Authors: Debanjali Bhattacharya, Neelam Sinha, Yashwanth R., Amit Chattopadhyay
This study proposes a new approach that investigates differences in topological characteristics of visual networks, which are constructed using fMRI BOLD time-series corresponding to visual datasets of COCO, ImageNet, and SUN. A publicly available BOLD5000 dataset is utilized that contains fMRI scans while viewing 5254 images of diverse complexities. The objective of this study is to examine how network topology differs in response to distinct visual stimuli from these visual datasets. To achieve this, 0- and 1-dimensional persistence diagrams are computed for each visual network representing COCO, ImageNet, and SUN. For extracting suitable features from topological persistence diagrams, K-means clustering is executed. The extracted K-means cluster features are fed to a novel deep-hybrid model that yields accuracy in the range of 90%-95% in classifying these visual networks. To understand vision, this type of visual network categorization across visual datasets is important as it captures differences in BOLD signals while perceiving images with different contexts and complexities. Furthermore, distinctive topological patterns of visual network associated with each dataset, as revealed from this study, could potentially lead to the development of future neuroimaging biomarkers for diagnosing visual processing disorders like visual agnosia or prosopagnosia, and tracking changes in visual cognition over time.
Authors: Yixuan Sun, Elizabeth Cucuzzella, Steven Brus, Sri Hari Krishna Narayanan, Balu Nadiga, Luke Van Roekel, Jan Hückelheim, Sandeep Madireddy
Modeling is crucial to understanding the effect of greenhouse gases, warming, and ice sheet melting on the ocean. At the same time, ocean processes affect phenomena such as hurricanes and droughts. Parameters in the models that cannot be physically measured have a significant effect on the model output. For an idealized ocean model, we generated perturbed parameter ensemble data and trained surrogate neural network models. The neural surrogates accurately predicted the one-step forward dynamics, of which we then computed the parametric sensitivity.
Authors: Vincent Yuansang Zha, Vaishnavi Kommaraju, Okenna Obi-Njoku, Vijay Dakshinamoorthy, Anirudh Agnihotri, Nantes Kirsten
Detecting anomalies in a daily time series with a weekly pattern is a common task with a wide range of applications. A typical way of performing the task is by using decomposition method. However, the method often generates false positive results where a data point falls within its weekly range but is just off from its weekday position. We refer to this type of anomalies as "in-season anomalies", and propose a k-parameter approach to address the issue. The approach provides configurable extra tolerance for in-season anomalies to suppress misleading alerts while preserving real positives. It yields favorable result.
Authors: Robyn Maxwell, Timothy Hanley, Dara Golden, Adara Andonie, Joseph Lemley, Ashkan Parsi
Breathing rate is a vital health metric that is an invaluable indicator of the overall health of a person. In recent years, the non-contact measurement of health signals such as breathing rate has been a huge area of development, with a wide range of applications from telemedicine to driver monitoring systems. This paper presents an investigation into a method of non-contact breathing rate detection using a motion detection algorithm, optical flow. Optical flow is used to successfully measure breathing rate by tracking the motion of specific points on the body. In this study, the success of optical flow when using different sets of points is evaluated. Testing shows that both chest and facial movement can be used to determine breathing rate but to different degrees of success. The chest generates very accurate signals, with an RMSE of 0.63 on the tested videos. Facial points can also generate reliable signals when there is minimal head movement but are much more vulnerable to noise caused by head/body movements. These findings highlight the potential of optical flow as a non-invasive method for breathing rate detection and emphasize the importance of selecting appropriate points to optimize accuracy.
Authors: Alice Bernasconi, Alessio Zanga, Peter J.F. Lucas, Marco Scutari Fabio Stella
Over the last decades, many prognostic models based on artificial intelligence techniques have been used to provide detailed predictions in healthcare. Unfortunately, the real-world observational data used to train and validate these models are almost always affected by biases that can strongly impact the outcomes validity: two examples are values missing not-at-random and selection bias. Addressing them is a key element in achieving transportability and in studying the causal relationships that are critical in clinical decision making, going beyond simpler statistical approaches based on probabilistic association.
In this context, we propose a novel approach that combines selection diagrams, missingness graphs, causal discovery and prior knowledge into a single graphical model to estimate the cardiovascular risk of adolescent and young females who survived breast cancer. We learn this model from data comprising two different cohorts of patients. The resulting causal network model is validated by expert clinicians in terms of risk assessment, accuracy and explainability, and provides a prognostic model that outperforms competing machine learning methods.
Authors: Tahmina Sultana Priya, Fan Leng, Anthony C. Luehrs, Eric W. Klee, Alina M. Allen, Konstantinos N. Lazaridis, Danfeng (Daphne)Yao, Shulan Tian
Non-alcoholic fatty liver disease (NAFLD) is a prevalent chronic liver disorder characterized by the excessive accumulation of fat in the liver in individuals who do not consume significant amounts of alcohol, including risk factors like obesity, insulin resistance, type 2 diabetes, etc. We aim to identify subgroups of NAFLD patients based on demographic, clinical, and genetic characteristics for precision medicine. The genomic and phenotypic data (3,408 cases and 4,739 controls) for this study were gathered from participants in Mayo Clinic Tapestry Study (IRB#19-000001) and their electric health records, including their demographic, clinical, and comorbidity data, and the genotype information through whole exome sequencing performed at Helix using the Exome+$^\circledR$ Assay according to standard procedure (www$.$helix$.$com). Factors highly relevant to NAFLD were determined by the chi-square test and stepwise backward-forward regression model. Latent class analysis (LCA) was performed on NAFLD cases using significant indicator variables to identify subgroups. The optimal clustering revealed 5 latent subgroups from 2,013 NAFLD patients (mean age 60.6 years and 62.1% women), while a polygenic risk score based on 6 single-nucleotide polymorphism (SNP) variants and disease outcomes were used to analyze the subgroups. The groups are characterized by metabolic syndrome, obesity, different comorbidities, psychoneurological factors, and genetic factors. Odds ratios were utilized to compare the risk of complex diseases, such as fibrosis, cirrhosis, and hepatocellular carcinoma (HCC), as well as liver failure between the clusters. Cluster 2 has a significantly higher complex disease outcome compared to other clusters. Keywords: Fatty liver disease; Polygenic risk score; Precision medicine; Deep phenotyping; NAFLD comorbidities; Latent class analysis.
Authors: Rex Chen, Kathleen M. Carley, Fei Fang, Norman Sadeh
Traffic simulators are used to generate data for learning in intelligent transportation systems (ITSs). A key question is to what extent their modelling assumptions affect the capabilities of ITSs to adapt to various scenarios when deployed in the real world. This work focuses on two simulators commonly used to train reinforcement learning (RL) agents for traffic applications, CityFlow and SUMO. A controlled virtual experiment varying driver behavior and simulation scale finds evidence against distributional equivalence in RL-relevant measures from these simulators, with the root mean squared error and KL divergence being significantly greater than 0 for all assessed measures. While granular real-world validation generally remains infeasible, these findings suggest that traffic simulators are not a deus ex machina for RL training: understanding the impacts of inter-simulator differences is necessary to train and deploy RL-based ITSs.
Authors: Wei Wen, Kuang-Hung Liu, Igor Fedorov, Xin Zhang, Hang Yin, Weiwei Chu, Kaveh Hassani, Mengying Sun, Jiang Liu, Xu Wang, Lin Jiang, Yuxin Chen, Buyun Zhang, Xi Liu, Dehua Cheng, Zhengxing Chen, Guang Zhao, Fangqiu Han, Jiyan Yang, Yuchen Hao, Liang Xiong, Wen-Yen Chen
Neural Architecture Search (NAS) has demonstrated its efficacy in computer vision and potential for ranking systems. However, prior work focused on academic problems, which are evaluated at small scale under well-controlled fixed baselines. In industry system, such as ranking system in Meta, it is unclear whether NAS algorithms from the literature can outperform production baselines because of: (1) scale - Meta ranking systems serve billions of users, (2) strong baselines - the baselines are production models optimized by hundreds to thousands of world-class engineers for years since the rise of deep learning, (3) dynamic baselines - engineers may have established new and stronger baselines during NAS search, and (4) efficiency - the search pipeline must yield results quickly in alignment with the productionization life cycle. In this paper, we present Rankitect, a NAS software framework for ranking systems at Meta. Rankitect seeks to build brand new architectures by composing low level building blocks from scratch. Rankitect implements and improves state-of-the-art (SOTA) NAS methods for comprehensive and fair comparison under the same search space, including sampling-based NAS, one-shot NAS, and Differentiable NAS (DNAS). We evaluate Rankitect by comparing to multiple production ranking models at Meta. We find that Rankitect can discover new models from scratch achieving competitive tradeoff between Normalized Entropy loss and FLOPs. When utilizing search space designed by engineers, Rankitect can generate better models than engineers, achieving positive offline evaluation and online A/B test at Meta scale.
Authors: Sangwon Baek, Seung Jun Lee
Few studies have investigated the diagnostic utilities of biomarkers for predicting bacteremia among septic patients admitted to intensive care units (ICU). Therefore, this study evaluated the prediction power of laboratory biomarkers to utilize those markers with high performance to optimize the predictive model for bacteremia. This retrospective cross-sectional study was conducted at the ICU department of Gyeongsang National University Changwon Hospital in 2019. Adult patients qualifying SEPSIS-3 (increase in sequential organ failure score greater than or equal to 2) criteria with at least two sets of blood culture were selected. Collected data was initially analyzed independently to identify the significant predictors, which was then used to build the multivariable logistic regression (MLR) model. A total of 218 patients with 48 cases of true bacteremia were analyzed in this research. Both CRP and PCT showed a substantial area under the curve (AUC) value for discriminating bacteremia among septic patients (0.757 and 0.845, respectively). To further enhance the predictive accuracy, we combined PCT, bilirubin, neutrophil lymphocyte ratio (NLR), platelets, lactic acid, erythrocyte sedimentation rate (ESR), and Glasgow Coma Scale (GCS) score to build the predictive model with an AUC of 0.907 (95% CI, 0.843 to 0.956). In addition, a high association between bacteremia and mortality rate was discovered through the survival analysis (0.004). While PCT is certainly a useful index for distinguishing patients with and without bacteremia by itself, our MLR model indicates that the accuracy of bacteremia prediction substantially improves by the combined use of PCT, bilirubin, NLR, platelets, lactic acid, ESR, and GCS score.
Authors: Haowen Wang, Xinyan Ye, Yangze Zhou, Zhiyi Zhang, Longhan Zhang, Jing Jiang
Uplift modeling is a fundamental component of marketing effect modeling, which is commonly employed to evaluate the effects of treatments on outcomes. Through uplift modeling, we can identify the treatment with the greatest benefit. On the other side, we can identify clients who are likely to make favorable decisions in response to a certain treatment. In the past, uplift modeling approaches relied heavily on the difference-in-difference (DID) architecture, paired with a machine learning model as the estimation learner, while neglecting the link and confidential information between features. We proposed a framework based on graph neural networks that combine causal knowledge with an estimate of uplift value. Firstly, we presented a causal representation technique based on CATE (conditional average treatment effect) estimation and adjacency matrix structure learning. Secondly, we suggested a more scalable uplift modeling framework based on graph convolution networks for combining causal knowledge. Our findings demonstrate that this method works effectively for predicting uplift values, with small errors in typical simulated data, and its effectiveness has been verified in actual industry marketing data.
Authors: Sujal Vijayaraghavan, Redwan Alqasemi, Rajiv Dubey, Sudeep Sarkar
Robot grasp typically follows five stages: object detection, object localisation, object pose estimation, grasp pose estimation, and grasp planning. We focus on object pose estimation. Our approach relies on three pieces of information: multiple views of the object, the camera's extrinsic parameters at those viewpoints, and 3D CAD models of objects. The first step involves a standard deep learning backbone (FCN ResNet) to estimate the object label, semantic segmentation, and a coarse estimate of the object pose with respect to the camera. Our novelty is using a refinement module that starts from the coarse pose estimate and refines it by optimisation through differentiable rendering. This is a purely vision-based approach that avoids the need for other information such as point cloud or depth images. We evaluate our object pose estimation approach on the ShapeNet dataset and show improvements over the state of the art. We also show that the estimated object pose results in 99.65% grasp accuracy with the ground truth grasp candidates on the Object Clutter Indoor Dataset (OCID) Grasp dataset, as computed using standard practice.
Authors: Jaeik Jeon, Jiyeon Kim, Yeonggul Jang, Yeonyee E. Yoon, Dawun Jeong, Youngtaek Hong, Seung-Ah Lee, Hyuk-Jae Chang
Doppler echocardiography offers critical insights into cardiac function and phases by quantifying blood flow velocities and evaluating myocardial motion. However, previous methods for automating Doppler analysis, ranging from initial signal processing techniques to advanced deep learning approaches, have been constrained by their reliance on electrocardiogram (ECG) data and their inability to process Doppler views collectively. We introduce a novel unified framework using a convolutional neural network for comprehensive analysis of spectral and tissue Doppler echocardiography images that combines automatic measurements and end-diastole (ED) detection into a singular method. The network automatically recognizes key features across various Doppler views, with novel Doppler shape embedding and anti-aliasing modules enhancing interpretation and ensuring consistent analysis. Empirical results indicate a consistent outperformance in performance metrics, including dice similarity coefficients (DSC) and intersection over union (IoU). The proposed framework demonstrates strong agreement with clinicians in Doppler automatic measurements and competitive performance in ED detection.
Authors: Michael Celentano, Zhou Fan, Licong Lin, Song Mei
We study mean-field variational inference in a Bayesian linear model when the sample size n is comparable to the dimension p. In high dimensions, the common approach of minimizing a Kullback-Leibler divergence from the posterior distribution, or maximizing an evidence lower bound, may deviate from the true posterior mean and underestimate posterior uncertainty. We study instead minimization of the TAP free energy, showing in a high-dimensional asymptotic framework that it has a local minimizer which provides a consistent estimate of the posterior marginals and may be used for correctly calibrated posterior inference. Geometrically, we show that the landscape of the TAP free energy is strongly convex in an extensive neighborhood of this local minimizer, which under certain general conditions can be found by an Approximate Message Passing (AMP) algorithm. We then exhibit an efficient algorithm that linearly converges to the minimizer within this local neighborhood. In settings where it is conjectured that no efficient algorithm can find this local neighborhood, we prove analogous geometric properties for a local minimizer of the TAP free energy reachable by AMP, and show that posterior inference based on this minimizer remains correctly calibrated.
Authors: Keiya Hirashima, Kana Moriwaki, Michiko S. Fujii, Yutaka Hirai, Takayuki R. Saitoh, Junichiro Makino, Shirley Ho
Some stars are known to explode at the end of their lives, called supernovae (SNe). The substantial amount of matter and energy that SNe release provides significant feedback to star formation and gas dynamics in a galaxy. SNe release a substantial amount of matter and energy to the interstellar medium, resulting in significant feedback to star formation and gas dynamics in a galaxy. While such feedback has a crucial role in galaxy formation and evolution, in simulations of galaxy formation, it has only been implemented using simple {\it sub-grid models} instead of numerically solving the evolution of gas elements around SNe in detail due to a lack of resolution. We develop a method combining machine learning and Gibbs sampling to predict how a supernova (SN) affects the surrounding gas. The fidelity of our model in the thermal energy and momentum distribution outperforms the low-resolution SN simulations. Our method can replace the SN sub-grid models and help properly simulate un-resolved SN feedback in galaxy formation simulations. We find that employing our new approach reduces the necessary computational cost to $\sim$ 1 percent compared to directly resolving SN feedback.
Authors: Xidong Wu, Wan-Yi Lin, Devin Willmott, Filipe Condessa, Yufei Huang, Zhenzhen Li, Madan Ravi Ganesh
Federated Learning (FL) is a distributed training paradigm that enables clients scattered across the world to cooperatively learn a global model without divulging confidential data. However, FL faces a significant challenge in the form of heterogeneous data distributions among clients, which leads to a reduction in performance and robustness. A recent approach to mitigating the impact of heterogeneous data distributions is through the use of foundation models, which offer better performance at the cost of larger computational overheads and slower inference speeds. We introduce foundation model distillation to assist in the federated training of lightweight client models and increase their performance under heterogeneous data settings while keeping inference costs low. Our results show improvement in the global model performance on a balanced testing set, which contains rarely observed samples, even under extreme non-IID client data distributions. We conduct a thorough evaluation of our framework with different foundation model backbones on CIFAR10, with varying degrees of heterogeneous data distributions ranging from class-specific data partitions across clients to dirichlet data sampling, parameterized by values between 0.01 and 1.0.
Authors: Thinh Viet Le, Vassilis Kekatos
Variational quantum approaches have shown great promise in finding near-optimal solutions to computationally challenging tasks. Nonetheless, enforcing constraints in a disciplined fashion has been largely unexplored. To address this gap, this work proposes a hybrid quantum-classical algorithmic paradigm termed VQEC that extends the celebrated VQE to handle optimization with constraints. As with the standard VQE, the vector of optimization variables is captured by the state of a variational quantum circuit (VQC). To deal with constraints, VQEC optimizes a Lagrangian function classically over both the VQC parameters as well as the dual variables associated with constraints. To comply with the quantum setup, variables are updated via a perturbed primal-dual method leveraging the parameter shift rule. Among a wide gamut of potential applications, we showcase how VQEC can approximately solve quadratically-constrained binary optimization (QCBO) problems, find stochastic binary policies satisfying quadratic constraints on the average and in probability, and solve large-scale linear programs (LP) over the probability simplex. Under an assumption on the error for the VQC to approximate an arbitrary probability mass function (PMF), we provide bounds on the optimality gap attained by a VQC. Numerical tests on a quantum simulator investigate the effect of various parameters and corroborate that VQEC can generate high-quality solutions.
Authors: Aveen Dayal, Vimal K. B., Linga Reddy Cenkeramaddi, C. Krishna Mohan, Abhinav Kumar, Vineeth N Balasubramanian
Domain Generalization (DG) techniques have emerged as a popular approach to address the challenges of domain shift in Deep Learning (DL), with the goal of generalizing well to the target domain unseen during the training. In recent years, numerous methods have been proposed to address the DG setting, among which one popular approach is the adversarial learning-based methodology. The main idea behind adversarial DG methods is to learn domain-invariant features by minimizing a discrepancy metric. However, most adversarial DG methods use 0-1 loss based $\mathcal{H}\Delta\mathcal{H}$ divergence metric. In contrast, the margin loss-based discrepancy metric has the following advantages: more informative, tighter, practical, and efficiently optimizable. To mitigate this gap, this work proposes a novel adversarial learning DG algorithm, MADG, motivated by a margin loss-based discrepancy metric. The proposed MADG model learns domain-invariant features across all source domains and uses adversarial training to generalize well to the unseen target domain. We also provide a theoretical analysis of the proposed MADG model based on the unseen target error bound. Specifically, we construct the link between the source and unseen domains in the real-valued hypothesis space and derive the generalization bound using margin loss and Rademacher complexity. We extensively experiment with the MADG model on popular real-world DG datasets, VLCS, PACS, OfficeHome, DomainNet, and TerraIncognita. We evaluate the proposed algorithm on DomainBed's benchmark and observe consistent performance across all the datasets.
Authors: Ye Tian, Xinwei Zhang, Zhiqiang Tan
Consider a semi-supervised setting with a labeled dataset of binary responses and predictors and an unlabeled dataset with only the predictors. Logistic regression is equivalent to an exponential tilt model in the labeled population. For semi-supervised estimation, we develop further analysis and understanding of a statistical approach using exponential tilt mixture (ETM) models and maximum nonparametric likelihood estimation, while allowing that the class proportions may differ between the unlabeled and labeled data. We derive asymptotic properties of ETM-based estimation and demonstrate improved efficiency over supervised logistic regression in a random sampling setup and an outcome-stratified sampling setup previously used. Moreover, we reconcile such efficiency improvement with the existing semiparametric efficiency theory when the class proportions in the unlabeled and labeled data are restricted to be the same. We also provide a simulation study to numerically illustrate our theoretical findings.
Authors: Gladys Tyen, Hassan Mansoor, Peter Chen, Tony Mak, Victor Cărbune
While self-correction has shown promise in improving LLM outputs in terms of style and quality (e.g. Chen et al., 2023; Madaan et al., 2023), recent attempts to self-correct logical or reasoning errors often cause correct answers to become incorrect, resulting in worse performances overall (Huang et al., 2023). In this paper, we break down the self-correction process into two core components: mistake finding and output correction. For mistake finding, we release BIG-Bench Mistake, a dataset of logical mistakes in Chain-of-Thought reasoning traces. We provide benchmark numbers for several state-of-the-art LLMs, and demonstrate that LLMs generally struggle with finding logical mistakes. For output correction, we propose a backtracking method which provides large improvements when given information on mistake location. We construe backtracking as a lightweight alternative to reinforcement learning methods, and show that it remains effective with a reward model at 60-70% accuracy.
Authors: Ridha Ouni, Haikel Alhichri
Detecting COVID-19 patients using Computed Tomography (CT) images of the lungs is an active area of research. Datasets of CT images from COVID-19 patients are becoming available. Deep learning (DL) solutions and in particular Convolutional Neural Networks (CNN) have achieved impressive results for the classification of COVID-19 CT images, but only when the training and testing take place within the same dataset. Work on the cross-dataset problem is still limited and the achieved results are low. Our work tackles the cross-dataset problem through a Domain Adaptation (DA) technique with deep learning. Our proposed solution, COVID19-DANet, is based on pre-trained CNN backbone for feature extraction. For this task, we select the pre-trained Efficientnet-B3 CNN because it has achieved impressive classification accuracy in previous work. The backbone CNN is followed by a prototypical layer which is a concept borrowed from prototypical networks in few-shot learning (FSL). It computes a cosine distance between given samples and the class prototypes and then converts them to class probabilities using the Softmax function. To train the COVID19-DANet model, we propose a combined loss function that is composed of the standard cross-entropy loss for class discrimination and another entropy loss computed over the unlabelled target set only. This so-called unlabelled target entropy loss is minimized and maximized in an alternative fashion, to reach the two objectives of class discrimination and domain invariance. COVID19-DANet is tested under four cross-dataset scenarios using the SARS-CoV-2-CT and COVID19-CT datasets and has achieved encouraging results compared to recent work in the literature.
Authors: Urchade Zaratiana, Nadi Tomeh, Pierre Holat, Thierry Charnois
Named Entity Recognition (NER) is essential in various Natural Language Processing (NLP) applications. Traditional NER models are effective but limited to a set of predefined entity types. In contrast, Large Language Models (LLMs) can extract arbitrary entities through natural language instructions, offering greater flexibility. However, their size and cost, particularly for those accessed via APIs like ChatGPT, make them impractical in resource-limited scenarios. In this paper, we introduce a compact NER model trained to identify any type of entity. Leveraging a bidirectional transformer encoder, our model, GLiNER, facilitates parallel entity extraction, an advantage over the slow sequential token generation of LLMs. Through comprehensive testing, GLiNER demonstrate strong performance, outperforming both ChatGPT and fine-tuned LLMs in zero-shot evaluations on various NER benchmarks.
Authors: Ivan Kapelyukh, Edward Johns
Arranging objects correctly is a key capability for robots which unlocks a wide range of useful tasks. A prerequisite for creating successful arrangements is the ability to evaluate the desirability of a given arrangement. Our method "SceneScore" learns a cost function for arrangements, such that desirable, human-like arrangements have a low cost. We learn the distribution of training arrangements offline using an energy-based model, solely from example images without requiring environment interaction or human supervision. Our model is represented by a graph neural network which learns object-object relations, using graphs constructed from images. Experiments demonstrate that the learned cost function can be used to predict poses for missing objects, generalise to novel objects using semantic features, and can be composed with other cost functions to satisfy constraints at inference time.
Authors: Ixandra Achitouv, Dragos Gorduza, Antoine Jacquier
This article provides an understanding of Natural Language Processing techniques in the framework of financial regulation, more specifically in order to perform semantic matching search between rules and policy when no dataset is available for supervised learning. We outline how to outperform simple pre-trained sentences-transformer models using freely available resources and explain the mathematical concepts behind the key building blocks of Natural Language Processing.
Authors: Amanie Azzam, Saba Sanami, Amir G. Aghdam
Non-intrusive Load Monitoring (NILM) is an established technique for effective and cost-efficient electricity consumption management. The method is used to estimate appliance-level power consumption from aggregated power measurements. This paper presents a hybrid learning approach, consisting of a convolutional neural network (CNN) and a bidirectional long short-term memory (BILSTM), featuring an integrated attention mechanism, all within the context of disaggregating low-frequency power data. While prior research has been mainly focused on high-frequency data disaggregation, our study takes a distinct direction by concentrating on low-frequency data. The proposed hybrid CNN-BILSTM model is adept at extracting both temporal (time-related) and spatial (location-related) features, allowing it to precisely identify energy consumption patterns at the appliance level. This accuracy is further enhanced by the attention mechanism, which aids the model in pinpointing crucial parts of the data for more precise event detection and load disaggregation. We conduct simulations using the existing low-frequency REDD dataset to assess our model performance. The results demonstrate that our proposed approach outperforms existing methods in terms of accuracy and computation time.
Authors: Ana Răduţoiu, Jan-Philipp Schulze, Philip Sperl, Konstantin Böttinger
Neural networks build the foundation of several intelligent systems, which, however, are known to be easily fooled by adversarial examples. Recent advances made these attacks possible even in air-gapped scenarios, where the autonomous system observes its surroundings by, e.g., a camera. We extend these ideas in our research and evaluate the robustness of multi-camera setups against such physical adversarial examples. This scenario becomes ever more important with the rise in popularity of autonomous vehicles, which fuse the information of several cameras for their driving decision. While we find that multi-camera setups provide some robustness towards past attack methods, we see that this advantage reduces when optimizing on multiple perspectives at once. We propose a novel attack method that we call Transcender-MC, where we incorporate online 3D renderings and perspective projections in the training process. Moreover, we motivate that certain data augmentation techniques can facilitate the generation of successful adversarial examples even further. Transcender-MC is 11% more effective in successfully attacking multi-camera setups than state-of-the-art methods. Our findings offer valuable insights regarding the resilience of object detection in a setup with multiple cameras and motivate the need of developing adequate defense mechanisms against them.
Authors: Jiarui Xu, Karim Said, Lizhong Zheng, Lingjia Liu
Orthogonal time frequency space (OTFS) is a promising modulation scheme for wireless communication in high-mobility scenarios. Recently, a reservoir computing (RC) based approach has been introduced for online subframe-based symbol detection in the OTFS system, where only a limited number of over-the-air (OTA) pilot symbols are utilized for training. However, this approach does not leverage the domain knowledge specific to the OTFS system. This paper introduces a novel two-dimensional RC (2D-RC) method that incorporates the structural knowledge of the OTFS system into the design for online symbol detection on a subframe basis. Specifically, as the channel response acts as a two-dimensional (2D) operation over the transmitted information symbols in the delay-Doppler (DD) domain, the 2D-RC is designed to have a 2D structure to equalize the channel. With the introduced architecture, the 2D-RC can benefit from the predictable channel representation in the DD domain. Moreover, unlike the previous work that requires multiple RCs to learn the channel feature, the 2D-RC only requires a single neural network for detection. Experimental results demonstrate the effectiveness of the 2D-RC approach across different OTFS system variants and modulation orders.
Authors: Keaton Hamm, Caroline Moosmüller, Bernhard Schmitzer, Matthew Thorpe
This paper aims at building the theoretical foundations for manifold learning algorithms in the space of absolutely continuous probability measures on a compact and convex subset of $\mathbb{R}^d$, metrized with the Wasserstein-2 distance $W$. We begin by introducing a natural construction of submanifolds $\Lambda$ of probability measures equipped with metric $W_\Lambda$, the geodesic restriction of $W$ to $\Lambda$. In contrast to other constructions, these submanifolds are not necessarily flat, but still allow for local linearizations in a similar fashion to Riemannian submanifolds of $\mathbb{R}^d$. We then show how the latent manifold structure of $(\Lambda,W_{\Lambda})$ can be learned from samples $\{\lambda_i\}_{i=1}^N$ of $\Lambda$ and pairwise extrinsic Wasserstein distances $W$ only. In particular, we show that the metric space $(\Lambda,W_{\Lambda})$ can be asymptotically recovered in the sense of Gromov--Wasserstein from a graph with nodes $\{\lambda_i\}_{i=1}^N$ and edge weights $W(\lambda_i,\lambda_j)$. In addition, we demonstrate how the tangent space at a sample $\lambda$ can be asymptotically recovered via spectral analysis of a suitable "covariance operator" using optimal transport maps from $\lambda$ to sufficiently close and diverse samples $\{\lambda_i\}_{i=1}^N$. The paper closes with some explicit constructions of submanifolds $\Lambda$ and numerical examples on the recovery of tangent spaces through spectral analysis.
Authors: Hrishikesh Vachhani, Thangarajah Akilan, Yash Devmurari, Nisharaff Shaik, Dhruvisha Patel
Pedestrian detection has become a cornerstone for several high-level tasks, including autonomous driving, intelligent transportation, and traffic surveillance. There are several works focussed on pedestrian detection using visible images, mainly in the daytime. However, this task is very intriguing when the environmental conditions change to poor lighting or nighttime. Recently, new ideas have been spurred to use alternative sources, such as Far InfraRed (FIR) temperature sensor feeds for detecting pedestrians in low-light conditions. This study comprehensively reviews recent developments in low-light pedestrian detection approaches. It systematically categorizes and analyses various algorithms from region-based to non-region-based and graph-based learning methodologies by highlighting their methodologies, implementation issues, and challenges. It also outlines the key benchmark datasets that can be used for research and development of advanced pedestrian detection algorithms, particularly in low-light situations
Authors: Pierre Le Pelletier de Woillemont, Rémi Labory, Vincent Corruble
Inverse Reinforcement Learning (IRL) learns an optimal policy, given some expert demonstrations, thus avoiding the need for the tedious process of specifying a suitable reward function. However, current methods are constrained by at least one of the following requirements. The first one is the need to fully solve a forward Reinforcement Learning (RL) problem in the inner loop of the algorithm, which might be prohibitively expensive in many complex environments. The second one is the need for full trajectories from the experts, which might not be easily available. The third one is the assumption that the expert data is homogeneous rather than a collection from various experts or possibly alternative solutions to the same task. Such constraints make IRL approaches either not scalable or not usable on certain existing systems. In this work we propose an approach which removes these requirements through a dynamic, adaptive method called Adversarial Imitation Learning on Aggregated Data (AILAD). It learns conjointly both a non linear reward function and the associated optimal policy using an adversarial framework. The reward learner only uses aggregated data. Moreover, it generates diverse behaviors producing a distribution over the aggregated data matching that of the experts.
Authors: Burcu Ozek, Zhenyuan Lu, Srinivasan Radhakrishnan, Sagar Kamarthi
Improper pain management can lead to severe physical or mental consequences, including suffering, and an increased risk of opioid dependency. Assessing the presence and severity of pain is imperative to prevent such outcomes and determine the appropriate intervention. However, the evaluation of pain intensity is challenging because different individuals experience pain differently. To overcome this, researchers have employed machine learning models to evaluate pain intensity objectively. However, these efforts have primarily focused on point estimation of pain, disregarding the inherent uncertainty and variability present in the data and model. Consequently, the point estimates provide only partial information for clinical decision-making. This study presents a neural network-based method for objective pain interval estimation, incorporating uncertainty quantification. This work explores three algorithms: the bootstrap method, lower and upper bound estimation (LossL) optimized by genetic algorithm, and modified lower and upper bound estimation (LossS) optimized by gradient descent algorithm. Our empirical results reveal that LossS outperforms the other two by providing a narrower prediction interval. As LossS outperforms, we assessed its performance in three different scenarios for pain assessment: (1) a generalized approach (single model for the entire population), (2) a personalized approach (separate model for each individual), and (3) a hybrid approach (separate model for each cluster of individuals). Our findings demonstrate the hybrid approach's superior performance, with notable practicality in clinical contexts. It has the potential to be a valuable tool for clinicians, enabling objective pain intensity assessment while taking uncertainty into account. This capability is crucial in facilitating effective pain management and reducing the risks associated with improper treatment.
Authors: Chenxi Whitehouse, Fantine Huot, Jasmijn Bastings, Mostafa Dehghani, Chu-Cheng Lin, Mirella Lapata
With the increasing prevalence of Large Language Models, traditional full fine-tuning approaches face growing challenges, especially in memory-intensive tasks. This paper investigates the potential of Parameter-Efficient Fine-Tuning, focusing on Low-Rank Adaptation (LoRA), for complex and under-explored multilingual summarisation tasks. We conduct an extensive study across different data availability scenarios, including full-data, low-data, and cross-lingual transfer, leveraging models of different sizes. Our findings reveal that LoRA lags behind full fine-tuning when trained with full data, however, it excels in low-data scenarios and cross-lingual transfer. Interestingly, as models scale up, the performance gap between LoRA and full fine-tuning diminishes. Additionally, we investigate effective strategies for few-shot cross-lingual transfer, finding that continued LoRA tuning achieves the best performance compared to both full fine-tuning and dynamic composition of language-specific LoRA modules.
Authors: Ethan Perez, Robert Long
As AI systems become more advanced and widely deployed, there will likely be increasing debate over whether AI systems could have conscious experiences, desires, or other states of potential moral significance. It is important to inform these discussions with empirical evidence to the extent possible. We argue that under the right circumstances, self-reports, or an AI system's statements about its own internal states, could provide an avenue for investigating whether AI systems have states of moral significance. Self-reports are the main way such states are assessed in humans ("Are you in pain?"), but self-reports from current systems like large language models are spurious for many reasons (e.g. often just reflecting what humans would say). To make self-reports more appropriate for this purpose, we propose to train models to answer many kinds of questions about themselves with known answers, while avoiding or limiting training incentives that bias self-reports. The hope of this approach is that models will develop introspection-like capabilities, and that these capabilities will generalize to questions about states of moral significance. We then propose methods for assessing the extent to which these techniques have succeeded: evaluating self-report consistency across contexts and between similar models, measuring the confidence and resilience of models' self-reports, and using interpretability to corroborate self-reports. We also discuss challenges for our approach, from philosophical difficulties in interpreting self-reports to technical reasons why our proposal might fail. We hope our discussion inspires philosophers and AI researchers to criticize and improve our proposed methodology, as well as to run experiments to test whether self-reports can be made reliable enough to provide information about states of moral significance.
Authors: Arman H Ter-Petrosyan, Jenna A Bilbrey, Christina M Doty, Bethany E Matthews, Le Wang, Yingge Du, Eric Lang, Khalid Hattar, Steven R Spurgeon
We present a method for the unsupervised segmentation of electron microscopy images, which are powerful descriptors of materials and chemical systems. Images are oversegmented into overlapping chips, and similarity graphs are generated from embeddings extracted from a domain$\unicode{x2010}$pretrained convolutional neural network (CNN). The Louvain method for community detection is then applied to perform segmentation. The graph representation provides an intuitive way of presenting the relationship between chips and communities. We demonstrate our method to track irradiation$\unicode{x2010}$induced amorphous fronts in thin films used for catalysis and electronics. This method has potential for "on$\unicode{x2010}$the$\unicode{x2010}$fly" segmentation to guide emerging automated electron microscopes.
Authors: Yunsung Kim, Sreechan Sankaranarayanan, Chris Piech, Candace Thille
Dynamic Item Response Models extend the standard Item Response Theory (IRT) to capture temporal dynamics in learner ability. While these models have the potential to allow instructional systems to actively monitor the evolution of learner proficiency in real time, existing dynamic item response models rely on expensive inference algorithms that scale poorly to massive datasets. In this work, we propose Variational Temporal IRT (VTIRT) for fast and accurate inference of dynamic learner proficiency. VTIRT offers orders of magnitude speedup in inference runtime while still providing accurate inference. Moreover, the proposed algorithm is intrinsically interpretable by virtue of its modular design. When applied to 9 real student datasets, VTIRT consistently yields improvements in predicting future learner performance over other learner proficiency models.
Authors: Mohamed Osman, Tamer Nadeem, Ghada Khoriba
Recognizing emotions in spoken communication is crucial for advanced human-machine interaction. Current emotion detection methodologies often display biases when applied cross-corpus. To address this, our study amalgamates 16 diverse datasets, resulting in 375 hours of data across languages like English, Chinese, and Japanese. We propose a soft labeling system to capture gradational emotional intensities. Using the Whisper encoder and data augmentation methods inspired by contrastive learning, our method emphasizes the temporal dynamics of emotions. Our validation on four multilingual datasets demonstrates notable zero-shot generalization. We publish our open source model weights and initial promising results after fine-tuning on Hume-Prosody.
Authors: Itamar Zimerman, Moran Baruch, Nir Drucker, Gilad Ezov, Omri Soceanu, Lior Wolf
Designing privacy-preserving deep learning models is a major challenge within the deep learning community. Homomorphic Encryption (HE) has emerged as one of the most promising approaches in this realm, enabling the decoupling of knowledge between the model owner and the data owner. Despite extensive research and application of this technology, primarily in convolutional neural networks, incorporating HE into transformer models has been challenging because of the difficulties in converting these models into a polynomial form. We break new ground by introducing the first polynomial transformer, providing the first demonstration of secure inference over HE with transformers. This includes a transformer architecture tailored for HE, alongside a novel method for converting operators to their polynomial equivalent. This innovation enables us to perform secure inference on LMs with WikiText-103. It also allows us to perform image classification with CIFAR-100 and Tiny-ImageNet. Our models yield results comparable to traditional methods, bridging the performance gap with transformers of similar scale and underscoring the viability of HE for state-of-the-art applications. Finally, we assess the stability of our models and conduct a series of ablations to quantify the contribution of each model component.
Authors: Albert S. Berahas, Lindon Roberts, Fred Roosta
The analysis of gradient descent-type methods typically relies on the Lipschitz continuity of the objective gradient. This generally requires an expensive hyperparameter tuning process to appropriately calibrate a stepsize for a given problem. In this work we introduce a local first-order smoothness oracle (LFSO) which generalizes the Lipschitz continuous gradients smoothness condition and is applicable to any twice-differentiable function. We show that this oracle can encode all relevant problem information for tuning stepsizes for a suitably modified gradient descent method and give global and local convergence results. We also show that LFSOs in this modified first-order method can yield global linear convergence rates for non-strongly convex problems with extremely flat minima, and thus improve over the lower bound on rates achievable by general (accelerated) first-order methods.
Authors: William Fleshman, Benjamin Van Durme
Character-level language models obviate the need for separately trained tokenizers, but efficiency suffers from longer sequence lengths. Learning to combine character representations into tokens has made training these models more efficient, but they still require decoding characters individually. We propose Toucan, an augmentation to character-level models to make them "token-aware". Comparing our method to prior work, we demonstrate significant speed-ups in character generation without a loss in language modeling performance. We then explore differences between our learned dynamic tokenization of character sequences with popular fixed vocabulary solutions such as Byte-Pair Encoding and WordPiece, finding our approach leads to a greater amount of longer sequences tokenized as single items. Our project and code are available at https://nlp.jhu.edu/nuggets/.
Authors: Peng Tang, Srikar Appalaraju, R. Manmatha, Yusheng Xie, Vijay Mahadevan
We present Multiple-Question Multiple-Answer (MQMA), a novel approach to do text-VQA in encoder-decoder transformer models. The text-VQA task requires a model to answer a question by understanding multi-modal content: text (typically from OCR) and an associated image. To the best of our knowledge, almost all previous approaches for text-VQA process a single question and its associated content to predict a single answer. In order to answer multiple questions from the same image, each question and content are fed into the model multiple times. In contrast, our proposed MQMA approach takes multiple questions and content as input at the encoder and predicts multiple answers at the decoder in an auto-regressive manner at the same time. We make several novel architectural modifications to standard encoder-decoder transformers to support MQMA. We also propose a novel MQMA denoising pre-training task which is designed to teach the model to align and delineate multiple questions and content with associated answers. MQMA pre-trained model achieves state-of-the-art results on multiple text-VQA datasets, each with strong baselines. Specifically, on OCR-VQA (+2.5%), TextVQA (+1.4%), ST-VQA (+0.6%), DocVQA (+1.1%) absolute improvements over the previous state-of-the-art approaches.
Authors: Peng Tang, Pengkai Zhu, Tian Li, Srikar Appalaraju, Vijay Mahadevan, R. Manmatha
Encoder-decoder transformer models have achieved great success on various vision-language (VL) tasks, but they suffer from high inference latency. Typically, the decoder takes up most of the latency because of the auto-regressive decoding. To accelerate the inference, we propose an approach of performing Dynamic Early Exit on Decoder (DEED). We build a multi-exit encoder-decoder transformer model which is trained with deep supervision so that each of its decoder layers is capable of generating plausible predictions. In addition, we leverage simple yet practical techniques, including shared generation head and adaptation modules, to keep accuracy when exiting at shallow decoder layers. Based on the multi-exit model, we perform step-level dynamic early exit during inference, where the model may decide to use fewer decoder layers based on its confidence of the current layer at each individual decoding step. Considering different number of decoder layers may be used at different decoding steps, we compute deeper-layer decoder features of previous decoding steps just-in-time, which ensures the features from different decoding steps are semantically aligned. We evaluate our approach with two state-of-the-art encoder-decoder transformer models on various VL tasks. We show our approach can reduce overall inference latency by 30%-60% with comparable or even higher accuracy compared to baselines.
Authors: Guangyin Jin, Lingbo Liu, Fuxian Li, Jincai Huang
Traffic congestion event prediction is an important yet challenging task in intelligent transportation systems. Many existing works about traffic prediction integrate various temporal encoders and graph convolution networks (GCNs), called spatio-temporal graph-based neural networks, which focus on predicting dense variables such as flow, speed and demand in time snapshots, but they can hardly forecast the traffic congestion events that are sparsely distributed on the continuous time axis. In recent years, neural point process (NPP) has emerged as an appropriate framework for event prediction in continuous time scenarios. However, most conventional works about NPP cannot model the complex spatio-temporal dependencies and congestion evolution patterns. To address these limitations, we propose a spatio-temporal graph neural point process framework, named STGNPP for traffic congestion event prediction. Specifically, we first design the spatio-temporal graph learning module to fully capture the long-range spatio-temporal dependencies from the historical traffic state data along with the road network. The extracted spatio-temporal hidden representation and congestion event information are then fed into a continuous gated recurrent unit to model the congestion evolution patterns. In particular, to fully exploit the periodic information, we also improve the intensity function calculation of the point process with a periodic gated mechanism. Finally, our model simultaneously predicts the occurrence time and duration of the next congestion. Extensive experiments on two real-world datasets demonstrate that our method achieves superior performance in comparison to existing state-of-the-art approaches.
Authors: Keunsu Kim, Hanbaek Lyu, Jinsu Kim, Jae-Hun Jung
We propose a novel methodology for forecasting spatio-temporal data using supervised semi-nonnegative matrix factorization (SSNMF) with frequency regularization. Matrix factorization is employed to decompose spatio-temporal data into spatial and temporal components. To improve clarity in the temporal patterns, we introduce a nonnegativity constraint on the time domain along with regularization in the frequency domain. Specifically, regularization in the frequency domain involves selecting features in the frequency space, making an interpretation in the frequency domain more convenient. We propose two methods in the frequency domain: soft and hard regularizations, and provide convergence guarantees to first-order stationary points of the corresponding constrained optimization problem. While our primary motivation stems from geophysical data analysis based on GRACE (Gravity Recovery and Climate Experiment) data, our methodology has the potential for wider application. Consequently, when applying our methodology to GRACE data, we find that the results with the proposed methodology are comparable to previous research in the field of geophysical sciences but offer clearer interpretability.
Authors: Jiachen Zhao, Wenlong Zhao, Andrew Drozdov, Benjamin Rozonoyer, Md Arafat Sultan, Jay-Yoon Lee, Mohit Iyyer, Andrew McCallum
We study semi-supervised sequence prediction tasks where labeled data are too scarce to effectively finetune a model and at the same time few-shot prompting of a large language model (LLM) has suboptimal performance. This happens when a task, such as parsing, is expensive to annotate and also unfamiliar to a pretrained LLM. In this paper, we present a discovery that student models distilled from a prompted LLM can often generalize better than their teacher on such tasks. Leveraging this finding, we propose a new distillation method, multistage collaborative knowledge distillation from an LLM (MCKD), for such tasks. MCKD first prompts an LLM using few-shot in-context learning to produce pseudolabels for unlabeled data. Then, at each stage of distillation, a pair of students are trained on disjoint partitions of the pseudolabeled data. Each student subsequently produces new and improved pseudolabels for the unseen partition to supervise the next round of student(s) with. We show the benefit of multistage cross-partition labeling on two constituency parsing tasks. On CRAFT biomedical parsing, 3-stage MCKD with 50 labeled examples matches the performance of supervised finetuning with 500 examples and outperforms the prompted LLM and vanilla KD by 7.5% and 3.7% parsing F1, respectively.
Authors: Yiheng Su, Juni Jessy Li, Matthew Lease
Can we preserve the accuracy of neural models while also providing faithful explanations? We present wrapper boxes, a general approach to generate faithful, example-based explanations for model predictions while maintaining predictive performance. After training a neural model as usual, its learned feature representation is input to a classic, interpretable model to perform the actual prediction. This simple strategy is surprisingly effective, with results largely comparable to those of the original neural model, as shown across three large pre-trained language models, two datasets of varying scale, four classic models, and four evaluation metrics. Moreover, because these classic models are interpretable by design, the subset of training examples that determine classic model predictions can be shown directly to users.
Authors: Wenhao Tang, Junding Sun, Shuihua Wang, Yudong Zhang
In recent years, the rapid development of deep learning has led to a wide range of applications in the field of medical image classification. The variants of neural network models with ever-increasing performance share some commonalities: to try to mitigate overfitting, improve generalization, avoid gradient vanishing and exploding, etc. AlexNet first utilizes the dropout technique to mitigate overfitting and the ReLU activation function to avoid gradient vanishing. Therefore, we focus our discussion on AlexNet, which has contributed greatly to the development of CNNs in 2012. After reviewing over 40 papers, including journal papers and conference papers, we give a narrative on the technical details, advantages, and application areas of AlexNet.
Authors: Mirali Purohit, Jacob Adler, Hannah Kerner
Over the years, space scientists have collected terabytes of Mars data from satellites and rovers. One important set of features identified in Mars orbital images is pitted cones, which are interpreted to be mud volcanoes believed to form in regions that were once saturated in water (i.e., a lake or ocean). Identifying pitted cones globally on Mars would be of great importance, but expert geologists are unable to sort through the massive orbital image archives to identify all examples. However, this task is well suited for computer vision. Although several computer vision datasets exist for various Mars-related tasks, there is currently no open-source dataset available for cone detection/segmentation. Furthermore, previous studies trained models using data from a single region, which limits their applicability for global detection and mapping. Motivated by this, we introduce ConeQuest, the first expert-annotated public dataset to identify cones on Mars. ConeQuest consists of >13k samples from 3 different regions of Mars. We propose two benchmark tasks using ConeQuest: (i) Spatial Generalization and (ii) Cone-size Generalization. We finetune and evaluate widely-used segmentation models on both benchmark tasks. Results indicate that cone segmentation is a challenging open problem not solved by existing segmentation models, which achieve an average IoU of 52.52% and 42.55% on in-distribution data for tasks (i) and (ii), respectively. We believe this new benchmark dataset will facilitate the development of more accurate and robust models for cone segmentation. Data and code are available at https://github.com/kerner-lab/ConeQuest.
Authors: Li Xu, Yili Hong, Eric P. Smith, David S. McLeod, Xinwei Deng, Laura J. Freeman
As is true of many complex tasks, the work of discovering, describing, and understanding the diversity of life on Earth (viz., biological systematics and taxonomy) requires many tools. Some of this work can be accomplished as it has been done in the past, but some aspects present us with challenges which traditional knowledge and tools cannot adequately resolve. One such challenge is presented by species complexes in which the morphological similarities among the group members make it difficult to reliably identify known species and detect new ones. We address this challenge by developing new tools using the principles of machine learning to resolve two specific questions related to species complexes. The first question is formulated as a classification problem in statistics and machine learning and the second question is an out-of-distribution (OOD) detection problem. We apply these tools to a species complex comprising Southeast Asian stream frogs (Limnonectes kuhlii complex) and employ a morphological character (hind limb skin texture) traditionally treated qualitatively in a quantitative and objective manner. We demonstrate that deep neural networks can successfully automate the classification of an image into a known species group for which it has been trained. We further demonstrate that the algorithm can successfully classify an image into a new class if the image does not belong to the existing classes. Additionally, we use the larger MNIST dataset to test the performance of our OOD detection algorithm. We finish our paper with some concluding remarks regarding the application of these methods to species complexes and our efforts to document true biodiversity. This paper has online supplementary materials.
Authors: Kokil Jaidka, Hansin Ahuja, Lynnette Ng
Online games are dynamic environments where players interact with each other, which offers a rich setting for understanding how players negotiate their way through the game to an ultimate victory. This work studies online player interactions during the turn-based strategy game, Diplomacy. We annotated a dataset of over 10,000 chat messages for different negotiation strategies and empirically examined their importance in predicting long- and short-term game outcomes. Although negotiation strategies can be predicted reasonably accurately through the linguistic modeling of the chat messages, more is needed for predicting short-term outcomes such as trustworthiness. On the other hand, they are essential in graph-aware reinforcement learning approaches to predict long-term outcomes, such as a player's success, based on their prior negotiation history. We close with a discussion of the implications and impact of our work. The dataset is available at https://github.com/kj2013/claff-diplomacy.
Authors: Yahan Yang, Soham Dan, Dan Roth, Insup Lee
Multilingual pre-trained language models are incredibly effective at Question Answering (QA), a core task in Natural Language Understanding, achieving high accuracies on several multilingual benchmarks. However, little is known about how well they are calibrated. In this paper, we study the calibration properties of several pre-trained multilingual large language models (LLMs) on a variety of question-answering tasks. We perform extensive experiments, spanning both extractive and generative QA model designs and diverse languages, spanning both high-resource and low-resource ones. We study different dimensions of calibration in in-distribution, out-of-distribution, and cross-lingual transfer settings, and investigate strategies to improve it, including post-hoc methods and regularized fine-tuning. We demonstrate automatically translated data augmentation as a highly effective technique to improve model calibration. We also conduct a number of ablation experiments to study the effect of model size on calibration and how multilingual models compare with their monolingual counterparts for diverse tasks and languages.
Authors: Xiaobo Xia, Jiale Liu, Shaokun Zhang, Qingyun Wu, Tongliang Liu
Coreset selection is powerful in reducing computational costs and accelerating data processing for deep learning algorithms. It strives to identify a small subset from large-scale data, so that training only on the subset practically performs on par with full data. When coreset selection is applied in realistic scenes, under the premise that the identified coreset has achieved comparable model performance, practitioners regularly desire the identified coreset can have a size as small as possible for lower costs and greater acceleration. Motivated by this desideratum, for the first time, we pose the problem of "coreset selection with prioritized multiple objectives", in which the smallest coreset size under model performance constraints is explored. Moreover, to address this problem, an innovative method is proposed, which maintains optimization priority order over the model performance and coreset size, and efficiently optimizes them in the coreset selection procedure. Theoretically, we provide the convergence guarantee of the proposed method. Empirically, extensive experiments confirm its superiority compared with previous strategies, often yielding better model performance with smaller coreset sizes.
Authors: Sin Cheng Ciou, Pin Jui Chen, Elvin Y. Tseng, Yuh-Jye Lee
In the rapidly evolving realm of machine learning, algorithm effectiveness often faces limitations due to data quality and availability. Traditional approaches grapple with data sharing due to legal and privacy concerns. The federated learning framework addresses this challenge. Federated learning is a decentralized approach where model training occurs on client sides, preserving privacy by keeping data localized. Instead of sending raw data to a central server, only model updates are exchanged, enhancing data security. We apply this framework to Sparse Principal Component Analysis (SPCA) in this work. SPCA aims to attain sparse component loadings while maximizing data variance for improved interpretability. Beside the L1 norm regularization term in conventional SPCA, we add a smoothing function to facilitate gradient-based optimization methods. Moreover, in order to improve computational efficiency, we introduce a least squares approximation to original SPCA. This enables analytic solutions on the optimization processes, leading to substantial computational improvements. Within the federated framework, we formulate SPCA as a consensus optimization problem, which can be solved using the Alternating Direction Method of Multipliers (ADMM). Our extensive experiments involve both IID and non-IID random features across various data owners. Results on synthetic and public datasets affirm the efficacy of our federated SPCA approach.
Authors: Keith Harrigian, Tina Tang, Anthony Gonzales, Cindy X. Cai, Mark Dredze
Diabetic eye disease is a major cause of blindness worldwide. The ability to monitor relevant clinical trajectories and detect lapses in care is critical to managing the disease and preventing blindness. Alas, much of the information necessary to support these goals is found only in the free text of the electronic medical record. To fill this information gap, we introduce a system for extracting evidence from clinical text of 19 clinical concepts related to diabetic eye disease and inferring relevant attributes for each. In developing this ophthalmology phenotyping system, we are also afforded a unique opportunity to evaluate the effectiveness of clinical language models at adapting to new clinical domains. Across multiple training paradigms, we find that BERT language models pretrained on out-of-distribution clinical data offer no significant improvement over BERT language models pretrained on non-clinical data for our domain. Our study tempers recent claims that language models pretrained on clinical data are necessary for clinical NLP tasks and highlights the importance of not treating clinical language data as a single homogeneous domain.
Authors: Yanlin Qi, Jia Li, Michael Zhang
Precise estimation of Crash Modification Factors (CMFs) is central to evaluating the effectiveness of various road safety treatments and prioritizing infrastructure investment accordingly. While customized study for each countermeasure scenario is desired, the conventional CMF estimation approaches rely heavily on the availability of crash data at given sites. This not only makes the estimation costly, but the results are also less transferable, since the intrinsic similarities between different safety countermeasure scenarios are not fully explored. Aiming to fill this gap, this study introduces a novel knowledge-mining framework for CMF prediction. This framework delves into the connections of existing countermeasures and reduces the reliance of CMF estimation on crash data availability and manual data collection. Specifically, it draws inspiration from human comprehension processes and introduces advanced Natural Language Processing (NLP) techniques to extract intricate variations and patterns from existing CMF knowledge. It effectively encodes unstructured countermeasure scenarios into machine-readable representations and models the complex relationships between scenarios and CMF values. This new data-driven framework provides a cost-effective and adaptable solution that complements the case-specific approaches for CMF estimation, which is particularly beneficial when availability of crash data or time imposes constraints. Experimental validation using real-world CMF Clearinghouse data demonstrates the effectiveness of this new approach, which shows significant accuracy improvements compared to baseline methods. This approach provides insights into new possibilities of harnessing accumulated transportation knowledge in various applications.
Authors: Keming Lu, Hongyi Yuan, Runji Lin, Junyang Lin, Zheng Yuan, Chang Zhou, Jingren Zhou
The complementary potential of Large Language Models (LLM) assumes off-the-shelf LLMs have heterogeneous expertise in a wide range of domains and tasks so that an ensemble of LLMs can achieve consistently better performance. Existing ensemble methods for LLMs mainly focus on reward model ranking of outputs, leading to significant computation overhead. To combat this issue, we revisit the complementary potential of LLMs and further elaborate it by mining latent expertise with off-the-shelf reward models. We propose Zooter, a reward-guided routing method distilling rewards on training queries to train a routing function, which can precisely distribute each query to the LLM with expertise about it. We also integrate a tag-based label enhancement to mitigate noise from uncertainty when using rewards as silver supervision. Zooter shows computation efficiency in inference as it introduces only a minor computation overhead of a routing function compared with reward model ranking methods. We evaluate Zooter on a comprehensive benchmark collection with 26 subsets on different domains and tasks. Zooter outperforms the best single model on average and ranks first on 44% of tasks, even surpassing multiple reward model ranking methods.
Authors: Ian Berlot-Attwell, A. Michael Carrell, Kumar Krishna Agrawal, Yash Sharma, Naomi Saphra
The degree to which neural networks can generalize to new combinations of familiar concepts, and the conditions under which they are able to do so, has long been an open question. In this work, we study the systematicity gap in visual question answering: the performance difference between reasoning on previously seen and unseen combinations of object attributes. To test, we introduce a novel diagnostic dataset, CLEVR-HOPE. We find that while increased quantity of training data does not reduce the systematicity gap, increased training data diversity of the attributes in the unseen combination does. In all, our experiments suggest that the more distinct attribute type combinations are seen during training, the more systematic we can expect the resulting model to be.
Authors: Shuhei Nitta, Taiji Suzuki, Albert Rodríguez Mulet, Atsushi Yaguchi, Ryusuke Hirai
Federated learning is a privacy-preserving training method which consists of training from a plurality of clients but without sharing their confidential data. However, previous work on federated learning do not explore suitable neural network architectures for clients with different input images sizes and different numbers of output categories. In this paper, we propose an effective federated learning method named ScalableFL, where the depths and widths of the local models for each client are adjusted according to the clients' input image size and the numbers of output categories. In addition, we provide a new bound for the generalization gap of federated learning. In particular, this bound helps to explain the effectiveness of our scalable neural network approach. We demonstrate the effectiveness of ScalableFL in several heterogeneous client settings for both image classification and object detection tasks.
Authors: Xiang Li, Che Wang, Bing Li, Hao Chen, Sizhe Li
The proposed method for linking entities in power distribution dispatch texts to a power distribution network knowledge graph is based on a deep understanding of these networks. This method leverages the unique features of entities in both the power distribution network's knowledge graph and the dispatch texts, focusing on their semantic, phonetic, and syntactic characteristics. An enhanced model, the Lexical Semantic Feature-based Skip Convolutional Neural Network (LSF-SCNN), is utilized for effectively matching dispatch text entities with those in the knowledge graph. The efficacy of this model, compared to a control model, is evaluated through cross-validation methods in real-world power distribution dispatch scenarios. The results indicate that the LSF-SCNN model excels in accurately linking a variety of entity types, demonstrating high overall accuracy in entity linking when the process is conducted in English.
Authors: Yunqin Zhu, Chao Wang, Hui Xiong
Recovering masked feedback with neural models is a popular paradigm in recommender systems. Seeing the success of diffusion models in solving ill-posed inverse problems, we introduce a conditional diffusion framework for collaborative filtering that iteratively reconstructs a user's hidden preferences guided by its historical interactions. To better align with the intrinsic characteristics of implicit feedback data, we implement forward diffusion by applying synthetic smoothing filters to interaction signals on an item-item graph. The resulting reverse diffusion can be interpreted as a personalized process that gradually refines preference scores. Through graph Fourier transform, we equivalently characterize this model as an anisotropic Gaussian diffusion in the graph spectral domain, establishing both forward and reverse formulations. Our model outperforms state-of-the-art methods by a large margin on one dataset and yields competitive results on the others.
Authors: Naoki Sato, Hideaki Iiduka
The graduated optimization approach is a heuristic method for finding globally optimal solutions for nonconvex functions and has been theoretically analyzed in several studies. This paper defines a new family of nonconvex functions for graduated optimization, discusses their sufficient conditions, and provides a convergence analysis of the graduated optimization algorithm for them. It shows that stochastic gradient descent (SGD) with mini-batch stochastic gradients has the effect of smoothing the function, the degree of which is determined by the learning rate and batch size. This finding provides theoretical insights from a graduated optimization perspective on why large batch sizes fall into sharp local minima, why decaying learning rates and increasing batch sizes are superior to fixed learning rates and batch sizes, and what the optimal learning rate scheduling is. To the best of our knowledge, this is the first paper to provide a theoretical explanation for these aspects. Moreover, a new graduated optimization framework that uses a decaying learning rate and increasing batch size is analyzed and experimental results of image classification that support our theoretical findings are reported.
Authors: Xuyao Yu, Jiazhao Wang, Wenchao Jiang
The ageing society brings attention to daily elderly care through sensing technologies. The future smart home is expected to enable in-home daily monitoring, such as fall detection, for seniors in a non-invasive, non-cooperative, and non-contact manner. The mmWave radar is a promising candidate technology for its privacy-preserving and non-contact manner. However, existing solutions suffer from low accuracy and robustness due to environment dependent features. In this paper, we present FADE (\underline{FA}ll \underline{DE}tection), a practical fall detection radar system with enhanced accuracy and robustness in real-world scenarios. The key enabler underlying FADE is an interacting multiple model (IMM) state estimator that can extract environment-independent features for highly accurate and instantaneous fall detection. Furthermore, we proposed a robust multiple-user tracking system to deal with noises from the environment and other human bodies. We deployed our algorithm on low computing power and low power consumption system-on-chip (SoC) composed of data front end, DSP, and ARM processor, and tested its performance in real-world. The experiment shows that the accuracy of fall detection is up to 95\%.
Authors: Hesham Ali, Idriss Tondji, Mennatullah Siam
AI-assisted nuclei segmentation in histopathological images is a crucial task in the diagnosis and treatment of cancer diseases. It decreases the time required to manually screen microscopic tissue images and can resolve the conflict between pathologists during diagnosis. Deep Learning has proven useful in such a task. However, lack of labeled data is a significant barrier for deep learning-based approaches. In this study, we propose a novel approach to nuclei segmentation that leverages the available labelled and unlabelled data. The proposed method combines the strengths of both transductive and inductive learning, which have been previously attempted separately, into a single framework. Inductive learning aims at approximating the general function and generalizing to unseen test data, while transductive learning has the potential of leveraging the unlabelled test data to improve the classification. To the best of our knowledge, this is the first study to propose such a hybrid approach for medical image segmentation. Moreover, we propose a novel two-stage transductive inference scheme. We evaluate our approach on MoNuSeg benchmark to demonstrate the efficacy and potential of our method.
Authors: Minqian Liu, Ying Shen, Zhiyang Xu, Yixin Cao, Eunah Cho, Vaibhav Kumar, Reza Ghanadan, Lifu Huang
Natural Language Generation (NLG) typically involves evaluating the generated text in various aspects (e.g., consistency and naturalness) to obtain a comprehensive assessment. However, multi-aspect evaluation remains challenging as it may require the evaluator to generalize to any given evaluation aspect even if it's absent during training. In this paper, we introduce X-Eval, a two-stage instruction tuning framework to evaluate the text in both seen and unseen aspects customized by end users. X-Eval consists of two learning stages: the vanilla instruction tuning stage that improves the model's ability to follow evaluation instructions, and an enhanced instruction tuning stage that exploits the connections between fine-grained evaluation aspects to better assess text quality. To support the training of X-Eval, we collect AspectInstruct, the first instruction tuning dataset tailored for multi-aspect NLG evaluation spanning 27 diverse evaluation aspects with 65 tasks. To enhance task diversity, we devise an augmentation strategy that converts human rating annotations into diverse forms of NLG evaluation tasks, including scoring, comparison, ranking, and Boolean question answering. Extensive experiments across three essential categories of NLG tasks: dialogue generation, summarization, and data-to-text coupled with 21 aspects in meta-evaluation, demonstrate that our X-Eval enables even a lightweight language model to achieve a comparable if not higher correlation with human judgments compared to the state-of-the-art NLG evaluators, such as GPT-4.
Authors: Cian Eastwood, Julius von Kügelgen, Linus Ericsson, Diane Bouchacourt, Pascal Vincent, Bernhard Schölkopf, Mark Ibrahim
Self-supervised representation learning often uses data augmentations to induce some invariance to "style" attributes of the data. However, with downstream tasks generally unknown at training time, it is difficult to deduce a priori which attributes of the data are indeed "style" and can be safely discarded. To address this, we introduce a more principled approach that seeks to disentangle style features rather than discard them. The key idea is to add multiple style embedding spaces where: (i) each is invariant to all-but-one augmentation; and (ii) joint entropy is maximized. We formalize our structured data-augmentation procedure from a causal latent-variable-model perspective, and prove identifiability of both content and (multiple blocks of) style variables. We empirically demonstrate the benefits of our approach on synthetic datasets and then present promising but limited results on ImageNet.
Authors: Davis Yoshida, Kartik Goyal, Kevin Gimpel
It has been widely observed that exact or approximate MAP (mode-seeking) decoding from natural language generation (NLG) models consistently leads to degenerate outputs (Stahlberg and Byrne, 2019, Holtzman et al., 2019). This has generally been attributed to either a fundamental inadequacy of modes in models or weaknesses in language modeling. Contrastingly in this work, we emphasize that degenerate modes can even occur in the absence of any model error, due to contamination of the training data. Specifically, we show that mixing even a tiny amount of low-entropy noise with a population text distribution can cause the data distribution's mode to become degenerate, implying that any models trained on it will be as well. As the unconditional mode of NLG models will often be degenerate, we therefore propose to apply MAP decoding to the model's distribution conditional on avoiding specific degeneracies. Using exact-search, we empirically verify that the length-conditional modes of machine translation models and language models are indeed more fluent and topical than their unconditional modes. For the first time, we also share many examples of exact modal sequences from these models, and from several variants of the LLaMA-7B model. Notably, the modes of the LLaMA models are still degenerate, showing that improvements in modeling have not fixed this issue. Because of the cost of exact mode finding algorithms, we develop an approximate mode finding approach, ACBS, which finds sequences that are both high-likelihood and high-quality. We apply this approach to LLaMA-7B, a model which was not trained for instruction following, and find that we are able to elicit reasonable outputs without any finetuning.
Authors: Donghyeok Shin, Seungjae Shin, Il-Chul Moon
This paper presents FreD, a novel parameterization method for dataset distillation, which utilizes the frequency domain to distill a small-sized synthetic dataset from a large-sized original dataset. Unlike conventional approaches that focus on the spatial domain, FreD employs frequency-based transforms to optimize the frequency representations of each data instance. By leveraging the concentration of spatial domain information on specific frequency components, FreD intelligently selects a subset of frequency dimensions for optimization, leading to a significant reduction in the required budget for synthesizing an instance. Through the selection of frequency dimensions based on the explained variance, FreD demonstrates both theoretical and empirical evidence of its ability to operate efficiently within a limited budget, while better preserving the information of the original dataset compared to conventional parameterization methods. Furthermore, based on the orthogonal compatibility of FreD with existing methods, we confirm that FreD consistently improves the performances of existing distillation methods over the evaluation scenarios with different benchmark datasets. We release the code at https://github.com/sdh0818/FreD.
Authors: Felix Abramovich
We consider a deep neural network estimator based on empirical risk minimization with l_1-regularization. We derive a general bound for its excess risk in regression and classification (including multiclass), and prove that it is adaptively nearly-minimax (up to log-factors) simultaneously across the entire range of various function classes.
Authors: Aviv Shamsian, David W. Zhang, Aviv Navon, Yan Zhang, Miltiadis Kofinas, Idan Achituve, Riccardo Valperga, Gertjan J. Burghouts, Efstratios Gavves, Cees G. M. Snoek, Ethan Fetaya, Gal Chechik, Haggai Maron
Learning in weight spaces, where neural networks process the weights of other deep neural networks, has emerged as a promising research direction with applications in various fields, from analyzing and editing neural fields and implicit neural representations, to network pruning and quantization. Recent works designed architectures for effective learning in that space, which takes into account its unique, permutation-equivariant, structure. Unfortunately, so far these architectures suffer from severe overfitting and were shown to benefit from large datasets. This poses a significant challenge because generating data for this learning setup is laborious and time-consuming since each data sample is a full set of network weights that has to be trained. In this paper, we address this difficulty by investigating data augmentations for weight spaces, a set of techniques that enable generating new data examples on the fly without having to train additional input weight space elements. We first review several recently proposed data augmentation schemes %that were proposed recently and divide them into categories. We then introduce a novel augmentation scheme based on the Mixup method. We evaluate the performance of these techniques on existing benchmarks as well as new benchmarks we generate, which can be valuable for future studies.
Authors: Mingzhao Yang, Shangchao Su, Bin Li, Xiangyang Xue
One-shot federated learning (OSFL) has gained attention in recent years due to its low communication cost. However, most of the existing methods require auxiliary datasets or training generators, which hinders their practicality in real-world scenarios. In this paper, we explore the novel opportunities that diffusion models bring to OSFL and propose FedCADO, utilizing guidance from client classifiers to generate data that complies with clients' distributions and subsequently training the aggregated model on the server. Specifically, our method involves targeted optimizations in two aspects. On one hand, we conditionally edit the randomly sampled initial noises, embedding them with specified semantics and distributions, resulting in a significant improvement in both the quality and stability of generation. On the other hand, we employ the BN statistics from the classifiers to provide detailed guidance during generation. These tailored optimizations enable us to limitlessly generate datasets, which closely resemble the distribution and quality of the original client dataset. Our method effectively handles the heterogeneous client models and the problems of non-IID features or labels. In terms of privacy protection, our method avoids training any generator or transferring any auxiliary information on clients, eliminating any additional privacy leakage risks. Leveraging the extensive knowledge stored in the pre-trained diffusion model, the synthetic datasets can assist us in surpassing the knowledge limitations of the client samples, resulting in aggregation models that even outperform the performance ceiling of centralized training in some cases, which is convincingly demonstrated in the sufficient quantification and visualization experiments conducted on three large-scale multi-domain image datasets.
Authors: Katharina Hechinger, Christoph Koller, Xiao Xiang Zhu, Göran Kauermann
Uncertainty quantification in machine learning is a timely and vast field of research. In supervised learning, uncertainty can already occur in the very first stage of the training process, the labelling step. In particular, this is the case when not every instance can be unambiguously classified. The problem occurs for classifying instances, where classes may overlap or instances can not be clearly categorised. In other words, there is inevitable ambiguity in the annotation step and not necessarily a 'ground truth'. We look exemplary at the classification of satellite images. Each image is annotated independently by multiple labellers and classified into local climate zones (LCZs). For each instance we have multiple votes, leading to a distribution of labels rather than a single value. The main idea of this work is that we do not assume a ground truth label but embed the votes into a K-dimensional space, with K as the number of possible categories. The embedding is derived from the voting distribution in a Bayesian setup, modelled via a Dirichlet-Multinomial model. We estimate the model and posteriors using a stochastic Expectation Maximisation algorithm with Markov Chain Monte Carlo steps. While we focus on the particular example of LCZ classification, the methods developed in this paper readily extend to other situations where multiple annotators independently label texts or images. We also apply our approach to two other benchmark datasets for image classification to demonstrate this. Besides the embeddings themselves, we can investigate the resulting correlation matrices, which can be seen as generalised confusion matrices and reflect the semantic similarities of the original classes very well for all three exemplary datasets. The insights gained are valuable and can serve as general label embedding if a single ground truth per observation cannot be guaranteed.
Authors: Vaishnavi Shrivastava, Percy Liang, Ananya Kumar
To maintain user trust, large language models (LLMs) should signal low confidence on examples where they are incorrect, instead of misleading the user. The standard approach of estimating confidence is to use the softmax probabilities of these models, but as of November 2023, state-of-the-art LLMs such as GPT-4 and Claude-v1.3 do not provide access to these probabilities. We first study eliciting confidence linguistically -- asking an LLM for its confidence in its answer -- which performs reasonably (80.5% AUC on GPT-4 averaged across 12 question-answering datasets -- 7% above a random baseline) but leaves room for improvement. We then explore using a surrogate confidence model -- using a model where we do have probabilities to evaluate the original model's confidence in a given question. Surprisingly, even though these probabilities come from a different and often weaker model, this method leads to higher AUC than linguistic confidences on 9 out of 12 datasets. Our best method composing linguistic confidences and surrogate model probabilities gives state-of-the-art confidence estimates on all 12 datasets (84.6% average AUC on GPT-4).
Authors: Rita Kuznetsova, Alizée Pace, Manuel Burger, Hugo Yèche, Gunnar Rätsch
Recent advances in deep learning architectures for sequence modeling have not fully transferred to tasks handling time-series from electronic health records. In particular, in problems related to the Intensive Care Unit (ICU), the state-of-the-art remains to tackle sequence classification in a tabular manner with tree-based methods. Recent findings in deep learning for tabular data are now surpassing these classical methods by better handling the severe heterogeneity of data input features. Given the similar level of feature heterogeneity exhibited by ICU time-series and motivated by these findings, we explore these novel methods' impact on clinical sequence modeling tasks. By jointly using such advances in deep learning for tabular data, our primary objective is to underscore the importance of step-wise embeddings in time-series modeling, which remain unexplored in machine learning methods for clinical data. On a variety of clinically relevant tasks from two large-scale ICU datasets, MIMIC-III and HiRID, our work provides an exhaustive analysis of state-of-the-art methods for tabular time-series as time-step embedding models, showing overall performance improvement. In particular, we evidence the importance of feature grouping in clinical time-series, with significant performance gains when considering features within predefined semantic groups in the step-wise embedding module.
Authors: Perry Gibson, José Cano, Elliot J. Crowley, Amos Storkey, Michael O'Boyle
Deep Neural Networks (DNNs) are extremely computationally demanding, which presents a large barrier to their deployment on resource-constrained devices. Since such devices are where many emerging deep learning applications lie (e.g., drones, vision-based medical technology), significant bodies of work from both the machine learning and systems communities have attempted to provide optimizations to accelerate DNNs. To help unify these two perspectives, in this paper we combine machine learning and systems techniques within the Deep Learning Acceleration Stack (DLAS), and demonstrate how these layers can be tightly dependent on each other with an across-stack perturbation study. We evaluate the impact on accuracy and inference time when varying different parameters of DLAS across two datasets, seven popular DNN architectures, four DNN compression techniques, three algorithmic primitives with sparse and dense variants, untuned and auto-scheduled code generation, and four hardware platforms. Our evaluation highlights how perturbations across DLAS parameters can cause significant variation and across-stack interactions. The highest level observation from our evaluation is that the model size, accuracy, and inference time are not guaranteed to be correlated. Overall we make 13 key observations, including that speedups provided by compression techniques are very hardware dependent, and that compiler auto-tuning can significantly alter what the best algorithm to use for a given configuration is. With DLAS, we aim to provide a reference framework to aid machine learning and systems practitioners in reasoning about the context in which their respective DNN acceleration solutions exist in. With our evaluation strongly motivating the need for co-design, we believe that DLAS can be a valuable concept for exploring the next generation of co-designed accelerated deep learning solutions.
Authors: Sadegh Khorasani, Saber Salehkaleybar, Negar Kiyavash, Niao He, Matthias Grossglauser
Policy gradient (PG) is widely used in reinforcement learning due to its scalability and good performance. In recent years, several variance-reduced PG methods have been proposed with a theoretical guarantee of converging to an approximate first-order stationary point (FOSP) with the sample complexity of $O(\epsilon^{-3})$. However, FOSPs could be bad local optima or saddle points. Moreover, these algorithms often use importance sampling (IS) weights which could impair the statistical effectiveness of variance reduction. In this paper, we propose a variance-reduced second-order method that uses second-order information in the form of Hessian vector products (HVP) and converges to an approximate second-order stationary point (SOSP) with sample complexity of $\tilde{O}(\epsilon^{-3})$. This rate improves the best-known sample complexity for achieving approximate SOSPs by a factor of $O(\epsilon^{-0.5})$. Moreover, the proposed variance reduction technique bypasses IS weights by using HVP terms. Our experimental results show that the proposed algorithm outperforms the state of the art and is more robust to changes in random seeds.
Authors: Yixiu Mao, Hongchang Zhang, Chen Chen, Yi Xu, Xiangyang Ji
Offline reinforcement learning suffers from the out-of-distribution issue and extrapolation error. Most policy constraint methods regularize the density of the trained policy towards the behavior policy, which is too restrictive in most cases. We propose Supported Trust Region optimization (STR) which performs trust region policy optimization with the policy constrained within the support of the behavior policy, enjoying the less restrictive support constraint. We show that, when assuming no approximation and sampling error, STR guarantees strict policy improvement until convergence to the optimal support-constrained policy in the dataset. Further with both errors incorporated, STR still guarantees safe policy improvement for each step. Empirical results validate the theory of STR and demonstrate its state-of-the-art performance on MuJoCo locomotion domains and much more challenging AntMaze domains.
Authors: Ahmed Emam, Mohamed Farag, Ribana Roscher
Protected natural areas are regions that have been minimally affected by human activities such as urbanization, agriculture, and other human interventions. To better understand and map the naturalness of these areas, machine learning models can be used to analyze satellite imagery. Specifically, explainable machine learning methods show promise in uncovering patterns that contribute to the concept of naturalness within these protected environments. Additionally, addressing the uncertainty inherent in machine learning models is crucial for a comprehensive understanding of this concept. However, existing approaches have limitations. They either fail to provide explanations that are both valid and objective or struggle to offer a quantitative metric that accurately measures the contribution of specific patterns to naturalness, along with the associated confidence. In this paper, we propose a novel framework called the Confident Naturalness Explanation (CNE) framework. This framework combines explainable machine learning and uncertainty quantification to assess and explain naturalness. We introduce a new quantitative metric that describes the confident contribution of patterns to the concept of naturalness. Furthermore, we generate an uncertainty-aware segmentation mask for each input sample, highlighting areas where the model lacks knowledge. To demonstrate the effectiveness of our framework, we apply it to a study site in Fennoscandia using two open-source satellite datasets.
Authors: Youran Dong, Shiqian Ma, Junfeng Yang, Chao Yin
Bilevel optimization has received more and more attention recently due to its wide applications in machine learning. In this paper, we consider bilevel optimization in decentralized networks. In particular, we propose a novel single-loop algorithm for solving decentralized bilevel optimization with strongly convex lower level problem. Our algorithm is fully single-loop and does not require heavy matrix-vector multiplications when approximating the hypergradient. Moreover, unlike existing methods for decentralized bilevel optimization and federated bilevel optimization, our algorithm does not require any gradient heterogeneity assumption. Our analysis shows that the proposed algorithm achieves the best known convergence rate for bilevel optimization algorithms.
Authors: Jonas Ammeling, Moritz Hecker, Jonathan Ganz, Taryn A. Donovan, Christof A. Bertram, Katharina Breininger, Marc Aubreville
The volume-corrected mitotic index (M/V-Index) was shown to provide prognostic value in invasive breast carcinomas. However, despite its prognostic significance, it is not established as the standard method for assessing aggressive biological behaviour, due to the high additional workload associated with determining the epithelial proportion. In this work, we show that using a deep learning pipeline solely trained with an annotation-free, immunohistochemistry-based approach, provides accurate estimations of epithelial segmentation in canine breast carcinomas. We compare our automatic framework with the manually annotated M/V-Index in a study with three board-certified pathologists. Our results indicate that the deep learning-based pipeline shows expert-level performance, while providing time efficiency and reproducibility.
Authors: Marcello Carioni, Subhadip Mukherjee, Hong Ye Tan, Junqi Tang
Unsupervised deep learning approaches have recently become one of the crucial research areas in imaging owing to their ability to learn expressive and powerful reconstruction operators even when paired high-quality training data is scarcely available. In this chapter, we review theoretically principled unsupervised learning schemes for solving imaging inverse problems, with a particular focus on methods rooted in optimal transport and convex analysis. We begin by reviewing the optimal transport-based unsupervised approaches such as the cycle-consistency-based models and learned adversarial regularization methods, which have clear probabilistic interpretations. Subsequently, we give an overview of a recent line of works on provably convergent learned optimization algorithms applied to accelerate the solution of imaging inverse problems, alongside their dedicated unsupervised training schemes. We also survey a number of provably convergent plug-and-play algorithms (based on gradient-step deep denoisers), which are among the most important and widely applied unsupervised approaches for imaging problems. At the end of this survey, we provide an overview of a few related unsupervised learning frameworks that complement our focused schemes. Together with a detailed survey, we provide an overview of the key mathematical results that underlie the methods reviewed in the chapter to keep our discussion self-contained.
Authors: Ricardo Ferreira, Cláudia Soares, Marta Guimarães
The proliferation of space debris in LEO has become a major concern for the space industry. With the growing interest in space exploration, the prediction of potential collisions between objects in orbit has become a crucial issue. It is estimated that, in orbit, there are millions of fragments a few millimeters in size and thousands of inoperative satellites and discarded rocket stages. Given the high speeds that these fragments can reach, even fragments a few millimeters in size can cause fractures in a satellite's hull or put a serious crack in the window of a space shuttle. The conventional method proposed by Akella and Alfriend in 2000 remains widely used to estimate the probability of collision in short-term encounters. Given the small period of time, it is assumed that, during the encounter: (1) trajectories are represented by straight lines with constant velocity; (2) there is no velocity uncertainty and the position exhibits a stationary distribution throughout the encounter; and (3) position uncertainties are independent and represented by Gaussian distributions. This study introduces a novel derivation based on first principles that naturally allows for tight and fast upper and lower bounds for the probability of collision. We tested implementations of both probability and bound computations with the original and our formulation on a real CDM dataset used in ESA's Collision Avoidance Challenge. Our approach reduces the calculation of the probability to two one-dimensional integrals and has the potential to significantly reduce the processing time compared to the traditional method, from 80% to nearly real-time.
Authors: Alon Diament (1), Maria Gorodetski (1), Adam Jankelow (1), Ayya Keshet (2), Tal Shor (1), Daphna Weissglas-Volkov (1), Hagai Rossman (1), Eran Segal (2) ((1) Pheno.AI, Tel-Aviv, Israel, (2) Weizmann Institute of Science, Rehovot, Israel)
This study introduces a novel, rich dataset obtained from home sleep apnea tests using the FDA-approved WatchPAT-300 device, collected from 7,077 participants over 21,412 nights. The dataset comprises three levels of sleep data: raw multi-channel time-series from sensors, annotated sleep events, and computed summary statistics, which include 447 features related to sleep architecture, sleep apnea, and heart rate variability (HRV). We present reference values for Apnea/Hypopnea Index (AHI), sleep efficiency, Wake After Sleep Onset (WASO), and HRV sample entropy, stratified by age and sex. Moreover, we demonstrate that the dataset improves the predictive capability for various health related traits, including body composition, bone density, blood sugar levels and cardiovascular health. These results illustrate the dataset's potential to advance sleep research, personalized healthcare, and machine learning applications in biomedicine.
Authors: David A. Kreplin, Moritz Willmann, Jan Schnabel, Frederic Rapp, Marco Roth
sQUlearn introduces a user-friendly, NISQ-ready Python library for quantum machine learning (QML), designed for seamless integration with classical machine learning tools like scikit-learn. The library's dual-layer architecture serves both QML researchers and practitioners, enabling efficient prototyping, experimentation, and pipelining. sQUlearn provides a comprehensive toolset that includes both quantum kernel methods and quantum neural networks, along with features like customizable data encoding strategies, automated execution handling, and specialized kernel regularization techniques. By focusing on NISQ-compatibility and end-to-end automation, sQUlearn aims to bridge the gap between current quantum computing capabilities and practical machine learning applications.
Authors: Gregory Yauney, Emily Reif, David Mimno
Large language models achieve high performance on many but not all downstream tasks. The interaction between pretraining data and task data is commonly assumed to determine this variance: a task with data that is more similar to a model's pretraining data is assumed to be easier for that model. We test whether distributional and example-specific similarity measures (embedding-, token- and model-based) correlate with language model performance through a large-scale comparison of the Pile and C4 pretraining datasets with downstream benchmarks. Similarity correlates with performance for multilingual datasets, but in other benchmarks, we surprisingly find that similarity metrics are not correlated with accuracy or even each other. This suggests that the relationship between pretraining data and downstream tasks is more complex than often assumed.
Authors: Lorenzo Nodari
In recent years, Reward Machines (RMs) have stood out as a simple yet effective automata-based formalism for exposing and exploiting task structure in reinforcement learning settings. Despite their relevance, little to no attention has been directed to the study of their security implications and robustness to adversarial scenarios, likely due to their recent appearance in the literature. With my thesis, I aim to provide the first analysis of the security of RM-based reinforcement learning techniques, with the hope of motivating further research in the field, and I propose and evaluate a novel class of attacks on RM-based techniques: blinding attacks.
Authors: Misha Ivkov, Tselil Schramm
Approximate message passing (AMP) is a family of iterative algorithms that generalize matrix power iteration. AMP algorithms are known to optimally solve many average-case optimization problems. In this paper, we show that a large class of AMP algorithms can be simulated in polynomial time by \emph{local statistics hierarchy} semidefinite programs (SDPs), even when an unknown principal minor of measure $1/\mathrm{polylog}(\mathrm{dimension})$ is adversarially corrupted. Ours are the first robust guarantees for many of these problems. Further, our results offer an interesting counterpoint to strong lower bounds against less constrained SDP relaxations for average-case max-cut-gain (a.k.a. "optimizing the Sherrington-Kirkpatrick Hamiltonian") and other problems.
Authors: Shengbo Wang, Nian Si, Jose Blanchet, Zhengyuan Zhou
Motivated by the need for a robust policy in the face of environment shifts between training and the deployment, we contribute to the theoretical foundation of distributionally robust reinforcement learning (DRRL). This is accomplished through a comprehensive modeling framework centered around distributionally robust Markov decision processes (DRMDPs). This framework obliges the decision maker to choose an optimal policy under the worst-case distributional shift orchestrated by an adversary. By unifying and extending existing formulations, we rigorously construct DRMDPs that embraces various modeling attributes for both the decision maker and the adversary. These attributes include adaptability granularity, exploring history-dependent, Markov, and Markov time-homogeneous decision maker and adversary dynamics. Additionally, we delve into the flexibility of shifts induced by the adversary, examining SA and S-rectangularity. Within this DRMDP framework, we investigate conditions for the existence or absence of the dynamic programming principle (DPP). From an algorithmic standpoint, the existence of DPP holds significant implications, as the vast majority of existing data and computationally efficiency RL algorithms are reliant on the DPP. To study its existence, we comprehensively examine combinations of controller and adversary attributes, providing streamlined proofs grounded in a unified methodology. We also offer counterexamples for settings in which a DPP with full generality is absent.
Authors: Lorenzo Nodari, Federico Cerutti
Robustness to noise is of utmost importance in reinforcement learning systems, particularly in military contexts where high stakes and uncertain environments prevail. Noise and uncertainty are inherent features of military operations, arising from factors such as incomplete information, adversarial actions, or unpredictable battlefield conditions. In RL, noise can critically impact decision-making, mission success, and the safety of personnel. Reward machines offer a powerful tool to express complex reward structures in RL tasks, enabling the design of tailored reinforcement signals that align with mission objectives. This paper considers the problem of the robustness of intelligence-driven reinforcement learning based on reward machines. The preliminary results presented suggest the need for further research in evidential reasoning and learning to harden current state-of-the-art reinforcement learning approaches before being mission-critical-ready.
Authors: Jörg K.H. Franke, Michael Hefenbrock, Gregor Koehler, Frank Hutter
This work presents constrained parameter regularization (CPR), an alternative to traditional weight decay. Instead of applying a constant penalty uniformly to all parameters, we enforce an upper bound on a statistical measure (e.g., the L$_2$-norm) of individual parameter groups. This reformulates learning as a constrained optimization problem. To solve this, we utilize an adaptation of the augmented Lagrangian method. Our approach allows for varying regularization strengths across different parameter groups, removing the need for explicit penalty coefficients in the regularization terms. CPR only requires two hyperparameters and introduces no measurable runtime overhead. We offer empirical evidence of CPR's effectiveness through experiments in the "grokking" phenomenon, image classification, and language modeling. Our findings show that CPR can counteract the effects of grokking, and it consistently matches or surpasses the performance of traditional weight decay.
Authors: Yeongbin Kim, Gautam Singh, Junyeong Park, Caglar Gulcehre, Sungjin Ahn
Systematic compositionality, or the ability to adapt to novel situations by creating a mental model of the world using reusable pieces of knowledge, remains a significant challenge in machine learning. While there has been considerable progress in the language domain, efforts towards systematic visual imagination, or envisioning the dynamical implications of a visual observation, are in their infancy. We introduce the Systematic Visual Imagination Benchmark (SVIB), the first benchmark designed to address this problem head-on. SVIB offers a novel framework for a minimal world modeling problem, where models are evaluated based on their ability to generate one-step image-to-image transformations under a latent world dynamics. The framework provides benefits such as the possibility to jointly optimize for systematic perception and imagination, a range of difficulty levels, and the ability to control the fraction of possible factor combinations used during training. We provide a comprehensive evaluation of various baseline models on SVIB, offering insight into the current state-of-the-art in systematic visual imagination. We hope that this benchmark will help advance visual systematic compositionality.
Authors: Hari Dahal, Wei Liu, Yangyang Xu
We give a damped proximal augmented Lagrangian method (DPALM) for solving problems with a weakly-convex objective and convex linear/nonlinear constraints. Instead of taking a full stepsize, DPALM adopts a damped dual stepsize to ensure the boundedness of dual iterates. We show that DPALM can produce a (near) $\vareps$-KKT point within $O(\vareps^{-2})$ outer iterations if each DPALM subproblem is solved to a proper accuracy. In addition, we establish overall iteration complexity of DPALM when the objective is either a regularized smooth function or in a regularized compositional form. For the former case, DPALM achieves the complexity of $\widetilde{\mathcal{O}}\left(\varepsilon^{-2.5} \right)$ to produce an $\varepsilon$-KKT point by applying an accelerated proximal gradient (APG) method to each DPALM subproblem. For the latter case, the complexity of DPALM is $\widetilde{\mathcal{O}}\left(\varepsilon^{-3} \right)$ to produce a near $\varepsilon$-KKT point by using an APG to solve a Moreau-envelope smoothed version of each subproblem. Our outer iteration complexity and the overall complexity either generalize existing best ones from unconstrained or linear-constrained problems to convex-constrained ones, or improve over the best-known results on solving the same-structured problems. Furthermore, numerical experiments on linearly/quadratically constrained non-convex quadratic programs and linear-constrained robust nonlinear least squares are conducted to demonstrate the empirical efficiency of the proposed DPALM over several state-of-the art methods.
Authors: Hakuei Yamada, Junpei Komiyama, Kenshi Abe, Atsushi Iwasaki
This work addresses learning online fair division under uncertainty, where a central planner sequentially allocates items without precise knowledge of agents' values or utilities. Departing from conventional online algorithm, the planner here relies on noisy, estimated values obtained after allocating items. We introduce wrapper algorithms utilizing \textit{dual averaging}, enabling gradual learning of both the type distribution of arriving items and agents' values through bandit feedback. This approach enables the algorithms to asymptotically achieve optimal Nash social welfare in linear Fisher markets with agents having additive utilities. We establish regret bounds in Nash social welfare and empirically validate the superior performance of our proposed algorithms across synthetic and empirical datasets.
Authors: Shumin Deng, Ningyu Zhang, Nay Oo, Bryan Hooi
Large Language Models (LLMs) employing Chain-of-Thought (CoT) prompting have broadened the scope for improving multi-step reasoning capabilities. Usually, answer calibration strategies such as step-level or path-level calibration play a vital role in multi-step reasoning. While effective, there remains a significant gap in our understanding of the key factors that drive their success. In this paper, we break down the design of recent answer calibration strategies and present a unified view which establishes connections between them. We then conduct a thorough evaluation on these strategies from a unified view, systematically scrutinizing step-level and path-level answer calibration across multiple paths. Our study holds the potential to illuminate key insights for optimizing multi-step reasoning with answer calibration.
Authors: Yusuke Sakai, Hidetaka Kamigaito, Katsuhiko Hayashi, Taro Watanabe
Knowledge graphs (KGs) consist of links that describe relationships between entities. Due to the difficulty of manually enumerating all relationships between entities, automatically completing them is essential for KGs. Knowledge Graph Completion (KGC) is a task that infers unseen relationships between entities in a KG. Traditional embedding-based KGC methods, such as RESCAL, TransE, DistMult, ComplEx, RotatE, HAKE, HousE, etc., infer missing links using only the knowledge from training data. In contrast, the recent Pre-trained Language Model (PLM)-based KGC utilizes knowledge obtained during pre-training. Therefore, PLM-based KGC can estimate missing links between entities by reusing memorized knowledge from pre-training without inference. This approach is problematic because building KGC models aims to infer unseen links between entities. However, conventional evaluations in KGC do not consider inference and memorization abilities separately. Thus, a PLM-based KGC method, which achieves high performance in current KGC evaluations, may be ineffective in practical applications. To address this issue, we analyze whether PLM-based KGC methods make inferences or merely access memorized knowledge. For this purpose, we propose a method for constructing synthetic datasets specified in this analysis and conclude that PLMs acquire the inference abilities required for KGC through pre-training, even though the performance improvements mostly come from textual information of entities and relations.
Authors: Haoqiang Kang, Juntong Ni, Huaxiu Yao
Large Language Models (LLMs) have demonstrated remarkable proficiency in generating fluent text. However, they often encounter the challenge of generating inaccurate or hallucinated content. This issue is common in both non-retrieval-based generation and retrieval-augmented generation approaches, and existing post-hoc rectification methods may not address the accumulated hallucination errors that may be caused by the "snowballing" issue, especially in reasoning tasks. To tackle these challenges, we introduce a novel approach called Real-time Verification and Rectification (Ever). Instead of waiting until the end of the generation process to rectify hallucinations, Ever employs a real-time, step-wise generation and hallucination rectification strategy. The primary objective is to detect and rectify hallucinations as they occur during the text generation process. When compared to both retrieval-based and non-retrieval-based baselines, Ever demonstrates a significant improvement in generating trustworthy and factually accurate text across a diverse range of tasks, including short-form QA, biography generation, and multi-hop reasoning.
Authors: Konstantin Hemker, Nikola Smidjievski, Mateja Jamnik
Technological advances in medical data collection such as high-resolution histopathology and high-throughput genomic sequencing have contributed to the rising requirement for multi-modal biomedical modelling, specifically for image, tabular, and graph data. Most multi-modal deep learning approaches use modality-specific architectures that are trained separately and cannot capture the crucial cross-modal information that motivates the integration of different data sources. This paper presents the Hybrid Early-fusion Attention Learning Network (HEALNet): a flexible multi-modal fusion architecture, which a) preserves modality-specific structural information, b) captures the cross-modal interactions and structural information in a shared latent space, c) can effectively handle missing modalities during training and inference, and d) enables intuitive model inspection by learning on the raw data input instead of opaque embeddings. We conduct multi-modal survival analysis on Whole Slide Images and Multi-omic data on four cancer cohorts of The Cancer Genome Atlas (TCGA). HEALNet achieves state-of-the-art performance, substantially improving over both uni-modal and recent multi-modal baselines, whilst being robust in scenarios with missing modalities.
Authors: Yuanwei Wu, Xiang Li, Yixin Liu, Pan Zhou, Lichao Sun
Existing work on jailbreak Multimodal Large Language Models (MLLMs) has focused primarily on adversarial examples in model inputs, with less attention to vulnerabilities in model APIs. To fill the research gap, we carry out the following work: 1) We discover a system prompt leakage vulnerability in GPT-4V. Through carefully designed dialogue, we successfully steal the internal system prompts of GPT-4V. This finding indicates potential exploitable security risks in MLLMs; 2)Based on the acquired system prompts, we propose a novel MLLM jailbreaking attack method termed SASP (Self-Adversarial Attack via System Prompt). By employing GPT-4 as a red teaming tool against itself, we aim to search for potential jailbreak prompts leveraging stolen system prompts. Furthermore, in pursuit of better performance, we also add human modification based on GPT-4's analysis, which further improves the attack success rate to 98.7\%; 3) We evaluated the effect of modifying system prompts to defend against jailbreaking attacks. Results show that appropriately designed system prompts can significantly reduce jailbreak success rates. Overall, our work provides new insights into enhancing MLLM security, demonstrating the important role of system prompts in jailbreaking, which could be leveraged to greatly facilitate jailbreak success rates while also holding the potential for defending against jailbreaks.
Authors: Julian Arnold, Frank Schäfer, Niels Lörch
Machine learning has been successfully used to study phase transitions. One of the most popular approaches to identifying critical points from data without prior knowledge of the underlying phases is the learning-by-confusion scheme. As input, it requires system samples drawn from a grid of the parameter whose change is associated with potential phase transitions. Up to now, the scheme required training a distinct binary classifier for each possible splitting of the grid into two sides, resulting in a computational cost that scales linearly with the number of grid points. In this work, we propose and showcase an alternative implementation that only requires the training of a single multi-class classifier. Ideally, such multi-task learning eliminates the scaling with respect to the number of grid points. In applications to the Ising model and an image dataset generated with Stable Diffusion, we find significant speedups that closely correspond to the ideal case, with only minor deviations.
Authors: Izak Yasrebi-de Kom, Joanna Klopotowska, Dave Dongelmans, Nicolette De Keizer, Kitty Jager, Ameen Abu-Hanna, Giovanni Cinà
The current best practice approach for the retrospective diagnosis of adverse drug events (ADEs) in hospitalized patients relies on a full patient chart review and a formal causality assessment by multiple medical experts. This evaluation serves to qualitatively estimate the probability of causation (PC); the probability that a drug was a necessary cause of an adverse event. This practice is manual, resource intensive and prone to human biases, and may thus benefit from data-driven decision support. Here, we pioneer a causal modeling approach using observational data to estimate a lower bound of the PC (PC$_{low}$). This method includes two key causal inference components: (1) the target trial emulation framework and (2) estimation of individualized treatment effects using machine learning. We apply our method to the clinically relevant use-case of vancomycin-induced acute kidney injury in intensive care patients, and compare our causal model-based PC$_{low}$ estimates to qualitative estimates of the PC provided by a medical expert. Important limitations and potential improvements are discussed, and we conclude that future improved causal models could provide essential data-driven support for medication safety monitoring in hospitalized patients.
Authors: Zheng-Meng Zhai, Mohammadamin Moradi, Bryan Glaz, Mulugeta Haile, Ying-Cheng Lai
Complex and nonlinear dynamical systems often involve parameters that change with time, accurate tracking of which is essential to tasks such as state estimation, prediction, and control. Existing machine-learning methods require full state observation of the underlying system and tacitly assume adiabatic changes in the parameter. Formulating an inverse problem and exploiting reservoir computing, we develop a model-free and fully data-driven framework to accurately track time-varying parameters from partial state observation in real time. In particular, with training data from a subset of the dynamical variables of the system for a small number of known parameter values, the framework is able to accurately predict the parameter variations in time. Low- and high-dimensional, Markovian and non-Markovian nonlinear dynamical systems are used to demonstrate the power of the machine-learning based parameter-tracking framework. Pertinent issues affecting the tracking performance are addressed.
Authors: Andrea Pugnana, Carlos Mougan, Dan Saattrup Nielsen
With the wide adoption of machine learning techniques, requirements have evolved beyond sheer high performance, often requiring models to be trustworthy. A common approach to increase the trustworthiness of such systems is to allow them to refrain from predicting. Such a framework is known as selective prediction. While selective prediction for classification tasks has been widely analyzed, the problem of selective regression is understudied. This paper presents a novel approach to selective regression that utilizes model-agnostic non-parametric uncertainty estimation. Our proposed framework showcases superior performance compared to state-of-the-art selective regressors, as demonstrated through comprehensive benchmarking on 69 datasets. Finally, we use explainable AI techniques to gain an understanding of the drivers behind selective regression. We implement our selective regression method in the open-source Python package doubt and release the code used to reproduce our experiments.
Authors: Helge Fredriksen (1), Per Joel Burman (2), Ashenafi Woldaregay (2), Karl Øyvind Mikalsen (2), Ståle Nymo (3) ((1) UiT - The Arctic University of Norway, (2) The Norwegian Centre for Clinical Artificial Intelligence, (3) Nordland Hospital Trust)
Patients being admitted to a hospital will most often be associated with a certain clinical development during their stay. However, there is always a risk of patients being subject to the wrong diagnosis or to a certain treatment not pertaining to the desired effect, potentially leading to adverse events. Our research aims to develop an anomaly detection system for identifying deviations from expected clinical trajectories. To address this goal we analyzed 16 months of vital sign recordings obtained from the Nordland Hospital Trust (NHT). We employed an self-supervised framework based on the STraTS transformer architecture to represent the time series data in a latent space. These representations were then subjected to various clustering techniques to explore potential patient phenotypes based on their clinical progress. While our preliminary results from this ongoing research are promising, they underscore the importance of enhancing the dataset with additional demographic information from patients. This additional data will be crucial for a more comprehensive evaluation of the method's performance.
Authors: Yixin Liu, Alexander R. Fabbri, Jiawen Chen, Yilun Zhao, Simeng Han, Shafiq Joty, Pengfei Liu, Dragomir Radev, Chien-Sheng Wu, Arman Cohan
While large language models (LLMs) already achieve strong performance on standard generic summarization benchmarks, their performance on more complex summarization task settings is less studied. Therefore, we benchmark LLMs on instruction controllable text summarization, where the model input consists of both a source article and a natural language requirement for the desired summary characteristics. To this end, we curate an evaluation-only dataset for this task setting and conduct human evaluation on 5 LLM-based summarization systems. We then benchmark LLM-based automatic evaluation for this task with 4 different evaluation protocols and 11 LLMs, resulting in 40 evaluation methods in total. Our study reveals that instruction controllable text summarization remains a challenging task for LLMs, since (1) all LLMs evaluated still make factual and other types of errors in their summaries; (2) all LLM-based evaluation methods cannot achieve a strong alignment with human annotators when judging the quality of candidate summaries; (3) different LLMs show large performance gaps in summary generation and evaluation. We make our collected benchmark, InstruSum, publicly available to facilitate future research in this direction.
Authors: Lucas Torroba Hennigen, Shannon Shen, Aniruddha Nrusimha, Bernhard Gapp, David Sontag, Yoon Kim
Large language models (LLMs) have demonstrated an impressive ability to synthesize plausible and fluent text. However they remain vulnerable to hallucinations, and thus their outputs generally require manual human verification for high-stakes applications, which can be time-consuming and difficult. This paper proposes symbolically grounded generation (SymGen) as a simple approach for enabling easier validation of an LLM's output. SymGen prompts an LLM to interleave its regular output text with explicit symbolic references to fields present in some conditioning data (e.g., a table in JSON format). The references can be used to display the provenance of different spans of text in the generation, reducing the effort required for manual verification. Across data-to-text and question answering experiments, we find that LLMs are able to directly output text that makes use of symbolic references while maintaining fluency and accuracy.
Authors: Giuseppe Serra, Photios A. Stavrou, Marios Kountouris
In this paper, we study the computation of the rate-distortion-perception function (RDPF) for a multivariate Gaussian source under mean squared error (MSE) distortion and, respectively, Kullback-Leibler divergence, geometric Jensen-Shannon divergence, squared Hellinger distance, and squared Wasserstein-2 distance perception metrics. To this end, we first characterize the analytical bounds of the scalar Gaussian RDPF for the aforementioned divergence functions, also providing the RDPF-achieving forward "test-channel" realization. Focusing on the multivariate case, we establish that, for tensorizable distortion and perception metrics, the optimal solution resides on the vector space spanned by the eigenvector of the source covariance matrix. Consequently, the multivariate optimization problem can be expressed as a function of the scalar Gaussian RDPFs of the source marginals, constrained by global distortion and perception levels. Leveraging this characterization, we design an alternating minimization scheme based on the block nonlinear Gauss-Seidel method, which optimally solves the problem while identifying the Gaussian RDPF-achieving realization. Furthermore, the associated algorithmic embodiment is provided, as well as the convergence and the rate of convergence characterization. Lastly, for the "perfect realism" regime, the analytical solution for the multivariate Gaussian RDPF is obtained. We corroborate our results with numerical simulations and draw connections to existing results.
Authors: Sang-Hyun Lee, Seung-Woo Seo
A significant bottleneck in applying current reinforcement learning algorithms to real-world scenarios is the need to reset the environment between every episode. This reset process demands substantial human intervention, making it difficult for the agent to learn continuously and autonomously. Several recent works have introduced autonomous reinforcement learning (ARL) algorithms that generate curricula for jointly training reset and forward policies. While their curricula can reduce the number of required manual resets by taking into account the agent's learning progress, they rely on task-specific knowledge, such as predefined initial states or reset reward functions. In this paper, we propose a novel ARL algorithm that can generate a curriculum adaptive to the agent's learning progress without task-specific knowledge. Our curriculum empowers the agent to autonomously reset to diverse and informative initial states. To achieve this, we introduce a success discriminator that estimates the success probability from each initial state when the agent follows the forward policy. The success discriminator is trained with relabeled transitions in a self-supervised manner. Our experimental results demonstrate that our ARL algorithm can generate an adaptive curriculum and enable the agent to efficiently bootstrap to solve sparse-reward maze navigation tasks, outperforming baselines with significantly fewer manual resets.
Authors: Jason Gaitonde, Elchanan Mossel
We revisit the problem of efficiently learning the underlying parameters of Ising models from data. Current algorithmic approaches achieve essentially optimal sample complexity when given i.i.d. samples from the stationary measure and the underlying model satisfies "width" bounds on the total $\ell_1$ interaction involving each node. We show that a simple existing approach based on node-wise logistic regression provably succeeds at recovering the underlying model in several new settings where these assumptions are violated:
(1) Given dynamically generated data from a wide variety of local Markov chains, like block or round-robin dynamics, logistic regression recovers the parameters with optimal sample complexity up to $\log\log n$ factors. This generalizes the specialized algorithm of Bresler, Gamarnik, and Shah [IEEE Trans. Inf. Theory'18] for structure recovery in bounded degree graphs from Glauber dynamics.
(2) For the Sherrington-Kirkpatrick model of spin glasses, given $\mathsf{poly}(n)$ independent samples, logistic regression recovers the parameters in most of the known high-temperature regime via a simple reduction to weaker structural properties of the measure. This improves on recent work of Anari, Jain, Koehler, Pham, and Vuong [ArXiv'23] which gives distribution learning at higher temperature.
(3) As a simple byproduct of our techniques, logistic regression achieves an exponential improvement in learning from samples in the M-regime of data considered by Dutt, Lokhov, Vuffray, and Misra [ICML'21] as well as novel guarantees for learning from the adversarial Glauber dynamics of Chin, Moitra, Mossel, and Sandon [ArXiv'23].
Our approach thus significantly generalizes the elegant analysis of Wu, Sanghavi, and Dimakis [Neurips'19] without any algorithmic modification.
Authors: Ryan R. Curtin, Marcus Edel, Rahul Ganesh Prabhu, Suryoday Basak, Zhihao Lou, Conrad Sanderson
This report provides an introduction to the ensmallen numerical optimization library, as well as a deep dive into the technical details of how it works. The library provides a fast and flexible C++ framework for mathematical optimization of arbitrary user-supplied functions. A large set of pre-built optimizers is provided, including many variants of Stochastic Gradient Descent and Quasi-Newton optimizers. Several types of objective functions are supported, including differentiable, separable, constrained, and categorical objective functions. Implementation of a new optimizer requires only one method, while a new objective function requires typically only one or two C++ methods. Through internal use of C++ template metaprogramming, ensmallen provides support for arbitrary user-supplied callbacks and automatic inference of unsupplied methods without any runtime overhead. Empirical comparisons show that ensmallen outperforms other optimization frameworks (such as Julia and SciPy), sometimes by large margins. The library is available at https://ensmallen.org and is distributed under the permissive BSD license.
Authors: Qianren Mao, Jiazheng Wang, Zheng Wang, Xi Li, Bo Li, Jianxin Li
Timeline summarization (TLS) involves creating summaries of long-running events using dated summaries from numerous news articles. However, limited data availability has significantly slowed down the development of timeline summarization. In this paper, we introduce the CNTLS dataset, a versatile resource for Chinese timeline summarization. CNTLS encompasses 77 real-life topics, each with 2524 documents and summarizes nearly 60\% days duration compression on average all topics.
We meticulously analyze the corpus using well-known metrics, focusing on the style of the summaries and the complexity of the summarization task. Specifically, we evaluate the performance of various extractive and generative summarization systems on the CNTLS corpus to provide benchmarks and support further research. To the best of our knowledge, CNTLS is the first Chinese timeline summarization dataset. The dataset and source code are released\footnote{Code and data available at: \emph{\url{https://github.com/OpenSUM/CNTLS}}.}.
Authors: Hadi Hojjati, Narges Armanfard
Semi-supervised anomaly detection aims to detect anomalies from normal samples using a model that is trained on normal data. With recent advancements in deep learning, researchers have designed efficient deep anomaly detection methods. Existing works commonly use neural networks to map the data into a more informative representation and then apply an anomaly detection algorithm. In this paper, we propose a method, DASVDD, that jointly learns the parameters of an autoencoder while minimizing the volume of an enclosing hyper-sphere on its latent representation. We propose an anomaly score which is a combination of autoencoder's reconstruction error and the distance from the center of the enclosing hypersphere in the latent representation. Minimizing this anomaly score aids us in learning the underlying distribution of the normal class during training. Including the reconstruction error in the anomaly score ensures that DASVDD does not suffer from the common hypersphere collapse issue since the DASVDD model does not converge to the trivial solution of mapping all inputs to a constant point in the latent representation. Experimental evaluations on several benchmark datasets show that the proposed method outperforms the commonly used state-of-the-art anomaly detection algorithms while maintaining robust performance across different anomaly classes.
Authors: Sai Srivatsa Ravindranath, Zhe Feng, Shira Li, Jonathan Ma, Scott D. Kominers, David C. Parkes
We initiate the study of deep learning for the automated design of two-sided matching mechanisms. What is of most interest is to use machine learning to understand the possibility of new tradeoffs between strategy-proofness and stability. These properties cannot be achieved simultaneously, but the efficient frontier is not understood. We introduce novel differentiable surrogates for quantifying ordinal strategy-proofness and stability and use them to train differentiable matching mechanisms that map discrete preferences to valid randomized matchings. We demonstrate that the efficient frontier characterized by these learned mechanisms is substantially better than that achievable through a convex combination of baselines of deferred acceptance (stable and strategy-proof for only one side of the market), top trading cycles (strategy-proof for one side, but not stable), and randomized serial dictatorship (strategy-proof for both sides, but not stable). This gives a new target for economic theory and opens up new possibilities for machine learning pipelines in matching market design.
Authors: Irene Tenison, Sai Aravind Sreeramadas, Vaikkunth Mugunthan, Edouard Oyallon, Irina Rish, Eugene Belilovsky
Federated learning (FL) is an emerging paradigm that permits a large number of clients with heterogeneous data to coordinate learning of a unified global model without the need to share data amongst each other. A major challenge in federated learning is the heterogeneity of data across client, which can degrade the performance of standard FL algorithms. Standard FL algorithms involve averaging of model parameters or gradient updates to approximate the global model at the server. However, we argue that in heterogeneous settings, averaging can result in information loss and lead to poor generalization due to the bias induced by dominant client gradients. We hypothesize that to generalize better across non-i.i.d datasets, the algorithms should focus on learning the invariant mechanism that is constant while ignoring spurious mechanisms that differ across clients. Inspired from recent works in Out-of-Distribution generalization, we propose a gradient masked averaging approach for FL as an alternative to the standard averaging of client updates. This aggregation technique for client updates can be adapted as a drop-in replacement in most existing federated algorithms. We perform extensive experiments on multiple FL algorithms with in-distribution, real-world, feature-skewed out-of-distribution, and quantity imbalanced datasets and show that it provides consistent improvements, particularly in the case of heterogeneous clients.
Authors: Tom Lefebvre
Probabilistic control design is founded on the principle that a rational agent attempts to match modelled with an arbitrary desired closed-loop system trajectory density. The framework was originally proposed as a tractable alternative to traditional optimal control design, parametrizing desired behaviour through fictitious transition and policy densities and using the information projection as a proximity measure. In this work we introduce an alternative parametrization of desired closed-loop behaviour and explore alternative proximity measures between densities. It is then illustrated how the associated probabilistic control problems solve into uncertain or probabilistic policies. Our main result is to show that the probabilistic control objectives majorize conventional, stochastic and risk sensitive, optimal control objectives. This observation allows us to identify two probabilistic fixed point iterations that converge to the deterministic optimal control policies establishing an explicit connection between either formulations. Further we demonstrate that the risk sensitive optimal control formulation is also technically equivalent to a Maximum Likelihood estimation problem on a probabilistic graph model where the notion of costs is directly encoded into the model. The associated treatment of the estimation problem is then shown to coincide with the moment projected probabilistic control formulation. That way optimal decision making can be reformulated as an iterative inference problem. Based on these insights we discuss directions for algorithmic development.
Authors: Yuchen Lu, Zhen Liu, Aristide Baratin, Romain Laroche, Aaron Courville, Alessandro Sordoni
We address the problem of evaluating the quality of self-supervised learning (SSL) models without access to supervised labels, while being agnostic to the architecture, learning algorithm or data manipulation used during training. We argue that representations can be evaluated through the lens of expressiveness and learnability. We propose to use the Intrinsic Dimension (ID) to assess expressiveness and introduce Cluster Learnability (CL) to assess learnability. CL is measured in terms of the performance of a KNN classifier trained to predict labels obtained by clustering the representations with K-means. We thus combine CL and ID into a single predictor -- CLID. Through a large-scale empirical study with a diverse family of SSL algorithms, we find that CLID better correlates with in-distribution model performance than other competing recent evaluation schemes. We also benchmark CLID on out-of-domain generalization, where CLID serves as a predictor of the transfer performance of SSL models on several visual classification tasks, yielding improvements with respect to the competing baselines.
Authors: Rūta Binkytė, Ljupcho Grozdanovski, Sami Zhioua
Besides its common use cases in epidemiology, political, and social sciences, causality turns out to be crucial in evaluating the fairness of automated decisions, both in a legal and everyday sense. We provide arguments and examples, of why causality is particularly important for fairness evaluation. In particular, we point out the social impact of non-causal predictions and the legal anti-discrimination process that relies on causal claims. We conclude with a discussion about the challenges and limitations of applying causality in practical scenarios as well as possible solutions.
Authors: Domenico Lofù, Pietro Di Gennaro, Pietro Tedeschi, Tommaso Di Noia, Eugenio Di Sciascio
Safety and security issues for Critical Infrastructures are growing as attackers adopt drones as an attack vector flying in sensitive airspaces, such as airports, military bases, city centers, and crowded places. Despite the use of UAVs for logistics, shipping recreation activities, and commercial applications, their usage poses severe concerns to operators due to the violations and the invasions of the restricted airspaces. A cost-effective and real-time framework is needed to detect the presence of drones in such cases. In this contribution, we propose an efficient radio frequency-based detection framework called URANUS. We leverage real-time data provided by the Radio Frequency/Direction Finding system, and radars in order to detect, classify and identify drones (multi-copter and fixed-wings) invading no-drone zones. We adopt a Multilayer Perceptron neural network to identify and classify UAVs in real-time, with $90$% accuracy. For the tracking task, we use a Random Forest model to predict the position of a drone with an MSE $\approx0.29$, MAE $\approx0.04$, and $R^2\approx 0.93$. Furthermore, coordinate regression is performed using Universal Transverse Mercator coordinates to ensure high accuracy. Our analysis shows that URANUS is an ideal framework for identifying, classifying, and tracking UAVs that most Critical Infrastructure operators can adopt.
Authors: Kyunghoon Hur, Jungwoo Oh, Junu Kim, Jiyoun Kim, Min Jae Lee, Eunbyeol Cho, Seong-Eun Moon, Young-Hak Kim, Louis Atallah, Edward Choi
Despite the remarkable progress in the development of predictive models for healthcare, applying these algorithms on a large scale has been challenging. Algorithms trained on a particular task, based on specific data formats available in a set of medical records, tend to not generalize well to other tasks or databases in which the data fields may differ. To address this challenge, we propose General Healthcare Predictive Framework (GenHPF), which is applicable to any EHR with minimal preprocessing for multiple prediction tasks. GenHPF resolves heterogeneity in medical codes and schemas by converting EHRs into a hierarchical textual representation while incorporating as many features as possible. To evaluate the efficacy of GenHPF, we conduct multi-task learning experiments with single-source and multi-source settings, on three publicly available EHR datasets with different schemas for 12 clinically meaningful prediction tasks. Our framework significantly outperforms baseline models that utilize domain knowledge in multi-source learning, improving average AUROC by 1.2%P in pooled learning and 2.6%P in transfer learning while also showing comparable results when trained on a single EHR dataset. Furthermore, we demonstrate that self-supervised pretraining using multi-source datasets is effective when combined with GenHPF, resulting in a 0.6%P AUROC improvement compared to models without pretraining. By eliminating the need for preprocessing and feature engineering, we believe that this work offers a solid framework for multi-task and multi-source learning that can be leveraged to speed up the scaling and usage of predictive algorithms in healthcare.
Authors: Masatoshi Uehara, Haruka Kiyohara, Andrew Bennett, Victor Chernozhukov, Nan Jiang, Nathan Kallus, Chengchun Shi, Wen Sun
We study off-policy evaluation (OPE) for partially observable MDPs (POMDPs) with general function approximation. Existing methods such as sequential importance sampling estimators and fitted-Q evaluation suffer from the curse of horizon in POMDPs. To circumvent this problem, we develop a novel model-free OPE method by introducing future-dependent value functions that take future proxies as inputs. Future-dependent value functions play similar roles as classical value functions in fully-observable MDPs. We derive a new Bellman equation for future-dependent value functions as conditional moment equations that use history proxies as instrumental variables. We further propose a minimax learning method to learn future-dependent value functions using the new Bellman equation. We obtain the PAC result, which implies our OPE estimator is consistent as long as futures and histories contain sufficient information about latent states, and the Bellman completeness. Finally, we extend our methods to learning of dynamics and establish the connection between our approach and the well-known spectral learning methods in POMDPs.
Authors: Tzvi Diskin, Yiftach Beer, Uri Okun, Ami Wiesel
We consider the problem of target detection with a constant false alarm rate (CFAR). This constraint is crucial in many practical applications and is a standard requirement in classical composite hypothesis testing. In settings where classical approaches are computationally expensive or where only data samples are given, machine learning methodologies are advantageous. CFAR is less understood in these settings. To close this gap, we introduce a framework of CFAR constrained detectors. Theoretically, we prove that a CFAR constrained Bayes optimal detector is asymptotically equivalent to the classical generalized likelihood ratio test (GLRT). Practically, we develop a deep learning framework for fitting neural networks that approximate it. Experiments of target detection in different setting demonstrate that the proposed CFARnet allows a flexible tradeoff between CFAR and accuracy.
Authors: Rolf A. N. Starre, Marco Loog, Elena Congeduti, Frans A. Oliehoek
Many methods for Model-based Reinforcement learning (MBRL) in Markov decision processes (MDPs) provide guarantees for both the accuracy of the model they can deliver and the learning efficiency. At the same time, state abstraction techniques allow for a reduction of the size of an MDP while maintaining a bounded loss with respect to the original problem. Therefore, it may come as a surprise that no such guarantees are available when combining both techniques, i.e., where MBRL merely observes abstract states. Our theoretical analysis shows that abstraction can introduce a dependence between samples collected online (e.g., in the real world). That means that, without taking this dependence into account, results for MBRL do not directly extend to this setting. Our result shows that we can use concentration inequalities for martingales to overcome this problem. This result makes it possible to extend the guarantees of existing MBRL algorithms to the setting with abstraction. We illustrate this by combining R-MAX, a prototypical MBRL algorithm, with abstraction, thus producing the first performance guarantees for model-based 'RL from Abstracted Observations': model-based reinforcement learning with an abstract model.
Authors: Clemens Karner, Vladimir Kazeev, Philipp Christian Petersen
We study the training of deep neural networks by gradient descent where floating-point arithmetic is used to compute the gradients. In this framework and under realistic assumptions, we demonstrate that it is highly unlikely to find ReLU neural networks that maintain, in the course of training with gradient descent, superlinearly many affine pieces with respect to their number of layers. In virtually all approximation theoretical arguments that yield high-order polynomial rates of approximation, sequences of ReLU neural networks with exponentially many affine pieces compared to their numbers of layers are used. As a consequence, we conclude that approximating sequences of ReLU neural networks resulting from gradient descent in practice differ substantially from theoretically constructed sequences. The assumptions and the theoretical results are compared to a numerical study, which yields concurring results.
Authors: Md. Iqbal Hossain, Mohammad Zunaed, Md. Kawsar Ahmed, S. M. Jawwad Hossain, Anwarul Hasan, Taufiq Hasan
Objective: Computer-aided disease diagnosis and prognosis based on medical images is a rapidly emerging field. Many Convolutional Neural Network (CNN) architectures have been developed by researchers for disease classification and localization from chest X-ray images. It is known that different thoracic disease lesions are more likely to occur in specific anatomical regions compared to others. This article aims to incorporate this disease and region-dependent prior probability distribution within a deep learning framework. Methods: We present the ThoraX-PriorNet, a novel attention-based CNN model for thoracic disease classification. We first estimate a disease-dependent spatial probability, i.e., an anatomical prior, that indicates the probability of occurrence of a disease in a specific region in a chest X-ray image. Next, we develop a novel attention-based classification model that combines information from the estimated anatomical prior and automatically extracted chest region of interest (ROI) masks to provide attention to the feature maps generated from a deep convolution network. Unlike previous works that utilize various self-attention mechanisms, the proposed method leverages the extracted chest ROI masks along with the probabilistic anatomical prior information, which selects the region of interest for different diseases to provide attention. Results: The proposed method shows superior performance in disease classification on the NIH ChestX-ray14 dataset compared to existing state-of-the-art methods while reaching an area under the ROC curve (%AUC) of 84.67. Regarding disease localization, the anatomy prior attention method shows competitive performance compared to state-of-the-art methods, achieving an accuracy of 0.80, 0.63, 0.49, 0.33, 0.28, 0.21, and 0.04 with an Intersection over Union (IoU) threshold of 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, and 0.7, respectively.
Authors: Yoichi Ishibashi, Sho Yokoi, Katsuhito Sudoh, Satoshi Nakamura
In natural language processing (NLP), the role of embeddings in representing linguistic semantics is crucial. Despite the prevalence of vector representations in embedding sets, they exhibit limitations in expressiveness and lack comprehensive set operations. To address this, we attempt to formulate and apply sets and their operations within pre-trained embedding spaces. Inspired by quantum logic, we propose to go beyond the conventional vector set representation with our novel subspace-based approach. This methodology constructs subspaces using pre-trained embedding sets, effectively preserving semantic nuances previously overlooked, and consequently consistently improving performance in downstream tasks.
Authors: Thomas J. Ringstrom
Reinforcement Learning views the maximization of rewards and avoidance of punishments as central to explaining goal-directed behavior. However, over a life, organisms will need to learn about many different aspects of the world's structure: the states of the world and state-vector transition dynamics. The number of combinations of states grows exponentially as an agent incorporates new knowledge, and there is no obvious weighted combination of pre-existing rewards or costs defined for a given combination of states, as such a weighting would need to encode information about good and bad combinations prior to an agent's experience in the world. Therefore, we must develop more naturalistic accounts of behavior and motivation in large state-spaces. We show that it is possible to use only the intrinsic motivation metric of empowerment, which measures the agent's capacity to realize many possible futures under a transition operator. We propose to scale empowerment to hierarchical state-spaces by using Operator Bellman Equations. These equations produce state-time feasibility functions, which are compositional hierarchical state-time transition operators that map an initial state and time when an agent begins a policy to the final states and times of completing a goal. Because these functions are hierarchical operators we can define hierarchical empowerment measures on them. An agent can then optimize plans to distant states and times to maximize its hierarchical empowerment-gain, allowing it to discover goals that bring about a more favorable coupling of its internal structure (physiological states) to its external environment (world structure & spatial state). Life-long agents could therefore be primarily animated by principles of compositionality and empowerment, exhibiting self-concern for the growth & maintenance of their own structural integrity without recourse to reward-maximization.
Authors: Jonathan W. Siegel
Let $\Omega = [0,1]^d$ be the unit cube in $\mathbb{R}^d$. We study the problem of how efficiently, in terms of the number of parameters, deep neural networks with the ReLU activation function can approximate functions in the Sobolev spaces $W^s(L_q(\Omega))$ and Besov spaces $B^s_r(L_q(\Omega))$, with error measured in the $L_p(\Omega)$ norm. This problem is important when studying the application of neural networks in a variety of fields, including scientific computing and signal processing, and has previously been solved only when $p=q=\infty$. Our contribution is to provide a complete solution for all $1\leq p,q\leq \infty$ and $s > 0$ for which the corresponding Sobolev or Besov space compactly embeds into $L_p$. The key technical tool is a novel bit-extraction technique which gives an optimal encoding of sparse vectors. This enables us to obtain sharp upper bounds in the non-linear regime where $p > q$. We also provide a novel method for deriving $L_p$-approximation lower bounds based upon VC-dimension when $p < \infty$. Our results show that very deep ReLU networks significantly outperform classical methods of approximation in terms of the number of parameters, but that this comes at the cost of parameters which are not encodable.
Authors: Yongsong Huang, Tomo Miyazaki, Xiaofeng Liu, Shinichiro Omachi
Image Super-Resolution (SR) is essential for a wide range of computer vision and image processing tasks. Investigating infrared (IR) image (or thermal images) super-resolution is a continuing concern within the development of deep learning. This survey aims to provide a comprehensive perspective of IR image super-resolution, including its applications, hardware imaging system dilemmas, and taxonomy of image processing methodologies. In addition, the datasets and evaluation metrics in IR image super-resolution tasks are also discussed. Furthermore, the deficiencies in current technologies and possible promising directions for the community to explore are highlighted. To cope with the rapid development in this field, we intend to regularly update the relevant excellent work at \url{https://github.com/yongsongH/Infrared_Image_SR_Survey
Authors: Matthias J. Ehrhardt, Lindon Roberts
Estimating hyperparameters has been a long-standing problem in machine learning. We consider the case where the task at hand is modeled as the solution to an optimization problem. Here the exact gradient with respect to the hyperparameters cannot be feasibly computed and approximate strategies are required. We introduce a unified framework for computing hypergradients that generalizes existing methods based on the implicit function theorem and automatic differentiation/backpropagation, showing that these two seemingly disparate approaches are actually tightly connected. Our framework is extremely flexible, allowing its subproblems to be solved with any suitable method, to any degree of accuracy. We derive a priori and computable a posteriori error bounds for all our methods, and numerically show that our a posteriori bounds are usually more accurate. Our numerical results also show that, surprisingly, for efficient bilevel optimization, the choice of hypergradient algorithm is at least as important as the choice of lower-level solver.
Authors: Siyuan Cheng, Ningyu Zhang, Bozhong Tian, Xi Chen, Qingbing Liu, Huajun Chen
Recently decades have witnessed the empirical success of framing Knowledge Graph (KG) embeddings via language models. However, language model-based KG embeddings are usually deployed as static artifacts, making them difficult to modify post-deployment without re-training after deployment. To address this issue, we propose a new task of editing language model-based KG embeddings in this paper. This task is designed to facilitate rapid, data-efficient updates to KG embeddings without compromising the performance of other aspects. We build four new datasets: E-FB15k237, A-FB15k237, E-WN18RR, and A-WN18RR, and evaluate several knowledge editing baselines demonstrating the limited ability of previous models to handle the proposed challenging task. We further propose a simple yet strong baseline dubbed KGEditor, which utilizes additional parametric layers of the hyper network to edit/add facts. Our comprehensive experimental results reveal that KGEditor excels in updating specific facts without impacting the overall performance, even when faced with limited training resources. Code and datasets are available in https://github.com/zjunlp/PromptKG/tree/main/deltaKG.
Authors: A. Feder Cooper, Katherine Lee, Madiha Choksi, Solon Barocas, Christopher De Sa, James Grimmelmann, Jon Kleinberg, Siddhartha Sen, Baobao Zhang
Variance in predictions across different trained models is a significant, under-explored source of error in fair binary classification. In practice, the variance on some data examples is so large that decisions can be effectively arbitrary. To investigate this problem, we take an experimental approach and make four overarching contributions: We: 1) Define a metric called self-consistency, derived from variance, which we use as a proxy for measuring and reducing arbitrariness; 2) Develop an ensembling algorithm that abstains from classification when a prediction would be arbitrary; 3) Conduct the largest to-date empirical study of the role of variance (vis-a-vis self-consistency and arbitrariness) in fair binary classification; and, 4) Release a toolkit that makes the US Home Mortgage Disclosure Act (HMDA) datasets easily usable for future research. Altogether, our experiments reveal shocking insights about the reliability of conclusions on benchmark datasets. Most fair binary classification benchmarks are close-to-fair when taking into account the amount of arbitrariness present in predictions -- before we even try to apply any fairness interventions. This finding calls into question the practical utility of common algorithmic fairness methods, and in turn suggests that we should reconsider how we choose to measure fairness in binary classification.
Authors: Yatong Bai, Brendon G. Anderson, Aerin Kim, Somayeh Sojoudi
While prior research has proposed a plethora of methods that build neural classifiers robust against adversarial robustness, practitioners are still reluctant to adopt them due to their unacceptably severe clean accuracy penalties. This paper significantly alleviates this accuracy-robustness trade-off by mixing the output probabilities of a standard classifier and a robust classifier, where the standard network is optimized for clean accuracy and is not robust in general. We show that the robust base classifier's confidence difference for correct and incorrect examples is the key to this improvement. In addition to providing intuitions and empirical evidence, we theoretically certify the robustness of the mixed classifier under realistic assumptions. Furthermore, we adapt an adversarial input detector into a mixing network that adaptively adjusts the mixture of the two base models, further reducing the accuracy penalty of achieving robustness. The proposed flexible method, termed "adaptive smoothing", can work in conjunction with existing or even future methods that improve clean accuracy, robustness, or adversary detection. Our empirical evaluation considers strong attack methods, including AutoAttack and adaptive attack. On the CIFAR-100 dataset, our method achieves an 85.21% clean accuracy while maintaining a 38.72% $\ell_\infty$-AutoAttacked ($\epsilon = 8/255$) accuracy, becoming the second most robust method on the RobustBench CIFAR-100 benchmark as of submission, while improving the clean accuracy by ten percentage points compared with all listed models. The code that implements our method is available at https://github.com/Bai-YT/AdaptiveSmoothing.
Authors: Francesco Semeraro, Jon Carberry, Angelo Cangelosi
Human-robot interaction (HRI) research is progressively addressing multi-party scenarios, where a robot interacts with more than one human user at the same time. Conversely, research is still at an early stage for human-robot collaboration. The use of machine learning techniques to handle such type of collaboration requires data that are less feasible to produce than in a typical HRC setup. This work outlines scenarios of concurrent tasks for non-dyadic HRC applications. Based upon these concepts, this study also proposes an alternative way of gathering data regarding multi-user activity, by collecting data related to single users and merging them in post-processing, to reduce the effort involved in producing recordings of pair settings. To validate this statement, 3D skeleton poses of activity of single users were collected and merged in pairs. After this, such datapoints were used to separately train a long short-term memory (LSTM) network and a variational autoencoder (VAE) composed of spatio-temporal graph convolutional networks (STGCN) to recognise the joint activities of the pairs of people. The results showed that it is possible to make use of data collected in this way for pair HRC settings and get similar performances compared to using training data regarding groups of users recorded under the same settings, relieving from the technical difficulties involved in producing these data.
The related code and collected data are publicly available.
Authors: Stamatis Alexandropoulos, Christos Sakaridis, Petros Maragos
Semantic segmentation is a fundamental task in visual scene understanding. We focus on the supervised setting, where ground-truth semantic annotations are available. Based on knowledge about the high regularity of real-world scenes, we propose a method for improving class predictions by learning to selectively exploit information from neighboring pixels. In particular, our method is based on the prior that for each pixel, there is a seed pixel in its close neighborhood sharing the same prediction with the former. Motivated by this prior, we design a novel two-head network, named Offset Vector Network (OVeNet), which generates both standard semantic predictions and a dense 2D offset vector field indicating the offset from each pixel to the respective seed pixel, which is used to compute an alternative, seed-based semantic prediction. The two predictions are adaptively fused at each pixel using a learnt dense confidence map for the predicted offset vector field. We supervise offset vectors indirectly via optimizing the seed-based prediction and via a novel loss on the confidence map. Compared to the baseline state-of-the-art architectures HRNet and HRNet+OCR on which OVeNet is built, the latter achieves significant performance gains on three prominent benchmarks for semantic segmentation, namely Cityscapes, ACDC and ADE20K. Code is available at https://github.com/stamatisalex/OVeNet
Authors: Borui Cai, Guangyan Huang, Shuiqiao Yang, Yong Xiang, Chi-Hung Chi
Shapelets that discriminate time series using local features (subsequences) are promising for time series clustering. Existing time series clustering methods may fail to capture representative shapelets because they discover shapelets from a large pool of uninformative subsequences, and thus result in low clustering accuracy. This paper proposes a Semi-supervised Clustering of Time Series Using Representative Shapelets (SE-Shapelets) method, which utilizes a small number of labeled and propagated pseudo-labeled time series to help discover representative shapelets, thereby improving the clustering accuracy. In SE-Shapelets, we propose two techniques to discover representative shapelets for the effective clustering of time series. 1) A \textit{salient subsequence chain} ($SSC$) that can extract salient subsequences (as candidate shapelets) of a labeled/pseudo-labeled time series, which helps remove massive uninformative subsequences from the pool. 2) A \textit{linear discriminant selection} ($LDS$) algorithm to identify shapelets that can capture representative local features of time series in different classes, for convenient clustering. Experiments on UCR time series datasets demonstrate that SE-shapelets discovers representative shapelets and achieves higher clustering accuracy than counterpart semi-supervised time series clustering methods.
Authors: Alberto Solera-Rico (1 and 2), Carlos Sanmiguel Vila (1 and 2), M. A. Gómez (2), Yuning Wang (4), Abdulrahman Almashjary (3), Scott T. M. Dawson (3), Ricardo Vinuesa (4) (1: Aerospace Engineering Research Group, Universidad Carlos III de Madrid, Leganés, Spain 2: Subdirectorate General of Terrestrial Systems, Spanish National Institute for Aerospace Technology (INTA), San Martín de la Vega, Spain 3: Mechanical, Materials, and Aerospace Engineering Department, Illinois Institute of Technology, Chicago, USA 4: FLOW, Engineering Mechanics, KTH Royal Institute of Technology, Stockholm, Sweden)
Variational autoencoder (VAE) architectures have the potential to develop reduced-order models (ROMs) for chaotic fluid flows. We propose a method for learning compact and near-orthogonal ROMs using a combination of a $\beta$-VAE and a transformer, tested on numerical data from a two-dimensional viscous flow in both periodic and chaotic regimes. The $\beta$-VAE is trained to learn a compact latent representation of the flow velocity, and the transformer is trained to predict the temporal dynamics in latent space. Using the $\beta$-VAE to learn disentangled representations in latent-space, we obtain a more interpretable flow model with features that resemble those observed in the proper orthogonal decomposition, but with a more efficient representation. Using Poincar\'e maps, the results show that our method can capture the underlying dynamics of the flow outperforming other prediction models. The proposed method has potential applications in other fields such as weather forecasting, structural dynamics or biomedical engineering.
Authors: Lillian Muyama, Antoine Neuraz, Adrien Coulet
Clinical diagnosis guidelines aim at specifying the steps that may lead to a diagnosis. Inspired by guidelines, we aim to learn the optimal sequence of actions to perform in order to obtain a correct diagnosis from electronic health records. We apply various deep reinforcement learning algorithms to this task and experiment on a synthetic but realistic dataset to differentially diagnose anemia and its subtypes and particularly evaluate the robustness of various approaches to noise and missing data. Experimental results show that the deep reinforcement learning algorithms show competitive performance compared to the state-of-the-art methods with the added advantage that they enable the progressive generation of a pathway to the suggested diagnosis, which can both guide and explain the decision process.
Authors: Hông Vân Lê
In this paper I propose a generative model of supervised learning that unifies two approaches to supervised learning, using a concept of a correct loss function. Addressing two measurability problems, which have been ignored in statistical learning theory, I propose to use convergence in outer probability to characterize the consistency of a learning algorithm. Building upon these results, I extend a result due to Cucker-Smale, which addresses the learnability of a regression model, to the setting of a conditional probability estimation problem. Additionally, I present a variant of Vapnik-Stefanuyk's regularization method for solving stochastic ill-posed problems, and using it to prove the generalizability of overparameterized supervised learning models.
Authors: Hongbin Ye, Honghao Gui, Xin Xu, Xi Chen, Huajun Chen, Ningyu Zhang
Conventional Knowledge Graph Construction (KGC) approaches typically follow the static information extraction paradigm with a closed set of pre-defined schema. As a result, such approaches fall short when applied to dynamic scenarios or domains, whereas a new type of knowledge emerges. This necessitates a system that can handle evolving schema automatically to extract information for KGC. To address this need, we propose a new task called schema-adaptable KGC, which aims to continually extract entity, relation, and event based on a dynamically changing schema graph without re-training. We first split and convert existing datasets based on three principles to build a benchmark, i.e., horizontal schema expansion, vertical schema expansion, and hybrid schema expansion; then investigate the schema-adaptable performance of several well-known approaches such as Text2Event, TANL, UIE and GPT-3.5. We further propose a simple yet effective baseline dubbed \textsc{AdaKGC}, which contains schema-enriched prefix instructor and schema-conditioned dynamic decoding to better handle evolving schema. Comprehensive experimental results illustrate that AdaKGC can outperform baselines but still have room for improvement. We hope the proposed work can deliver benefits to the community. Code and datasets available at https://github.com/zjunlp/AdaKGC.
Authors: Chandan Singh, Aliyah R. Hsu, Richard Antonello, Shailee Jain, Alexander G. Huth, Bin Yu, Jianfeng Gao
Large language models (LLMs) have demonstrated remarkable prediction performance for a growing array of tasks. However, their rapid proliferation and increasing opaqueness have created a growing need for interpretability. Here, we ask whether we can automatically obtain natural language explanations for black box text modules. A "text module" is any function that maps text to a scalar continuous value, such as a submodule within an LLM or a fitted model of a brain region. "Black box" indicates that we only have access to the module's inputs/outputs.
We introduce Summarize and Score (SASC), a method that takes in a text module and returns a natural language explanation of the module's selectivity along with a score for how reliable the explanation is. We study SASC in 3 contexts. First, we evaluate SASC on synthetic modules and find that it often recovers ground truth explanations. Second, we use SASC to explain modules found within a pre-trained BERT model, enabling inspection of the model's internals. Finally, we show that SASC can generate explanations for the response of individual fMRI voxels to language stimuli, with potential applications to fine-grained brain mapping. All code for using SASC and reproducing results is made available on Github.
Authors: Junze Liu, Aishik Ghosh, Dylan Smith, Pierre Baldi, Daniel Whiteson
Generation of simulated detector response to collision products is crucial to data analysis in particle physics, but computationally very expensive. One subdetector, the calorimeter, dominates the computational time due to the high granularity of its cells and complexity of the interactions. Generative models can provide more rapid sample production, but currently require significant effort to optimize performance for specific detector geometries, often requiring many models to describe the varying cell sizes and arrangements, without the ability to generalize to other geometries. We develop a $\textit{geometry-aware}$ autoregressive model, which learns how the calorimeter response varies with geometry, and is capable of generating simulated responses to unseen geometries without additional training. The geometry-aware model outperforms a baseline unaware model by over $50\%$ in several metrics such as the Wasserstein distance between the generated and the true distributions of key quantities which summarize the simulated response. A single geometry-aware model could replace the hundreds of generative models currently designed for calorimeter simulation by physicists analyzing data collected at the Large Hadron Collider. This proof-of-concept study motivates the design of a foundational model that will be a crucial tool for the study of future detectors, dramatically reducing the large upfront investment usually needed to develop generative calorimeter models.
Authors: Benjamin Coleman, Wang-Cheng Kang, Matthew Fahrbach, Ruoxi Wang, Lichan Hong, Ed H. Chi, Derek Zhiyuan Cheng
Learning high-quality feature embeddings efficiently and effectively is critical for the performance of web-scale machine learning systems. A typical model ingests hundreds of features with vocabularies on the order of millions to billions of tokens. The standard approach is to represent each feature value as a d-dimensional embedding, introducing hundreds of billions of parameters for extremely high-cardinality features. This bottleneck has led to substantial progress in alternative embedding algorithms. Many of these methods, however, make the assumption that each feature uses an independent embedding table. This work introduces a simple yet highly effective framework, Feature Multiplexing, where one single representation space is used across many different categorical features. Our theoretical and empirical analysis reveals that multiplexed embeddings can be decomposed into components from each constituent feature, allowing models to distinguish between features. We show that multiplexed representations lead to Pareto-optimal parameter-accuracy tradeoffs for three public benchmark datasets. Further, we propose a highly practical approach called Unified Embedding with three major benefits: simplified feature configuration, strong adaptation to dynamic data distributions, and compatibility with modern hardware. Unified embedding gives significant improvements in offline and online metrics compared to highly competitive baselines across five web-scale search, ads, and recommender systems, where it serves billions of users across the world in industry-leading products.
Authors: Tarek Naous, Michael J. Ryan, Anton Lavrouk, Mohit Chandra, Wei Xu
We present a systematic study and comprehensive evaluation of large language models for automatic multilingual readability assessment. In particular, we construct ReadMe++, a multilingual multi-domain dataset with human annotations of 9757 sentences in Arabic, English, French, Hindi, and Russian collected from 112 different data sources. ReadMe++ offers more domain and language diversity than existing readability datasets, making it ideal for benchmarking multilingual and non-English language models (including mBERT, XLM-R, mT5, Llama-2, GPT-4, etc.) in the supervised, unsupervised, and few-shot prompting settings. Our experiments reveal that models fine-tuned on ReadMe++ outperform those trained on single-domain datasets, showcasing superior performance on multi-domain readability assessment and cross-lingual transfer capabilities. We also compare to traditional readability metrics (such as Flesch-Kincaid Grade Level and Open Source Metric for Measuring Arabic Narratives), as well as the state-of-the-art unsupervised metric RSRS (Martinc et al., 2021). We will make our data and code publicly available at: https://github.com/tareknaous/readme.
Authors: Samuel Lanthaler, Nicholas H. Nelsen
This paper provides a comprehensive error analysis of learning with vector-valued random features (RF). The theory is developed for RF ridge regression in a fully general infinite-dimensional input-output setting, but nonetheless applies to and improves existing finite-dimensional analyses. In contrast to comparable work in the literature, the approach proposed here relies on a direct analysis of the underlying risk functional and completely avoids the explicit RF ridge regression solution formula in terms of random matrices. This removes the need for concentration results in random matrix theory or their generalizations to random operators. The main results established in this paper include strong consistency of vector-valued RF estimators under model misspecification and minimax optimal convergence rates in the well-specified setting. The parameter complexity (number of random features) and sample complexity (number of labeled data) required to achieve such rates are comparable with Monte Carlo intuition and free from logarithmic factors.
Authors: Dongyang Fan, Celestine Mendler-Dünner, Martin Jaggi
We consider a collaborative learning setting where the goal of each agent is to improve their own model by leveraging the expertise of collaborators, in addition to their own training data. To facilitate the exchange of expertise among agents, we propose a distillation-based method leveraging shared unlabeled auxiliary data, which is pseudo-labeled by the collective. Central to our method is a trust weighting scheme that serves to adaptively weigh the influence of each collaborator on the pseudo-labels until a consensus on how to label the auxiliary data is reached. We demonstrate empirically that our collaboration scheme is able to significantly boost the performance of individual models in the target domain from which the auxiliary data is sampled. By design, our method adeptly accommodates heterogeneity in model architectures and substantially reduces communication overhead compared to typical collaborative learning methods. At the same time, it can provably mitigate the negative impact of bad models on the collective.
Authors: Yu-Hsiang Wang, Huang-Yu Chen, Kai-Wei Chang, Winston Hsu, Hung-yi Lee
SUPERB was proposed to evaluate the generalizability of self-supervised learning (SSL) speech models across various tasks. However, it incurs high computational costs due to the large datasets and diverse tasks. In this paper, we introduce MiniSUPERB, a lightweight benchmark that efficiently evaluates SSL speech models with comparable results to SUPERB but lower computational costs significantly. We carefully select representative tasks, sample datasets, and extract model representations offline. Our approach achieves a Spearman's rank correlation of 0.954 and 0.982 with SUPERB Paper and SUPERB Challenge, respectively. Additionally, we reduce the computational cost by 97% in terms of Multiply-ACcumulate operations (MACs). Furthermore, we evaluate SSL speech models in few-shot scenarios and observe significant variations in their performance. To our knowledge, this is the first study to examine both the computational cost of the model itself and the cost of evaluating it on a benchmark.
Authors: Jonas Eschmann, Dario Albani, Giuseppe Loianno
Deep Reinforcement Learning (RL) has been demonstrated to yield capable agents and control policies in several domains but is commonly plagued by prohibitively long training times. Additionally, in the case of continuous control problems, the applicability of learned policies on real-world embedded devices is limited due to the lack of real-time guarantees and portability of existing deep learning libraries. To address these challenges, we present RLtools, a dependency-free, header-only, pure C++ library for deep supervised and reinforcement learning. Leveraging the template meta-programming capabilities of recent C++ standards, we provide composable components that can be tightly integrated by the compiler. Its novel architecture allows RLtools to be used seamlessly on a heterogeneous set of platforms, from HPC clusters over workstations and laptops to smartphones, smartwatches, and microcontrollers. Specifically, due to the tight integration of the RL algorithms with simulation environments, RLtools can solve popular RL problems like the Pendulum-v1 swing-up about 7 to 15 times faster in terms of wall-clock training time compared to other popular RL frameworks when using TD3. We also provide a low-overhead and parallelized interface to the MuJoCo simulator, showing that our PPO implementation achieves state of the art returns in the Ant-v4 environment while being 25%-30% faster in terms of wall-clock training time. Finally, we also benchmark the policy inference on a diverse set of microcontrollers and show that in most cases our optimized inference implementation is much faster than even the manufacturer's DSP libraries. To the best of our knowledge, RLtools enables the first-ever demonstration of training a deep RL algorithm directly on a microcontroller, giving rise to the field of TinyRL. The source code is available through our project page at https://rl.tools.
Authors: Abhilash Nandy, Manav Nitin Kapadnis, Sohan Patnaik, Yash Parag Butala, Pawan Goyal, Niloy Ganguly
As the demand for sophisticated Natural Language Processing (NLP) models continues to grow, so does the need for efficient pre-training techniques. Current NLP models undergo resource-intensive pre-training. In response, we introduce $FastDoc$ (Fast Pre-training Technique using Document-Level Metadata and Taxonomy), a novel approach designed to significantly reduce computational demands. $FastDoc$ leverages document metadata and domain-specific taxonomy as supervision signals. It involves continual pre-training of an open-domain transformer encoder using sentence-level embeddings, followed by fine-tuning using token-level embeddings. We evaluate $FastDoc$ on six tasks across nine datasets spanning three distinct domains. Remarkably, $FastDoc$ achieves remarkable compute reductions of approximately 1,000x, 4,500x, 500x compared to competitive approaches in Customer Support, Scientific, and Legal domains, respectively. Importantly, these efficiency gains do not compromise performance relative to competitive baselines. Furthermore, reduced pre-training data mitigates catastrophic forgetting, ensuring consistent performance in open-domain scenarios. $FastDoc$ offers a promising solution for resource-efficient pre-training, with potential applications spanning various domains.
Authors: Zeyu Zhou, Ruqi Bai, Sean Kulinski, Murat Kocaoglu, David I. Inouye
Answering counterfactual queries has many important applications such as knowledge discovery and explainability, but is challenging when causal variables are unobserved and we only see a projection onto an observation space, for instance, image pixels. One approach is to recover the latent Structural Causal Model (SCM), but this typically needs unrealistic assumptions, such as linearity of the causal mechanisms. Another approach is to use na\"ive ML approximations, such as generative models, to generate counterfactual samples; however, these lack guarantees of accuracy. In this work, we strive to strike a balance between practicality and theoretical guarantees by focusing on a specific type of causal query called domain counterfactuals, which hypothesizes what a sample would have looked like if it had been generated in a different domain (or environment). Concretely, by only assuming invertibility, sparse domain interventions and access to observational data from different domains, we aim to improve domain counterfactual estimation both theoretically and practically with less restrictive assumptions. We define domain counterfactually equivalent models and prove necessary and sufficient properties for equivalent models that provide a tight characterization of the domain counterfactual equivalence classes. Building upon this result, we prove that every equivalence class contains a model where all intervened variables are at the end when topologically sorted by the causal DAG. This surprising result suggests that a model design that only allows intervention in the last $k$ latent variables may improve model estimation for counterfactuals. We then test this model design on extensive simulated and image-based experiments which show the sparse canonical model indeed improves counterfactual estimation over baseline non-sparse models.
Authors: Maziar Gomrokchi, Owen Levin, Jeffrey Roach, Jonah White
We introduce AdCraft, a novel benchmark environment for the Reinforcement Learning (RL) community distinguished by its stochastic and non-stationary properties. The environment simulates bidding and budgeting dynamics within Search Engine Marketing (SEM), a digital marketing technique utilizing paid advertising to enhance the visibility of websites on search engine results pages (SERPs). The performance of SEM advertisement campaigns depends on several factors, including keyword selection, ad design, bid management, budget adjustments, and performance monitoring. Deep RL recently emerged as a potential strategy to optimize campaign profitability within the complex and dynamic landscape of SEM, but it requires substantial data, which may be costly or infeasible to acquire in practice. Our customizable environment enables practitioners to assess and enhance the robustness of RL algorithms pertinent to SEM bid and budget management without such costs. Through a series of experiments within the environment, we demonstrate the challenges imposed on agent convergence and performance by sparsity and non-stationarity. We hope these challenges further encourage discourse and development around effective strategies for managing real-world uncertainties.
Authors: Neeratyoy Mallik, Edward Bergman, Carl Hvarfner, Danny Stoll, Maciej Janowski, Marius Lindauer, Luigi Nardi, Frank Hutter
Hyperparameters of Deep Learning (DL) pipelines are crucial for their downstream performance. While a large number of methods for Hyperparameter Optimization (HPO) have been developed, their incurred costs are often untenable for modern DL. Consequently, manual experimentation is still the most prevalent approach to optimize hyperparameters, relying on the researcher's intuition, domain knowledge, and cheap preliminary explorations. To resolve this misalignment between HPO algorithms and DL researchers, we propose PriorBand, an HPO algorithm tailored to DL, able to utilize both expert beliefs and cheap proxy tasks. Empirically, we demonstrate PriorBand's efficiency across a range of DL benchmarks and show its gains under informative expert input and robustness against poor expert beliefs
Authors: Sebastian Zeng, Florian Graf, Roland Kwitt
We consider the problem of variational Bayesian inference in a latent variable model where a (possibly complex) observed stochastic process is governed by the solution of a latent stochastic differential equation (SDE). Motivated by the challenges that arise when trying to learn an (almost arbitrary) latent neural SDE from large-scale data, such as efficient gradient computation, we take a step back and study a specific subclass instead. In our case, the SDE evolves on a homogeneous latent space and is induced by stochastic dynamics of the corresponding (matrix) Lie group. In learning problems, SDEs on the unit $n$-sphere are arguably the most relevant incarnation of this setup. Notably, for variational inference, the sphere not only facilitates using a truly uninformative prior SDE, but we also obtain a particularly simple and intuitive expression for the Kullback-Leibler divergence between the approximate posterior and prior process in the evidence lower bound. Experiments demonstrate that a latent SDE of the proposed type can be learned efficiently by means of an existing one-step geometric Euler-Maruyama scheme. Despite restricting ourselves to a less diverse class of SDEs, we achieve competitive or even state-of-the-art performance on various time series interpolation and classification benchmarks.
Authors: Alec Helbling, Duen Horng Chau
There has been an explosion in interest in machine learning (ML) in recent years due to its applications to science and engineering. However, as ML techniques have advanced, tools for explaining and visualizing novel ML algorithms have lagged behind. Animation has been shown to be a powerful tool for making engaging visualizations of systems that dynamically change over time, which makes it well suited to the task of communicating ML algorithms. However, the current approach to animating ML algorithms is to handcraft applications that highlight specific algorithms or use complex generalized animation software. We developed ManimML, an open-source Python library for easily generating animations of ML algorithms directly from code. We sought to leverage ML practitioners' preexisting knowledge of programming rather than requiring them to learn complex animation software. ManimML has a familiar syntax for specifying neural networks that mimics popular deep learning frameworks like Pytorch. A user can take a preexisting neural network architecture and easily write a specification for an animation in ManimML, which will then automatically compose animations for different components of the system into a final animation of the entire neural network. ManimML is open source and available at https://github.com/helblazer811/ManimML.
Authors: Kavosh Asadi, Rasool Fakoor, Shoham Sabach
We focus on the task of approximating the optimal value function in deep reinforcement learning. This iterative process is comprised of solving a sequence of optimization problems where the loss function changes per iteration. The common approach to solving this sequence of problems is to employ modern variants of the stochastic gradient descent algorithm such as Adam. These optimizers maintain their own internal parameters such as estimates of the first-order and the second-order moments of the gradient, and update them over time. Therefore, information obtained in previous iterations is used to solve the optimization problem in the current iteration. We demonstrate that this can contaminate the moment estimates because the optimization landscape can change arbitrarily from one iteration to the next one. To hedge against this negative effect, a simple idea is to reset the internal parameters of the optimizer when starting a new iteration. We empirically investigate this resetting idea by employing various optimizers in conjunction with the Rainbow algorithm. We demonstrate that this simple modification significantly improves the performance of deep RL on the Atari benchmark.
Authors: Xuan Zhang, Limei Wang, Jacob Helwig, Youzhi Luo, Cong Fu, Yaochen Xie, Meng Liu, Yuchao Lin, Zhao Xu, Keqiang Yan, Keir Adams, Maurice Weiler, Xiner Li, Tianfan Fu, Yucheng Wang, Haiyang Yu, YuQing Xie, Xiang Fu, Alex Strasser, Shenglong Xu, Yi Liu, Yuanqi Du, Alexandra Saxton, Hongyi Ling, Hannah Lawrence, Hannes Stärk, Shurui Gui, Carl Edwards, Nicholas Gao, Adriana Ladera, Tailin Wu, Elyssa F. Hofgard, Aria Mansouri Tehrani, Rui Wang, Ameya Daigavane, Montgomery Bohde, Jerry Kurtin, Qian Huang, Tuong Phung, Minkai Xu, Chaitanya K. Joshi, Simon V. Mathis, Kamyar Azizzadenesheli, Ada Fang, Alán Aspuru-Guzik, Erik Bekkers, Michael Bronstein, Marinka Zitnik, Anima Anandkumar, Stefano Ermon, Pietro Liò, Rose Yu, Stephan Günnemann, Jure Leskovec, Heng Ji, Jimeng Sun, Regina Barzilay, et al. (6 additional authors not shown)
Advances in artificial intelligence (AI) are fueling a new paradigm of discoveries in natural sciences. Today, AI has started to advance natural sciences by improving, accelerating, and enabling our understanding of natural phenomena at a wide range of spatial and temporal scales, giving rise to a new area of research known as AI for science (AI4Science). Being an emerging research paradigm, AI4Science is unique in that it is an enormous and highly interdisciplinary area. Thus, a unified and technical treatment of this field is needed yet challenging. This work aims to provide a technically thorough account of a subarea of AI4Science; namely, AI for quantum, atomistic, and continuum systems. These areas aim at understanding the physical world from the subatomic (wavefunctions and electron density), atomic (molecules, proteins, materials, and interactions), to macro (fluids, climate, and subsurface) scales and form an important subarea of AI4Science. A unique advantage of focusing on these areas is that they largely share a common set of challenges, thereby allowing a unified and foundational treatment. A key common challenge is how to capture physics first principles, especially symmetries, in natural systems by deep learning methods. We provide an in-depth yet intuitive account of techniques to achieve equivariance to symmetry transformations. We also discuss other common technical challenges, including explainability, out-of-distribution generalization, knowledge transfer with foundation and large language models, and uncertainty quantification. To facilitate learning and education, we provide categorized lists of resources that we found to be useful. We strive to be thorough and unified and hope this initial effort may trigger more community interests and efforts to further advance AI4Science.
Authors: Ahmad Naser Eddin, Jacopo Bono, David Aparício, Hugo Ferreira, João Ascensão, Pedro Ribeiro, Pedro Bizarro
Many real-world datasets have an underlying dynamic graph structure, where entities and their interactions evolve over time. Machine learning models should consider these dynamics in order to harness their full potential in downstream tasks. Previous approaches for graph representation learning have focused on either sampling k-hop neighborhoods, akin to breadth-first search, or random walks, akin to depth-first search. However, these methods are computationally expensive and unsuitable for real-time, low-latency inference on dynamic graphs. To overcome these limitations, we propose graph-sprints a general purpose feature extraction framework for continuous-time-dynamic-graphs (CTDGs) that has low latency and is competitive with state-of-the-art, higher latency models. To achieve this, a streaming, low latency approximation to the random-walk based features is proposed. In our framework, time-aware node embeddings summarizing multi-hop information are computed using only single-hop operations on the incoming edges. We evaluate our proposed approach on three open-source datasets and two in-house datasets, and compare with three state-of-the-art algorithms (TGN-attn, TGN-ID, Jodie). We demonstrate that our graph-sprints features, combined with a machine learning classifier, achieve competitive performance (outperforming all baselines for the node classification tasks in five datasets). Simultaneously, graph-sprints significantly reduce inference latencies, achieving close to an order of magnitude speed-up in our experimental setting.
Authors: Xuan Zhao, Klaus Broelemann, Gjergji Kasneci
Counterfactual Explanations (CEs) are an important tool in Algorithmic Recourse for addressing two questions: 1. What are the crucial factors that led to an automated prediction/decision? 2. How can these factors be changed to achieve a more favorable outcome from a user's perspective? Thus, guiding the user's interaction with AI systems by proposing easy-to-understand explanations and easy-to-attain feasible changes is essential for the trustworthy adoption and long-term acceptance of AI systems. In the literature, various methods have been proposed to generate CEs, and different quality measures have been suggested to evaluate these methods. However, the generation of CEs is usually computationally expensive, and the resulting suggestions are unrealistic and thus non-actionable. In this paper, we introduce a new method to generate CEs for a pre-trained binary classifier by first shaping the latent space of an autoencoder to be a mixture of Gaussian distributions. CEs are then generated in latent space by linear interpolation between the query sample and the centroid of the target class. We show that our method maintains the characteristics of the input sample during the counterfactual search. In various experiments, we show that the proposed method is competitive based on different quality measures on image and tabular datasets -- efficiently returns results that are closer to the original data manifold compared to three state-of-the-art methods, which are essential for realistic high-dimensional machine learning applications.
Authors: Olivier Jeunen, Ivan Potapov, Aleksei Ustimenko
Approaches to recommendation are typically evaluated in one of two ways: (1) via a (simulated) online experiment, often seen as the gold standard, or (2) via some offline evaluation procedure, where the goal is to approximate the outcome of an online experiment. Several offline evaluation metrics have been adopted in the literature, inspired by ranking metrics prevalent in the field of Information Retrieval. (Normalised) Discounted Cumulative Gain (nDCG) is one such metric that has seen widespread adoption in empirical studies, and higher (n)DCG values have been used to present new methods as the state-of-the-art in top-$n$ recommendation for many years.
Our work takes a critical look at this approach, and investigates when we can expect such metrics to approximate the gold standard outcome of an online experiment. We formally present the assumptions that are necessary to consider DCG an unbiased estimator of online reward and provide a derivation for this metric from first principles, highlighting where we deviate from its traditional uses in IR. Importantly, we show that normalising the metric renders it inconsistent, in that even when DCG is unbiased, ranking competing methods by their normalised DCG can invert their relative order. Through a correlation analysis between off- and on-line experiments conducted on a large-scale recommendation platform, we show that our unbiased DCG estimates strongly correlate with online reward, even when some of the metric's inherent assumptions are violated. This statement no longer holds for its normalised variant, suggesting that nDCG's practical utility may be limited.
Authors: Preethi Seshadri, Sameer Singh, Yanai Elazar
Bias amplification is a phenomenon in which models exacerbate biases or stereotypes present in the training data. In this paper, we study bias amplification in the text-to-image domain using Stable Diffusion by comparing gender ratios in training vs. generated images. We find that the model appears to amplify gender-occupation biases found in the training data (LAION) considerably. However, we discover that amplification can be largely attributed to discrepancies between training captions and model prompts. For example, an inherent difference is that captions from the training data often contain explicit gender information while our prompts do not, which leads to a distribution shift and consequently inflates bias measures. Once we account for distributional differences between texts used for training and generation when evaluating amplification, we observe that amplification decreases drastically. Our findings illustrate the challenges of comparing biases in models and their training data, and highlight confounding factors that impact analyses.
Authors: Shintaro Nakamura, Masashi Sugiyama
We study the real-valued combinatorial pure exploration of the multi-armed bandit (R-CPE-MAB) problem. In R-CPE-MAB, a player is given $d$ stochastic arms, and the reward of each arm $s\in\{1, \ldots, d\}$ follows an unknown distribution with mean $\mu_s$. In each time step, a player pulls a single arm and observes its reward. The player's goal is to identify the optimal \emph{action} $\boldsymbol{\pi}^{*} = \argmax_{\boldsymbol{\pi} \in \mathcal{A}} \boldsymbol{\mu}^{\top}\boldsymbol{\pi}$ from a finite-sized real-valued \emph{action set} $\mathcal{A}\subset \mathbb{R}^{d}$ with as few arm pulls as possible. Previous methods in the R-CPE-MAB assume that the size of the action set $\mathcal{A}$ is polynomial in $d$. We introduce an algorithm named the Generalized Thompson Sampling Explore (GenTS-Explore) algorithm, which is the first algorithm that can work even when the size of the action set is exponentially large in $d$. We also introduce a novel problem-dependent sample complexity lower bound of the R-CPE-MAB problem, and show that the GenTS-Explore algorithm achieves the optimal sample complexity up to a problem-dependent constant factor.
Authors: Noam Fluss, Guy Hacohen, Daphna Weinshall
Semi-Supervised Learning (SSL) is a framework that utilizes both labeled and unlabeled data to enhance model performance. Conventional SSL methods operate under the assumption that labeled and unlabeled data share the same label space. However, in practical real-world scenarios, especially when the labeled training dataset is limited in size, some classes may be totally absent from the labeled set. To address this broader context, we propose a general approach to augment existing SSL methods, enabling them to effectively handle situations where certain classes are missing. This is achieved by introducing an additional term into their objective function, which penalizes the KL-divergence between the probability vectors of the true class frequencies and the inferred class frequencies. Our experimental results reveal significant improvements in accuracy when compared to state-of-the-art SSL, open-set SSL, and open-world SSL methods. We conducted these experiments on two benchmark image classification datasets, CIFAR-100 and STL-10, with the most remarkable improvements observed when the labeled data is severely limited, with only a few labeled examples per class
Authors: Zhen Bi, Ningyu Zhang, Yinuo Jiang, Shumin Deng, Guozhou Zheng, Huajun Chen
In the realm of embodied artificial intelligence, the reasoning capabilities of Large Language Models (LLMs) play a pivotal role. Although there are effective methods like program-of-thought prompting for LLMs which uses programming language to tackle complex reasoning tasks, the specific impact of code data on the improvement of reasoning capabilities remains under-explored. To address this gap, we propose complexity-impacted reasoning score (CIRS), which combines structural and logical attributes, to measure the correlation between code and reasoning abilities. Specifically, we use the abstract syntax tree to encode the structural information and calculate logical complexity by considering the difficulty and the cyclomatic complexity. Through an empirical analysis, we find not all code data of complexity can be learned or understood by LLMs. Optimal level of complexity is critical to the improvement of reasoning abilities by program-aided prompting. Then we design an auto-synthesizing and stratifying algorithm, and apply it to instruction generation for mathematical reasoning and code data filtering for code generation tasks. Extensive results demonstrates the effectiveness of our proposed approach. Code will be integrated into the EasyInstruct framework at https://github.com/zjunlp/EasyInstruct.
Authors: Tyler LaBonte, Vidya Muthukumar, Abhishek Kumar
Empirical risk minimization (ERM) of neural networks is prone to over-reliance on spurious correlations and poor generalization on minority groups. The recent deep feature reweighting (DFR) technique achieves state-of-the-art group robustness via simple last-layer retraining, but it requires held-out group and class annotations to construct a group-balanced reweighting dataset. In this work, we examine this impractical requirement and find that last-layer retraining can be surprisingly effective with no group annotations (other than for model selection) and only a handful of class annotations. We first show that last-layer retraining can greatly improve worst-group accuracy even when the reweighting dataset has only a small proportion of worst-group data. This implies a "free lunch" where holding out a subset of training data to retrain the last layer can substantially outperform ERM on the entire dataset with no additional data or annotations. To further improve group robustness, we introduce a lightweight method called selective last-layer finetuning (SELF), which constructs the reweighting dataset using misclassifications or disagreements. Our empirical and theoretical results present the first evidence that model disagreement upsamples worst-group data, enabling SELF to nearly match DFR on four well-established benchmarks across vision and language tasks with no group annotations and less than 3% of the held-out class annotations. Our code is available at https://github.com/tmlabonte/last-layer-retraining.
Authors: Mohamad M.A. Ashames, Ahmet Demir, Omer N. Gerek, Mehmet Fidan, M. Bilginer Gulmezoglu, Semih Ergin, Mehmet Koc, Atalay Barkana, Cuneyt Calisir
Following the great success of various deep learning methods in image and object classification, the biomedical image processing society is also overwhelmed with their applications to various automatic diagnosis cases. Unfortunately, most of the deep learning-based classification attempts in the literature solely focus on the aim of extreme accuracy scores, without considering interpretability, or patient-wise separation of training and test data. For example, most lung nodule classification papers using deep learning randomly shuffle data and split it into training, validation, and test sets, causing certain images from the CT scan of a person to be in the training set, while other images of the exact same person to be in the validation or testing image sets. This can result in reporting misleading accuracy rates and the learning of irrelevant features, ultimately reducing the real-life usability of these models. When the deep neural networks trained on the traditional, unfair data shuffling method are challenged with new patient images, it is observed that the trained models perform poorly. In contrast, deep neural networks trained with strict patient-level separation maintain their accuracy rates even when new patient images are tested. Heat-map visualizations of the activations of the deep neural networks trained with strict patient-level separation indicate a higher degree of focus on the relevant nodules. We argue that the research question posed in the title has a positive answer only if the deep neural networks are trained with images of patients that are strictly isolated from the validation and testing patient sets.
Authors: Joel Oskarsson, Tomas Landelius, Fredrik Lindsten
The rise of accurate machine learning methods for weather forecasting is creating radical new possibilities for modeling the atmosphere. In the time of climate change, having access to high-resolution forecasts from models like these is also becoming increasingly vital. While most existing Neural Weather Prediction (NeurWP) methods focus on global forecasting, an important question is how these techniques can be applied to limited area modeling. In this work we adapt the graph-based NeurWP approach to the limited area setting and propose a multi-scale hierarchical model extension. Our approach is validated by experiments with a local model for the Nordic region.
Authors: Pei Xu, Kaixiang Xie, Sheldon Andrews, Paul G. Kry, Michael Neff, Morgan McGuire, Ioannis Karamouzas, Victor Zordan
Motivated by humans' ability to adapt skills in the learning of new ones, this paper presents AdaptNet, an approach for modifying the latent space of existing policies to allow new behaviors to be quickly learned from like tasks in comparison to learning from scratch. Building on top of a given reinforcement learning controller, AdaptNet uses a two-tier hierarchy that augments the original state embedding to support modest changes in a behavior and further modifies the policy network layers to make more substantive changes. The technique is shown to be effective for adapting existing physics-based controllers to a wide range of new styles for locomotion, new task targets, changes in character morphology and extensive changes in environment. Furthermore, it exhibits significant increase in learning efficiency, as indicated by greatly reduced training times when compared to training from scratch or using other approaches that modify existing policies. Code is available at https://motion-lab.github.io/AdaptNet.
Authors: Ties van Rozendaal, Tushar Singhal, Hoang Le, Guillaume Sautiere, Amir Said, Krishna Buska, Anjuman Raha, Dimitris Kalatzis, Hitarth Mehta, Frank Mayer, Liang Zhang, Markus Nagel, Auke Wiggers
Neural video codecs have recently become competitive with standard codecs such as HEVC in the low-delay setting. However, most neural codecs are large floating-point networks that use pixel-dense warping operations for temporal modeling, making them too computationally expensive for deployment on mobile devices. Recent work has demonstrated that running a neural decoder in real time on mobile is feasible, but shows this only for 720p RGB video. This work presents the first neural video codec that decodes 1080p YUV420 video in real time on a mobile device. Our codec relies on two major contributions. First, we design an efficient codec that uses a block-based motion compensation algorithm available on the warping core of the mobile accelerator, and we show how to quantize this model to integer precision. Second, we implement a fast decoder pipeline that concurrently runs neural network components on the neural signal processor, parallel entropy coding on the mobile GPU, and warping on the warping core. Our codec outperforms the previous on-device codec by a large margin with up to 48% BD-rate savings, while reducing the MAC count on the receiver side by $10 \times$. We perform a careful ablation to demonstrate the effect of the introduced motion compensation scheme, and ablate the effect of model quantization.
Authors: Ibrahim Ethem Hamamci
Glioblastoma is a highly aggressive and lethal form of brain cancer. Magnetic resonance imaging (MRI) plays a significant role in the diagnosis, treatment planning, and follow-up of glioblastoma patients due to its non-invasive and radiation-free nature. The International Brain Tumor Segmentation (BraTS) challenge has contributed to generating numerous AI algorithms to accurately and efficiently segment glioblastoma sub-compartments using four structural (T1, T1Gd, T2, T2-FLAIR) MRI scans. However, these four MRI sequences may not always be available. To address this issue, Generative Adversarial Networks (GANs) can be used to synthesize the missing MRI sequences. In this paper, we implement and utilize an open-source GAN approach that takes any three MRI sequences as input to generate the missing fourth structural sequence. Our proposed approach is contributed to the community-driven generally nuanced deep learning framework (GaNDLF) and demonstrates promising results in synthesizing high-quality and realistic MRI sequences, enabling clinicians to improve their diagnostic capabilities and support the application of AI methods to brain tumor MRI quantification.
Authors: Maya Okawa, Ekdeep Singh Lubana, Robert P. Dick, Hidenori Tanaka
Modern generative models exhibit unprecedented capabilities to generate extremely realistic data. However, given the inherent compositionality of the real world, reliable use of these models in practical applications requires that they exhibit the capability to compose a novel set of concepts to generate outputs not seen in the training data set. Prior work demonstrates that recent diffusion models do exhibit intriguing compositional generalization abilities, but also fail unpredictably. Motivated by this, we perform a controlled study for understanding compositional generalization in conditional diffusion models in a synthetic setting, varying different attributes of the training data and measuring the model's ability to generate samples out-of-distribution. Our results show: (i) the order in which the ability to generate samples from a concept and compose them emerges is governed by the structure of the underlying data-generating process; (ii) performance on compositional tasks exhibits a sudden "emergence" due to multiplicative reliance on the performance of constituent tasks, partially explaining emergent phenomena seen in generative models; and (iii) composing concepts with lower frequency in the training data to generate out-of-distribution samples requires considerably more optimization steps compared to generating in-distribution samples. Overall, our study lays a foundation for understanding capabilities and compositionality in generative models from a data-centric perspective.
Authors: Ti-Rong Wu, Hung Guei, Po-Wei Huang, Pei-Chiun Peng, Ting Han Wei, Chung-Chin Shih, Yun-Jui Tsai
This paper presents MiniZero, a zero-knowledge learning framework that supports four state-of-the-art algorithms, including AlphaZero, MuZero, Gumbel AlphaZero, and Gumbel MuZero. While these algorithms have demonstrated super-human performance in many games, it remains unclear which among them is most suitable or efficient for specific tasks. Through MiniZero, we systematically evaluate the performance of each algorithm in two board games, 9x9 Go and 8x8 Othello, as well as 57 Atari games. For two board games, using more simulations generally results in higher performance. However, the choice of AlphaZero and MuZero may differ based on game properties. For Atari games, both MuZero and Gumbel MuZero are worth considering. Since each game has unique characteristics, different algorithms and simulations yield varying results. In addition, we introduce an approach, called progressive simulation, which progressively increases the simulation budget during training to allocate computation more efficiently. Our empirical results demonstrate that progressive simulation achieves significantly superior performance in two board games. By making our framework and trained models publicly available, this paper contributes a benchmark for future research on zero-knowledge learning algorithms, assisting researchers in algorithm selection and comparison against these zero-knowledge learning baselines. Our code and data are available at https://rlg.iis.sinica.edu.tw/papers/minizero.
Authors: Lihang Liu, Donglong He, Xianbin Ye, Jingbo Zhou, Shanzhuo Zhang, Xiaonan Zhang, Jun Li, Hua Chai, Fan Wang, Jingzhou He, Liang Zheng, Yonghui Li, Xiaomin Fang
Protein-ligand structure prediction is an essential task in drug discovery, predicting the binding interactions between small molecules (ligands) and target proteins (receptors). Although conventional physics-based docking tools are widely utilized, their accuracy is compromised by limited conformational sampling and imprecise scoring functions. Recent advances have incorporated deep learning techniques to improve the accuracy of structure prediction. Nevertheless, the experimental validation of docking conformations remains costly, it raises concerns regarding the generalizability of these deep learning-based methods due to the limited training data. In this work, we show that by pre-training a geometry-aware SE(3)-Equivariant neural network on a large-scale docking conformation generated by traditional physics-based docking tools and then fine-tuning with a limited set of experimentally validated receptor-ligand complexes, we can achieve outstanding performance. This process involved the generation of 100 million docking conformations, consuming roughly 1 million CPU core days. The proposed model, HelixDock, aims to acquire the physical knowledge encapsulated by the physics-based docking tools during the pre-training phase. HelixDock has been benchmarked against both physics-based and deep learning-based baselines, showing that it outperforms its closest competitor by over 40% for RMSD. HelixDock also exhibits enhanced performance on a dataset that poses a greater challenge, thereby highlighting its robustness. Moreover, our investigation reveals the scaling laws governing pre-trained structure prediction models, indicating a consistent enhancement in performance with increases in model parameters and pre-training data. This study illuminates the strategic advantage of leveraging a vast and varied repository of generated data to advance the frontiers of AI-driven drug discovery.
Authors: Michael I. Jordan, Tianyi Lin, Zhengyuan Zhou
Online gradient descent (OGD) is well known to be doubly optimal under strong convexity or monotonicity assumptions: (1) in the single-agent setting, it achieves an optimal regret of $\Theta(\log T)$ for strongly convex cost functions; and (2) in the multi-agent setting of strongly monotone games, with each agent employing OGD, we obtain last-iterate convergence of the joint action to a unique Nash equilibrium at an optimal rate of $\Theta(\frac{1}{T})$. While these finite-time guarantees highlight its merits, OGD has the drawback that it requires knowing the strong convexity/monotonicity parameters. In this paper, we design a fully adaptive OGD algorithm, \textsf{AdaOGD}, that does not require a priori knowledge of these parameters. In the single-agent setting, our algorithm achieves $O(\log^2(T))$ regret under strong convexity, which is optimal up to a log factor. Further, if each agent employs \textsf{AdaOGD} in strongly monotone games, the joint action converges in a last-iterate sense to a unique Nash equilibrium at a rate of $O(\frac{\log^3 T}{T})$, again optimal up to log factors. We illustrate our algorithms in a learning version of the classical newsvendor problem, where due to lost sales, only (noisy) gradient feedback can be observed. Our results immediately yield the first feasible and near-optimal algorithm for both the single-retailer and multi-retailer settings. We also extend our results to the more general setting of exp-concave cost functions and games, using the online Newton step (ONS) algorithm.
Authors: Illia Horenko
Simply-verifiable mathematical conditions for existence, uniqueness and explicit analytical computation of minimal adversarial paths (MAP) and minimal adversarial distances (MAD) for (locally) uniquely-invertible classifiers, for generalized linear models (GLM), and for entropic AI (EAI) are formulated and proven. Practical computation of MAP and MAD, their comparison and interpretations for various classes of AI tools (for neuronal networks, boosted random forests, GLM and EAI) are demonstrated on the common synthetic benchmarks: on a double Swiss roll spiral and its extensions, as well as on the two biomedical data problems (for the health insurance claim predictions, and for the heart attack lethality classification). On biomedical applications it is demonstrated how MAP provides unique minimal patient-specific risk-mitigating interventions in the predefined subsets of accessible control variables.
Authors: Moussa Koulako Bala Doumbouya, Baba Mamadi Diané, Solo Farabado Cissé, Djibrila Diané, Abdoulaye Sow, Séré Moussa Doumbouya, Daouda Bangoura, Fodé Moriba Bayo, Ibrahima Sory 2. Condé, Kalo Mory Diané, Chris Piech, Christopher Manning
Currently, there is no usable machine translation system for Nko, a language spoken by tens of millions of people across multiple West African countries, which holds significant cultural and educational value.
To address this issue, we present a set of tools, resources, and baseline results aimed towards the development of usable machine translation systems for Nko and other languages that do not currently have sufficiently large parallel text corpora available.
(1) Fria$\parallel$el: A novel collaborative parallel text curation software that incorporates quality control through copyedit-based workflows.
(2) Expansion of the FLoRes-200 and NLLB-Seed corpora with 2,009 and 6,193 high-quality Nko translations in parallel with 204 and 40 other languages.
(3) nicolingua-0005: A collection of trilingual and bilingual corpora with 130,850 parallel segments and monolingual corpora containing over 3 million Nko words.
(4) Baseline bilingual and multilingual neural machine translation results with the best model scoring 30.83 English-Nko chrF++ on FLoRes-devtest.
Authors: Shintaro Nakamura, Masashi Sugiyama
We study the real-valued combinatorial pure exploration of the multi-armed bandit in the fixed-budget setting. We first introduce the Combinatorial Successive Asign (CSA) algorithm, which is the first algorithm that can identify the best action even when the size of the action class is exponentially large with respect to the number of arms. We show that the upper bound of the probability of error of the CSA algorithm matches a lower bound up to a logarithmic factor in the exponent. Then, we introduce another algorithm named the Minimax Combinatorial Successive Accepts and Rejects (Minimax-CombSAR) algorithm for the case where the size of the action class is polynomial, and show that it is optimal, which matches a lower bound. Finally, we experimentally compare the algorithms with previous methods and show that our algorithm performs better.
Authors: Yuan Peiwen, Zhu Changsheng
There has been an emergence of various models for long-term time series forecasting. Recent studies have demonstrated that a single linear layer, using Channel Dependent (CD) or Channel Independent (CI) modeling, can even outperform a large number of sophisticated models. However, current research primarily considers CD and CI as two complementary yet mutually exclusive approaches, unable to harness these two extremes simultaneously. And it is also a challenging issue that both CD and CI are static strategies that cannot be determined to be optimal for a specific dataset without extensive experiments. In this paper, we reconsider whether the current CI strategy is the best solution for time series forecasting. First, we propose a simple yet effective strategy called CSC, which stands for $\mathbf{C}$hannel $\mathbf{S}$elf-$\mathbf{C}$lustering strategy, for linear models. Our Channel Self-Clustering (CSC) enhances CI strategy's performance improvements while reducing parameter size, for exmpale by over 10 times on electricity dataset, and significantly cutting training time. Second, we further propose Channel Rearrangement (CR), a method for deep models inspired by the self-clustering. CR attains competitive performance against baselines. Finally, we also discuss whether it is best to forecast the future values using the historical values of the same channel as inputs. We hope our findings and methods could inspire new solutions beyond CD/CI.
Authors: Erik Andries, Ramin Nikzad-Langerodi
Spectroscopic measurements can show distorted spectral shapes arising from a mixture of absorbing and scattering contributions. These distortions (or baselines) often manifest themselves as non-constant offsets or low-frequency oscillations. As a result, these baselines can adversely affect analytical and quantitative results. Baseline correction is an umbrella term where one applies pre-processing methods to obtain baseline spectra (the unwanted distortions) and then remove the distortions by differencing. However, current state-of-the art baseline correction methods do not utilize analyte concentrations even if they are available, or even if they contribute significantly to the observed spectral variability. We examine a class of state-of-the-art methods (penalized baseline correction) and modify them such that they can accommodate a priori analyte concentrations such that prediction can be enhanced. Performance will be assessed on two near infra-red data sets across both classical penalized baseline correction methods (without analyte information) and modified penalized baseline correction methods (leveraging analyte information).
Authors: Ta-Chung Chi, Ting-Han Fan, Alexander I. Rudnicky
An ideal length-extrapolatable Transformer language model can handle sequences longer than the training length without any fine-tuning. Such long-context utilization capability relies heavily on a flexible positional embedding design. Upon investigating the flexibility of existing large pre-trained Transformer language models, we find that the T5 family deserves a closer look, as its positional embeddings capture rich and flexible attention patterns. However, T5 suffers from the dispersed attention issue: the longer the input sequence, the flatter the attention distribution. To alleviate the issue, we propose two attention alignment strategies via temperature scaling. Our findings show improvement on the long-context utilization capability of T5 on language modeling, retrieval, multi-document question answering, and code completion tasks without any fine-tuning. This suggests that a flexible positional embedding design and attention alignment can go a long way toward Transformer length extrapolation.
Authors: Bohui Shen, Wei Zhang, Xubiao Liu, Pengfei Yu, Shirui Jiang, Xinchong Shi, Xiangsong Zhang, Xiaoyu Zhou, Weirui Zhang, Bingxuan Li, Qiegen Liu
Positron emission tomography (PET) serves as an essential tool for diagnosis of encephalopathy and brain science research. However, it suffers from the limited choice of tracers. Nowadays, with the wide application of PET imaging in neuropsychiatric treatment, 6-18F-fluoro-3, 4-dihydroxy-L-phenylalanine (DOPA) has been found to be more effective than 18F-labeled fluorine-2-deoxyglucose (FDG) in the field. Nevertheless, due to the complexity of its preparation and other limitations, DOPA is far less widely used than FDG. To address this issue, a tracer conversion invertible neural network (TC-INN) for image projection is developed to map FDG images to DOPA images through deep learning. More diagnostic information is obtained by generating PET images from FDG to DOPA. Specifically, the proposed TC-INN consists of two separate phases, one for training traceable data, the other for rebuilding new data. The reference DOPA PET image is used as a learning target for the corresponding network during the training process of tracer conversion. Meanwhile, the invertible network iteratively estimates the resultant DOPA PET data and compares it to the reference DOPA PET data. Notably, the reversible model employs variable enhancement technique to achieve better power generation. Moreover, image registration needs to be performed before training due to the angular deviation of the acquired FDG and DOPA data information. Experimental results exhibited excellent generation capability in mapping between FDG and DOPA, suggesting that PET tracer conversion has great potential in the case of limited tracer applications.
Authors: Fangjun Zhou, Anyong Mao, Eftychios Sifakis
We proposed a new Convolution Neural Network implementation optimized for sparse 3D data inference. This implementation uses NanoVDB as the data structure to store the sparse tensor. It leaves a relatively small memory footprint while maintaining high performance. We demonstrate that this architecture is around 20 times faster than the state-of-the-art dense CNN model on a high-resolution 3D object classification network.
Authors: Yiqiu Shen, Jungkyu Park, Frank Yeung, Eliana Goldberg, Laura Heacock, Farah Shamout, Krzysztof J. Geras
Breast cancer screening, primarily conducted through mammography, is often supplemented with ultrasound for women with dense breast tissue. However, existing deep learning models analyze each modality independently, missing opportunities to integrate information across imaging modalities and time. In this study, we present Multi-modal Transformer (MMT), a neural network that utilizes mammography and ultrasound synergistically, to identify patients who currently have cancer and estimate the risk of future cancer for patients who are currently cancer-free. MMT aggregates multi-modal data through self-attention and tracks temporal tissue changes by comparing current exams to prior imaging. Trained on 1.3 million exams, MMT achieves an AUROC of 0.943 in detecting existing cancers, surpassing strong uni-modal baselines. For 5-year risk prediction, MMT attains an AUROC of 0.826, outperforming prior mammography-based risk models. Our research highlights the value of multi-modal and longitudinal imaging in cancer diagnosis and risk stratification.
Authors: Rūta Binkytė, Carlos Pinzón, Szilvia Lestyán, Kangsoo Jung, Héber H. Arcolezi, Catuscia Palamidessi
Differential privacy is a widely adopted framework designed to safeguard the sensitive information of data providers within a data set. It is based on the application of controlled noise at the interface between the server that stores and processes the data, and the data consumers. Local differential privacy is a variant that allows data providers to apply the privatization mechanism themselves on their data individually. Therefore it provides protection also in contexts in which the server, or even the data collector, cannot be trusted. The introduction of noise, however, inevitably affects the utility of the data, particularly by distorting the correlations between individual data components. This distortion can prove detrimental to tasks such as causal discovery. In this paper, we consider various well-known locally differentially private mechanisms and compare the trade-off between the privacy they provide, and the accuracy of the causal structure produced by algorithms for causal learning when applied to data obfuscated by these mechanisms. Our analysis yields valuable insights for selecting appropriate local differentially private protocols for causal discovery tasks. We foresee that our findings will aid researchers and practitioners in conducting locally private causal discovery.
Authors: Hanlin Zhang, Benjamin L. Edelman, Danilo Francati, Daniele Venturi, Giuseppe Ateniese, Boaz Barak
Watermarking generative models consists of planting a statistical signal (watermark) in a model's output so that it can be later verified that the output was generated by the given model. A strong watermarking scheme satisfies the property that a computationally bounded attacker cannot erase the watermark without causing significant quality degradation. In this paper, we study the (im)possibility of strong watermarking schemes. We prove that, under well-specified and natural assumptions, strong watermarking is impossible to achieve. This holds even in the private detection algorithm setting, where the watermark insertion and detection algorithms share a secret key, unknown to the attacker. To prove this result, we introduce a generic efficient watermark attack; the attacker is not required to know the private key of the scheme or even which scheme is used. Our attack is based on two assumptions: (1) The attacker has access to a "quality oracle" that can evaluate whether a candidate output is a high-quality response to a prompt, and (2) The attacker has access to a "perturbation oracle" which can modify an output with a nontrivial probability of maintaining quality, and which induces an efficiently mixing random walk on high-quality outputs. We argue that both assumptions can be satisfied in practice by an attacker with weaker computational capabilities than the watermarked model itself, to which the attacker has only black-box access. Furthermore, our assumptions will likely only be easier to satisfy over time as models grow in capabilities and modalities. We demonstrate the feasibility of our attack by instantiating it to attack three existing watermarking schemes for large language models: Kirchenbauer et al. (2023), Kuditipudi et al. (2023), and Zhao et al. (2023). The same attack successfully removes the watermarks planted by all three schemes, with only minor quality degradation.
Authors: Matt Gorbett, Hossein Shirazi, Indrakshi Ray
Learning from the collective knowledge of data dispersed across private sources can provide neural networks with enhanced generalization capabilities. Federated learning, a method for collaboratively training a machine learning model across remote clients, achieves this by combining client models via the orchestration of a central server. However, current approaches face two critical limitations: i) they struggle to converge when client domains are sufficiently different, and ii) current aggregation techniques produce an identical global model for each client. In this work, we address these issues by reformulating the typical federated learning setup: rather than learning a single global model, we learn N models each optimized for a common objective. To achieve this, we apply a weighted distance minimization to model parameters shared in a peer-to-peer topology. The resulting framework, Iterative Parameter Alignment, applies naturally to the cross-silo setting, and has the following properties: (i) a unique solution for each participant, with the option to globally converge each model in the federation, and (ii) an optional early-stopping mechanism to elicit fairness among peers in collaborative learning settings. These characteristics jointly provide a flexible new framework for iteratively learning from peer models trained on disparate datasets. We find that the technique achieves competitive results on a variety of data partitions compared to state-of-the-art approaches. Further, we show that the method is robust to divergent domains (i.e. disjoint classes across peers) where existing approaches struggle.
Authors: Jing Hu, Qinrui Fan, Shu Hu, Siwei Lyu, Xi Wu, Xin Wang
In the field of clinical medicine, computed tomography (CT) is an effective medical imaging modality for the diagnosis of various pathologies. Compared with X-ray images, CT images can provide more information, including multi-planar slices and three-dimensional structures for clinical diagnosis. However, CT imaging requires patients to be exposed to large doses of ionizing radiation for a long time, which may cause irreversible physical harm. In this paper, we propose an Uncertainty-aware MedNeRF (UMedNeRF) network based on generated radiation fields. The network can learn a continuous representation of CT projections from 2D X-ray images by obtaining the internal structure and depth information and using adaptive loss weights to ensure the quality of the generated images. Our model is trained on publicly available knee and chest datasets, and we show the results of CT projection rendering with a single X-ray and compare our method with other methods based on generated radiation fields.
Authors: Franz A. Heinsen
We find a succinct expression for computing the sequence $x_t = a_t x_{t-1} + b_t$ in parallel with two prefix sums, given $t = (1, 2, \dots, n)$, $a_t \in \mathbb{R}^n$, $b_t \in \mathbb{R}^n$, and initial value $x_0 \in \mathbb{R}$. On $n$ parallel processors, the computation of $n$ elements incurs $\mathcal{O}(\log n)$ time and $\mathcal{O}(n)$ space. Sequences of this form are ubiquitous in science and engineering, making efficient parallelization useful for a vast number of applications. We implement our expression in software, test it on parallel hardware, and verify that it executes faster than sequential computation by a factor of $\frac{n}{\log n}$.
Authors: Ziyu Lu, Anika Tabassum, Shruti Kulkarni, Lu Mi, J. Nathan Kutz, Eric Shea-Brown, Seung-Hwan Lim
This paper explores the potential of the transformer models for learning Granger causality in networks with complex nonlinear dynamics at every node, as in neurobiological and biophysical networks. Our study primarily focuses on a proof-of-concept investigation based on simulated neural dynamics, for which the ground-truth causality is known through the underlying connectivity matrix. For transformer models trained to forecast neuronal population dynamics, we show that the cross attention module effectively captures the causal relationship among neurons, with an accuracy equal or superior to that for the most popular Granger causality analysis method. While we acknowledge that real-world neurobiology data will bring further challenges, including dynamic connectivity and unobserved variability, this research offers an encouraging preliminary glimpse into the utility of the transformer model for causal representation learning in neuroscience.
Authors: Byeong-Hoo Lee, Byoung-Hee Kwon, Seong-Whan Lee
Deep learning has shown promise in decoding brain signals, such as electroencephalogram (EEG), in the field of brain-computer interfaces (BCIs). However, the non-stationary characteristics of EEG signals pose challenges for training neural networks to acquire appropriate knowledge. Inconsistent EEG signals resulting from these non-stationary characteristics can lead to poor performance. Therefore, it is crucial to investigate and address sample inconsistency to ensure robust performance in spontaneous BCIs. In this study, we introduce the concept of sample dominance as a measure of EEG signal inconsistency and propose a method to modulate its effect on network training. We present a two-stage dominance score estimation technique that compensates for performance degradation caused by sample inconsistencies. Our proposed method utilizes non-parametric estimation to infer sample inconsistency and assigns each sample a dominance score. This score is then aggregated with the loss function during training to modulate the impact of sample inconsistency. Furthermore, we design a curriculum learning approach that gradually increases the influence of inconsistent signals during training to improve overall performance. We evaluate our proposed method using public spontaneous BCI dataset. The experimental results confirm that our findings highlight the importance of addressing sample dominance for achieving robust performance in spontaneous BCIs.
Authors: Amina Mollaysa, Ahmed Allam, Michael Krauthammer
Human genetic diseases often arise from point mutations, emphasizing the critical need for precise genome editing techniques. Among these, base editing stands out as it allows targeted alterations at the single nucleotide level. However, its clinical application is hindered by low editing efficiency and unintended mutations, necessitating extensive trial-and-error experimentation in the laboratory. To speed up this process, we present an attention-based two-stage machine learning model that learns to predict the likelihood of all possible editing outcomes for a given genomic target sequence. We further propose a multi-task learning schema to jointly learn multiple base editors (i.e. variants) at once. Our model's predictions consistently demonstrated a strong correlation with the actual experimental results on multiple datasets and base editor variants. These results provide further validation for the models' capacity to enhance and accelerate the process of refining base editing designs.
Authors: Tomer Bar Natan, Gilad Deutch, Nadav Magar, Guy Dar
In-context learning (ICL) has shown impressive results in few-shot learning tasks, yet its underlying mechanism is still not fully understood. Recent works suggest that ICL can be thought of as a gradient descent (GD) based optimization process. While promising, these results mainly focus on simplified settings of ICL and provide only a preliminary evaluation of the similarities between the two methods. In this work, we revisit the comparison between ICL and GD-based finetuning and study what properties of ICL an equivalent process must follow. We highlight a major difference in the flow of information between ICL and standard finetuning. Namely, ICL can only rely on information from lower layers at every point, while finetuning depends on loss gradients from deeper layers. We refer to this discrepancy as Layer Causality and show that a layer causal variant of the finetuning process aligns with ICL on par with vanilla finetuning and is even better in most cases across relevant metrics. To the best of our knowledge, this is the first work to discuss this discrepancy explicitly and suggest a solution that tackles this problem with minimal changes.
Authors: Aaditya K. Singh, Stephanie C.Y. Chan, Ted Moskovitz, Erin Grant, Andrew M. Saxe, Felix Hill
Transformer neural networks can exhibit a surprising capacity for in-context learning (ICL) despite not being explicitly trained for it. Prior work has provided a deeper understanding of how ICL emerges in transformers, e.g. through the lens of mechanistic interpretability, Bayesian inference, or by examining the distributional properties of training data. However, in each of these cases, ICL is treated largely as a persistent phenomenon; namely, once ICL emerges, it is assumed to persist asymptotically. Here, we show that the emergence of ICL during transformer training is, in fact, often transient. We train transformers on synthetic data designed so that both ICL and in-weights learning (IWL) strategies can lead to correct predictions. We find that ICL first emerges, then disappears and gives way to IWL, all while the training loss decreases, indicating an asymptotic preference for IWL. The transient nature of ICL is observed in transformers across a range of model sizes and datasets, raising the question of how much to "overtrain" transformers when seeking compact, cheaper-to-run models. We find that L2 regularization may offer a path to more persistent ICL that removes the need for early stopping based on ICL-style validation tasks. Finally, we present initial evidence that ICL transience may be caused by competition between ICL and IWL circuits.
Authors: Joe Carlsmith
This report examines whether advanced AIs that perform well in training will be doing so in order to gain power later -- a behavior I call "scheming" (also sometimes called "deceptive alignment"). I conclude that scheming is a disturbingly plausible outcome of using baseline machine learning methods to train goal-directed AIs sophisticated enough to scheme (my subjective probability on such an outcome, given these conditions, is roughly 25%). In particular: if performing well in training is a good strategy for gaining power (as I think it might well be), then a very wide variety of goals would motivate scheming -- and hence, good training performance. This makes it plausible that training might either land on such a goal naturally and then reinforce it, or actively push a model's motivations towards such a goal as an easy way of improving performance. What's more, because schemers pretend to be aligned on tests designed to reveal their motivations, it may be quite difficult to tell whether this has occurred. However, I also think there are reasons for comfort. In particular: scheming may not actually be such a good strategy for gaining power; various selection pressures in training might work against schemer-like goals (for example, relative to non-schemers, schemers need to engage in extra instrumental reasoning, which might harm their training performance); and we may be able to increase such pressures intentionally. The report discusses these and a wide variety of other considerations in detail, and it suggests an array of empirical research directions for probing the topic further.
Authors: SayedHassan Khatoonabadi, Diego Elias Costa, Rabe Abdalkareem, Emad Shihab
Pull-based development has enabled numerous volunteers to contribute to open-source projects with fewer barriers. Nevertheless, a considerable amount of pull requests (PRs) with valid contributions are abandoned by their contributors, wasting the effort and time put in by both the contributors and maintainers. To better understand the underlying dynamics of contributor-abandoned PRs, we conduct a mixed-methods study using both quantitative and qualitative methods. We curate a dataset consisting of 265,325 PRs including 4,450 abandoned ones from ten popular and mature GitHub projects and measure 16 features characterizing PRs, contributors, review processes, and projects. Using statistical and machine learning techniques, we find that complex PRs, novice contributors, and lengthy reviews have a higher probability of abandonment and the rate of PR abandonment fluctuates alongside the projects' maturity or workload. To identify why contributors abandon their PRs, we also manually examine a random sample of 354 abandoned PRs. We observe that the most frequent abandonment reasons are related to the obstacles faced by contributors, followed by the hurdles imposed by maintainers during the review process. Finally, we survey the top core maintainers of the studied projects to understand their perspectives on dealing with PR abandonment and on our findings.
Authors: Viet Pham Ngoc (Imperial College London), David Tuckey (Imperial College London), Herbert Wiklicky (Imperial College London)
In this paper, we investigate the performances of tunable quantum neural networks in the Quantum Probably Approximately Correct (QPAC) learning framework. Tunable neural networks are quantum circuits made of multi-controlled X gates. By tuning the set of controls these circuits are able to approximate any Boolean functions. This architecture is particularly suited to be used in the QPAC-learning framework as it can handle the superposition produced by the oracle. In order to tune the network so that it can approximate a target concept, we have devised and implemented an algorithm based on amplitude amplification. The numerical results show that this approach can efficiently learn concepts from a simple class.
Authors: SayedHassan Khatoonabadi, Ahmad Abdellatif, Diego Elias Costa, Emad Shihab
The success of a Pull Request (PR) depends on the responsiveness of the maintainers and the contributor during the review process. Being aware of the expected waiting times can lead to better interactions and managed expectations for both the maintainers and the contributor. In this paper, we propose a machine-learning approach to predict the first response latency of the maintainers following the submission of a PR, and the first response latency of the contributor after receiving the first response from the maintainers. We curate a dataset of 20 large and popular open-source projects on GitHub and extract 21 features to characterize projects, contributors, PRs, and review processes. Using these features, we then evaluate seven types of classifiers to identify the best-performing models. We also perform permutation feature importance and SHAP analyses to understand the importance and impact of different features on the predicted response latencies. Our best-performing models achieve an average improvement of 33% in AUC-ROC and 58% in AUC-PR for maintainers, as well as 42% in AUC-ROC and 95% in AUC-PR for contributors compared to a no-skilled classifier across the projects. Our findings indicate that PRs submitted earlier in the week, containing an average or slightly above-average number of commits, and with concise descriptions are more likely to receive faster first responses from the maintainers. Similarly, PRs with a lower first response latency from maintainers, that received the first response of maintainers earlier in the week, and containing an average or slightly above-average number of commits tend to receive faster first responses from the contributors. Additionally, contributors with a higher acceptance rate and a history of timely responses in the project are likely to both obtain and provide faster first responses.