classification of forum posts regarding their intentions may help forum maintainers or third-party tool developers improve the organization and retrieval of posts on technical forums. We have released our annotated dataset and codes in our supplementary material package.
Authors: Matthew Kowal, Achal Dave, Rares Ambrus, Adrien Gaidon, Konstantinos G. Derpanis, Pavel Tokmakov
Abstract: This paper studies the problem of concept-based interpretability of transformer representations for videos. Concretely, we seek to explain the decision-making process of video transformers based on high-level, spatiotemporal concepts that are automatically discovered. Prior research on concept-based interpretability has concentrated solely on image-level tasks. Comparatively, video models deal with the added temporal dimension, increasing complexity and posing challenges in identifying dynamic concepts over time. In this work, we systematically address these challenges by introducing the first Video Transformer Concept Discovery (VTCD) algorithm. To this end, we propose an efficient approach for unsupervised identification of units of video transformer representations - concepts, and ranking their importance to the output of a model. The resulting concepts are highly interpretable, revealing spatio-temporal reasoning mechanisms and object-centric representations in unstructured video models. Performing this analysis jointly over a diverse set of supervised and self-supervised representations, we discover that some of these mechanism are universal in video transformers. Finally, we show that VTCD can be used for fine-grained action recognition and video object segmentation.
Authors: Manuel Mu\~noz S\'anchez, Chris van der Ploeg, Robin Smit, Jos Elfring, Emilia Silvas, Ren\'e van de Molengraft
Abstract: Predicting the movement of other road users is beneficial for improving automated vehicle (AV) performance. However, the relationship between the time horizon associated with these predictions and AV performance remains unclear. Despite the existence of numerous trajectory prediction algorithms, no studies have been conducted on how varying prediction lengths affect AV safety and other vehicle performance metrics, resulting in undefined horizon requirements for prediction methods. Our study addresses this gap by examining the effects of different prediction horizons on AV performance, focusing on safety, comfort, and efficiency. Through multiple experiments using a state-of-the-art, risk-based predictive trajectory planner, we simulated predictions with horizons up to 20 seconds. Based on our simulations, we propose a framework for specifying the minimum required and optimal prediction horizons based on specific AV performance criteria and application needs. Our results indicate that a horizon of 1.6 seconds is required to prevent collisions with crossing pedestrians, horizons of 7-8 seconds yield the best efficiency, and horizons up to 15 seconds improve passenger comfort. We conclude that prediction horizon requirements are application-dependent, and recommend aiming for a prediction horizon of 11.8 seconds as a general guideline for applications involving crossing pedestrians.
Authors: Liang Ding, Rui Tuo
Abstract: It is well known that the state space (SS) model formulation of a Gaussian process (GP) can lower its training and prediction time both to $\CalO(n)$ for $n$ data points. We prove that an $m$-dimensional SS model formulation of GP is equivalent to a concept we introduce as the general right Kernel Packet (KP): a transformation for the GP covariance $K$ such that $\sum_{i=0}^{m}a_iD_t^{(j)}K(t,t_i)=0$ holds for any $t \leq t_1$, 0 $\leq j \leq m-1$, and $m+1$ consecutive points $t_i$, where ${D}_t^{(j)}f(t) $ denotes $j$-th derivative acting on $t$. We extend this idea to the backward SS model formulation, leading to the left KP for next $m$ consecutive points: $\sum_{i=0}^{m}b_i{D}_t^{(j)}K(t,t_{m+i})=0$ for any $t\geq t_{2m}$. By combining both left and right KPs, we can prove that a suitable linear combination of these covariance functions yields $m$ KP functions compactly supported on $(t_0,t_{2m})$. KPs improve GP prediction time to $\mathcal{O}(\log n)$ or $\mathcal{O}(1)$, enable broader applications including GP's derivatives and kernel multiplications, and can be generalized to multi-dimensional additive and product kernels for scattered data.
Authors: Andre Weiner, Janis Geise
Abstract: In recent years, deep reinforcement learning has emerged as a technique to solve closed-loop flow control problems. Employing simulation-based environments in reinforcement learning enables a priori end-to-end optimization of the control system, provides a virtual testbed for safety-critical control applications, and allows to gain a deep understanding of the control mechanisms. While reinforcement learning has been applied successfully in a number of rather simple flow control benchmarks, a major bottleneck toward real-world applications is the high computational cost and turnaround time of flow simulations. In this contribution, we demonstrate the benefits of model-based reinforcement learning for flow control applications. Specifically, we optimize the policy by alternating between trajectories sampled from flow simulations and trajectories sampled from an ensemble of environment models. The model-based learning reduces the overall training time by up to $85\%$ for the fluidic pinball test case. Even larger savings are expected for more demanding flow simulations.
Authors: Zihao Wang, Yingyu Yang, Yuzhou Chen, Tingting Yuan, Maxime Sermesant, Herve Delingette, Ona Wu
Abstract: Cross-modality image segmentation aims to segment the target modalities using a method designed in the source modality. Deep generative models can translate the target modality images into the source modality, thus enabling cross-modality segmentation. However, a vast body of existing cross-modality image translation methods relies on supervised learning. In this work, we aim to address the challenge of zero-shot learning-based image translation tasks (extreme scenarios in the target modality is unseen in the training phase). To leverage generative learning for zero-shot cross-modality image segmentation, we propose a novel unsupervised image translation method. The framework learns to translate the unseen source image to the target modality for image segmentation by leveraging the inherent statistical consistency between different modalities for diffusion guidance. Our framework captures identical cross-modality features in the statistical domain, offering diffusion guidance without relying on direct mappings between the source and target domains. This advantage allows our method to adapt to changing source domains without the need for retraining, making it highly practical when sufficient labeled source domain data is not available. The proposed framework is validated in zero-shot cross-modality image segmentation tasks through empirical comparisons with influential generative models, including adversarial-based and diffusion-based models.
Authors: Lars Ankile, Anthony Simeonov, Idan Shenfeld, Pulkit Agrawal
Abstract: While learning from demonstrations is powerful for acquiring visuomotor policies, high-performance imitation without large demonstration datasets remains challenging for tasks requiring precise, long-horizon manipulation. This paper proposes a pipeline for improving imitation learning performance with a small human demonstration budget. We apply our approach to assembly tasks that require precisely grasping, reorienting, and inserting multiple parts over long horizons and multiple task phases. Our pipeline combines expressive policy architectures and various techniques for dataset expansion and simulation-based data augmentation. These help expand dataset support and supervise the model with locally corrective actions near bottleneck regions requiring high precision. We demonstrate our pipeline on four furniture assembly tasks in simulation, enabling a manipulator to assemble up to five parts over nearly 2500 time steps directly from RGB images, outperforming imitation and data augmentation baselines. Project website: https://imitation-juicer.github.io/.
Authors: Vishaal Udandarao, Ameya Prabhu, Adhiraj Ghosh, Yash Sharma, Philip H. S. Torr, Adel Bibi, Samuel Albanie, Matthias Bethge
Abstract: Web-crawled pretraining datasets underlie the impressive "zero-shot" evaluation performance of multimodal models, such as CLIP for classification/retrieval and Stable-Diffusion for image generation. However, it is unclear how meaningful the notion of "zero-shot" generalization is for such multimodal models, as it is not known to what extent their pretraining datasets encompass the downstream concepts targeted for during "zero-shot" evaluation. In this work, we ask: How is the performance of multimodal models on downstream concepts influenced by the frequency of these concepts in their pretraining datasets? We comprehensively investigate this question across 34 models and five standard pretraining datasets (CC-3M, CC-12M, YFCC-15M, LAION-400M, LAION-Aesthetics), generating over 300GB of data artifacts. We consistently find that, far from exhibiting "zero-shot" generalization, multimodal models require exponentially more data to achieve linear improvements in downstream "zero-shot" performance, following a sample inefficient log-linear scaling trend. This trend persists even when controlling for sample-level similarity between pretraining and downstream datasets, and testing on purely synthetic data distributions. Furthermore, upon benchmarking models on long-tailed data sampled based on our analysis, we demonstrate that multimodal models across the board perform poorly. We contribute this long-tail test set as the "Let it Wag!" benchmark to further research in this direction. Taken together, our study reveals an exponential need for training data which implies that the key to "zero-shot" generalization capabilities under large-scale training paradigms remains to be found.
Authors: Cailean Osborne
Abstract: Governments are increasingly allocating funding for open source software (OSS) development to address concerns related to software security, digital sovereignty, and national competitiveness in science and innovation, amongst others. While announcements of governmental funding are generally well-received by OSS developers, we still have a limited understanding of OSS developers evaluate the relative benefits and drawbacks of such funding compared to other types of funding. This paper explores this question through a case study on scikit-learn, a Python library for machine learning, whose funding model combines research grants, commercial sponsorship, community donations, and a 32 million euro grant from the France's artificial intelligence strategy. Through 25 interviews with scikit-learn's maintainers and funders, this study makes two key contributions to research and practice. First, the study illustrates how the maintainers have weaved public and private funding into their project to ensure the continued provision of scikit-learn as a digital public good, as well as the importance of diversified funding and governance protocols for funding to safeguard the community ethos of the project. Second, it offers practical recommendations to various stakeholders. For OSS developer communities, it illustrates the benefits of a diversified funding model in balancing the merits and drawbacks of different funding sources. For companies, it serves as a reminder that sponsoring developers or OSS projects can significantly support OSS maintainers, who often struggle with limited resources and towering workloads. For governments, it emphasises the importance of funding the maintenance of existing OSS in addition to or exclusively funding the development of new OSS libraries or features. The paper concludes with suggestions for future research directions.