Machine learning algorithms typically assume that the training and test samples come from the same distributions, i.e., in-distribution. However, in open-world scenarios, streaming big data can be Out-Of-Distribution (OOD), rendering these algorithms ineffective. Prior solutions to the OOD challenge seek to identify invariant features across different training domains. The underlying assumption is that these invariant features should also work reasonably well in the unlabeled target domain. By contrast, this work is interested in the domain-specific features that include both invariant features and features unique to the target domain. We propose a simple yet effective approach that relies on correlations in general regardless of whether the features are invariant or not. Our approach uses the most confidently predicted samples identified by an OOD base model (teacher model) to train a new model (student model) that effectively adapts to the target domain. Empirical evaluations on benchmark datasets show that the performance is improved over the SOTA by ~10-20%
Detecting out-of-distribution (OOD) data has become a critical component in ensuring the safe deployment of machine learning models in the real world. Existing OOD detection approaches primarily rely on the output or feature space for deriving OOD scores, while largely overlooking information from the gradient space. In this paper, we present GradNorm, a simple and effective approach for detecting OOD inputs by utilizing information extracted from the gradient space. GradNorm directly employs the vector norm of gradients, backpropagated from the KL divergence between the softmax output and a u…
Manipal Institute of Technology, MAHE（马尼帕尔理工学院，马尼帕尔高等教育学院）
Most machine learning models operate under the assumption that the training, testing and deployment data is independent and identically distributed (i.i.d.). This assumption doesn't generally hold true in a natural setting. Usually, the deployment data is subject to various types of distributional shifts. The magnitude of a model's performance is proportional to this shift in the distribution of the dataset. Thus it becomes necessary to evaluate a model's uncertainty and robustness to distributional shifts to get a realistic estimate of its expected performance on real-world data. Present meth…
The Offline-Frontier Shift: Diagnosing Distributional Limits in Generative Multi-Objective Optimization
LIT AI Lab and Institute for Machine Learning JKU Linz, Austria（LIT人工智能实验室和机器学习研究所，约翰·肯普夫大学（JKU）林茨分校，奥地利）；School of Computing, Engineering and Technology RGU, Aberdeen, Scotland（计算、工程与技术学院 RGU，阿伯丁，苏格兰）；Linz Center of Mechatronics GmbH Linz, Austria（林茨机电研究中心 GmbH，林茨，奥地利）
Deep learning-based models are developed to automatically detect if a retina image is `referable' in diabetic retinopathy (DR) screening. However, their classification accuracy degrades as the input images distributionally shift from their training distribution. Further, even if the input is not a retina image, a standard DR classifier produces a high confident prediction that the image is `referable'. Our paper presents a Dirichlet Prior Network-based framework to address this issue. It utilizes an out-of-distribution (OOD) detector model and a DR classification model to improve generalizabil…
Machine learning algorithms with empirical risk minimization are vulnerable under distributional shifts due to the greedy adoption of all the correlations found in training data. Recently, there are robust learning methods aiming at this problem by minimizing the worst-case risk over an uncertainty set. However, they equally treat all covariates to form the decision sets regardless of the stability of their correlations with the target, resulting in the overwhelmingly large set and low confidence of the learner.In this paper, we propose Stable Adversarial Learning (SAL) algorithm that leverage…
Fed-ADE: Adaptive Learning Rate for Federated Post-adaptation under Distribution Shift
Department of Electrical and Computer Engineering, Sungkyunkwan University, Republic of Korea（电气与计算机工程系，成均馆大学，大韩民国）；Soongsil University, Seoul, Republic of Korea（顺世大学，首尔，大韩民国）
Machine learning algorithms with empirical risk minimization are vulnerable under distributional shifts due to the greedy adoption of all the correlations found in training data. There is an emerging literature on tackling this problem by minimizing the worst-case risk over an uncertainty set. However, existing methods mostly construct ambiguity sets by treating all variables equally regardless of the stability of their correlations with the target, resulting in the overwhelmingly-large uncertainty set and low confidence of the learner. In this paper, we propose a novel Stable Adversarial Lear…
As black-box models increasingly power high-stakes applications, a variety of data-driven explanation methods have been introduced. Meanwhile, machine learning models are constantly challenged by distributional shifts. A question naturally arises: Are data-driven explanations robust against out-of-distribution data? Our empirical results show that even though predict correctly, the model might still yield unreliable explanations under distributional shifts. How to develop robust explanations against out-of-distribution data? To address this problem, we propose an end-to-end model-agnostic lear…
Generative models for decision-making under distributional shift
Department of Mathematics, Duke University（杜克大学数学系）；H. Milton Stewart School of Industrial and Systems Engineering, Georgia Institute of Technology（佐治亚理工学院H. Milton Stewart工业与系统工程学院）
Georgia Institute of Technology（佐治亚理工学院）；Microsoft（微软）；Tsinghua University（清华大学）
We present a new zero-shot dense retrieval (ZeroDR) method, COCO-DR, to improve the generalization ability of dense retrieval by combating the distribution shifts between source training tasks and target scenarios. To mitigate the impact of document differences, COCO-DR continues pretraining the language model on the target corpora to adapt the model to target distributions via COtinuous COtrastive learning. To prepare for unseen target queries, COCO-DR leverages implicit Distributionally Robust Optimization (iDRO) to reweight samples from different source query clusters for improving model ro…
VinAI Research（VinAI研究院）；Monash University（莫纳什大学）；Johns Hopkins University（约翰斯·霍普金斯大学）；University of Texas, Austin（德克萨斯大学奥斯汀分校）
Despite superior performance in many situations, deep neural networks are often vulnerable to adversarial examples and distribution shifts, limiting model generalization ability in real-world applications. To alleviate these problems, recent approaches leverage distributional robustness optimization (DRO) to find the most challenging distribution, and then minimize loss function over this most challenging distribution. Regardless of achieving some improvements, these DRO approaches have some obvious limitations. First, they purely focus on local regularization to strengthen model robustness, m…
Cornell University（康奈尔大学）；Facebook AI Research（Facebook 人工智能研究院）
Machine learning models often encounter distribution shifts when deployed in the real world. In this paper, we focus on adaptation to label distribution shift in the online setting, where the test-time label distribution is continually changing and the model must dynamically adapt to it without observing the true label. Leveraging a novel analysis, we show that the lack of true label does not hinder estimation of the expected test loss, which enables the reduction of online label shift adaptation to conventional online learning. Informed by this observation, we propose adaptation algorithms in…
Traditional Bayesian approaches for model uncertainty quantification rely on notoriously difficult processes of marginalization over each network parameter to estimate its probability density function (PDF). Our hypothesis is that internal layer outputs of a trained neural network contain all of the information related to both its mapping function (quantified by its weights) as well as the input data distribution. We therefore propose a framework for predictive uncertainty quantification of a trained neural network that explicitly estimates the PDF of its raw prediction space (before activatio…
Loss Smoothing for Stable Adaptation Under Distribution Shift
Chandar Research Lab（Chandar 研究实验室）；Mila – Quebec AI Institute（Mila – 魁北克人工智能研究所）；Université de Montréal（蒙特利尔大学）；Polytechnique Montréal（蒙特利尔理工学院）；Canada CIFAR AI Chair（加拿大 CIFAR 人工智能主席）
Adaptive Sample-Level Framework Motivated by Distributionally Robust Optimization with Variance-Based Radius Assignment for Enhanced Neural Network Generalization Under Distribution Shift
Bangladesh University of Engineering and Technology (BUET)（孟加拉国工程技术大学）
University of Washington（华盛顿大学）；Allen Institute for AI（艾伦人工智能研究所）
We conduct a large empirical evaluation to investigate the landscape of distributional robustness in question answering. Our investigation spans over 350 models and 16 question answering datasets, including a diverse set of architectures, model sizes, and adaptation methods (e.g., fine-tuning, adapter tuning, in-context learning, etc.). We find that, in many cases, model variations do not affect robustness and in-distribution performance alone determines out-of-distribution performance. Moreover, our findings indicate that i) zero-shot and in-context learning methods are more robust to distrib…
Temporal distributional shifts, with underlying dynamics changing over time, frequently occur in real-world time series and pose a fundamental challenge for deep neural networks (DNNs). In this paper, we propose a novel deep sequence model based on the Koopman theory for time series forecasting: Koopman Neural Forecaster (KNF) which leverages DNNs to learn the linear Koopman space and the coefficients of chosen measurement functions. KNF imposes appropriate inductive biases for improved robustness against distributional shifts, employing both a global operator to learn shared characteristics a…
Mila（米拉研究所）；University of Montreal（蒙特利尔大学）；Vector（Vector研究所）；University of Toronto（多伦多大学）；McGill University（麦吉尔大学）；Facebook AI Research（脸书人工智能研究院）
Distributional shift is one of the major obstacles when transferring machine learning prediction systems from the lab to the real world. To tackle this problem, we assume that variation across training domains is representative of the variation we might encounter at test time, but also that shifts at test time may be more extreme in magnitude. In particular, we show that reducing differences in risk across training domains can reduce a model's sensitivity to a wide range of extreme distributional shifts, including the challenging setting where the input contains both causal and anti-causal ele…
The use of Reinforcement Learning (RL) agents in practical applications requires the consideration of suboptimal outcomes, depending on the familiarity of the agent with its environment. This is especially important in safety-critical environments, where errors can lead to high costs or damage. In distributional RL, the risk-sensitivity can be controlled via different distortion measures of the estimated return distribution. However, these distortion functions require an estimate of the risk level, which is difficult to obtain and depends on the current state. In this work, we demonstrate the …
Domain Adaptation (DA) has recently received significant attention due to its potential to adapt a learning model across source and target domains with mismatched distributions. Since DA methods rely exclusively on the given source and target domain samples, they generally yield models that are vulnerable to noise and unable to adapt to unseen samples from the target domain, which calls for DA methods that guarantee the robustness and generalization of the learned models. In this paper, we propose DRDA, a distributionally robust domain adaptation method. DRDA leverages a distributionally robus…
In this paper, we propose a novel domain adaptation method for the source-free setting. In this setting, we cannot access source data during adaptation, while unlabeled target data and a model pretrained with source data are given. Due to lack of source data, we cannot directly match the data distributions between domains unlike typical domain adaptation algorithms. To cope with this problem, we propose utilizing batch normalization statistics stored in the pretrained model to approximate the distribution of unobserved source data. Specifically, we fix the classifier part of the model during a…
Recent work introduced the epinet as a new approach to uncertainty modeling in deep learning. An epinet is a small neural network added to traditional neural networks, which, together, can produce predictive distributions. In particular, using an epinet can greatly improve the quality of joint predictions across multiple inputs, a measure of how well a neural network knows what it does not know. In this paper, we examine whether epinets can offer similar advantages under distributional shifts. We find that, across ImageNet-A/O/C, epinets generally improve robustness metrics. Moreover, these im…
UC, Berkeley（加州大学伯克利分校）；MILA, Université de Montréal（蒙特利尔大学MILA）；DiDi（滴滴）；UC, San Diego（加州大学圣地亚哥分校）；CIFAR（加拿大高等研究院）
Domain adaptation (DA) is a technique that transfers predictive models trained on a labeled source domain to an unlabeled target domain, with the core difficulty of resolving distributional shift between domains. Currently, most popular DA algorithms are based on distributional matching (DM). However in practice, realistic domain shifts (RDS) may violate their basic assumptions and as a result these methods will fail. In this paper, in order to devise robust DA algorithms, we first systematically analyze the limitations of DM based methods, and then build new benchmarks with more realistic dom…
Ecole Polytechnique Fédérale de Lausanne（洛桑联邦理工学院）；The Hong Kong Polytechnic University（香港理工大学）；Stanford University（斯坦福大学）；VinAI Research（VinAI研究院）
Least squares estimators, when trained on a few target domain samples, may predict poorly. Supervised domain adaptation aims to improve the predictive accuracy by exploiting additional labeled training samples from a source distribution that is close to the target distribution. Given available data, we investigate novel strategies to synthesize a family of least squares estimator experts that are robust with regard to moment conditions. When these moment conditions are specified using Kullback-Leibler or Wasserstein-type divergences, we can find the robust estimators efficiently using convex o…
Distributional Drift Adaptation with Temporal Conditional Variational Autoencoder for Multivariate Time Series Forecasting
School of Medical Technology, Beijing Institute of Technology（北京理工大学医学技术学院）；School of Computer Science and Technology, Beijing Institute of Technology（北京理工大学计算机科学与技术学院）；Department of Computer Science, Tongji University（同济大学计算机科学系）；University of Technology Sydney（悉尼科技大学）；DataX Research Centre, School of Computing, Macquarie University（麦考瑞大学计算学院DataX研究中心）
The main challenges of using electroencephalogram (EEG) signals to make eye-tracking (ET) predictions are the differences in distributional patterns between benchmark data and real-world data and the noise resulting from the unintended interference of brain signals from multiple sources. Increasing the robustness of machine learning models in predicting eye-tracking position from EEG data is therefore integral for both research and consumer use. In medical research, the usage of more complicated data collection methods to test for simpler tasks has been explored to address this very issue. In …
Generalized Conformal Predictive Systems Under Distributional Shifts
IDLab Seminar for Statistics（统计研究所研讨会）；Department of Electronics（电子系）；ETH Zurich（苏黎世联邦理工学院）；Information Systems Zurich, Switzerland（苏黎世信息系统，瑞士）；Ghent University（根特大学）
In distributed learning systems, robustness issues may arise from two sources. On one hand, due to distributional shifts between training data and test data, the trained model could exhibit poor out-of-sample performance. On the other hand, a portion of working nodes might be subject to byzantine attacks which could invalidate the learning result. Existing works mostly deal with these two issues separately. In this paper, we propose a new algorithm that equips distributed learning with robustness measures against both distributional shifts and byzantine attacks. Our algorithm is built on recen…
