Repeated Environment Inference for Invariant Learning

• URL: http://arxiv.org/abs/2207.12876v1
• Date: Tue, 26 Jul 2022 13:07:22 GMT
• Title: Repeated Environment Inference for Invariant Learning
• Authors: Aayush Mishra and Anqi Liu
• Abstract summary: We focus on the invariant representation notion when the Bayes optimal conditional label distribution is the same across different environments. Previous work conducts Environment Inference (EI) by maximizing the penalty term from Invariant Risk Minimization (IRM) framework. We show that this method outperforms baselines on both synthetic and real-world datasets.
• Score: 8.372465442144046
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: We study the problem of invariant learning when the environment labels are unknown. We focus on the invariant representation notion when the Bayes optimal conditional label distribution is the same across different environments. Previous work conducts Environment Inference (EI) by maximizing the penalty term from Invariant Risk Minimization (IRM) framework. The EI step uses a reference model which focuses on spurious correlations to efficiently reach a good environment partition. However, it is not clear how to find such a reference model. In this work, we propose to repeat the EI process and retrain an ERM model on the \textit{majority} environment inferred by the previous EI step. Under mild assumptions, we find that this iterative process helps learn a representation capturing the spurious correlation better than the single step. This results in better Environment Inference and better Invariant Learning. We show that this method outperforms baselines on both synthetic and real-world datasets.

Related papers

• No Regrets: Investigating and Improving Regret Approximations for Curriculum Discovery [53.08822154199948]
  Unsupervised Environment Design (UED) methods have gained recent attention as their adaptive curricula promise to enable agents to be robust to in- and out-of-distribution tasks. This work investigates how existing UED methods select training environments, focusing on task prioritisation metrics. We develop a method that directly trains on scenarios with high learnability.
  arXiv  Detail & Related papers  (2024-08-27T14:31:54Z)
• Invariant Correlation of Representation with Label [30.82552387894663]
  We introduce ICorr (an abbreviation for textbfInvariant textbfCorrelation), a novel approach designed to surmount the challenge of domain generalization in noisy settings. We empirically demonstrate the effectiveness of ICorr by comparing it with other domain generalization methods on various noisy datasets.
  arXiv  Detail & Related papers  (2024-07-01T19:27:28Z)
• Graph Invariant Learning with Subgraph Co-mixup for Out-Of-Distribution Generalization [51.913685334368104]
  We propose a novel graph invariant learning method based on invariant and variant patterns co-mixup strategy. Our method significantly outperforms state-of-the-art under various distribution shifts.
  arXiv  Detail & Related papers  (2023-12-18T07:26:56Z)
• Winning Prize Comes from Losing Tickets: Improve Invariant Learning by Exploring Variant Parameters for Out-of-Distribution Generalization [76.27711056914168]
  Out-of-Distribution (OOD) Generalization aims to learn robust models that generalize well to various environments without fitting to distribution-specific features. Recent studies based on Lottery Ticket Hypothesis (LTH) address this problem by minimizing the learning target to find some of the parameters that are critical to the task. We propose Exploring Variant parameters for Invariant Learning (EVIL) which also leverages the distribution knowledge to find the parameters that are sensitive to distribution shift.
  arXiv  Detail & Related papers  (2023-10-25T06:10:57Z)
• Exploiting Counter-Examples for Active Learning with Partial labels [45.665996618836516]
  This paper studies a new problem, emphactive learning with partial labels (ALPL) In this setting, an oracle annotates the query samples with partial labels, relaxing the oracle from the demanding accurate labeling process. We propose a simple but effective WorseNet to directly learn from this pattern.
  arXiv  Detail & Related papers  (2023-07-14T15:41:53Z)
• Decorr: Environment Partitioning for Invariant Learning and OOD Generalization [10.799855921851332]
  Invariant learning methods are aimed at identifying a consistent predictor across multiple environments. When environments aren't inherent in the data, practitioners must define them manually. This environment partitioning affects invariant learning's efficacy but remains underdiscussed. In this paper, we suggest partitioning the dataset into several environments by isolating low-correlation data subsets.
  arXiv  Detail & Related papers  (2022-11-18T06:49:35Z)
• Env-Aware Anomaly Detection: Ignore Style Changes, Stay True to Content! [6.633524353120579]
  We introduce a formalization and benchmark for the unsupervised anomaly detection task in the distribution-shift scenario. We empirically validate that environment-aware methods perform better in such cases when compared with the basic Empirical Risk Minimization (ERM) We propose an extension for generating positive samples for contrastive methods that considers the environment labels when training, improving the baseline score by 8.7%.
  arXiv  Detail & Related papers  (2022-10-06T17:52:33Z)
• A Relational Intervention Approach for Unsupervised Dynamics Generalization in Model-Based Reinforcement Learning [113.75991721607174]
  We introduce an interventional prediction module to estimate the probability of two estimated $hatz_i, hatz_j$ belonging to the same environment. We empirically show that $hatZ$ estimated by our method enjoy less redundant information than previous methods.
  arXiv  Detail & Related papers  (2022-06-09T15:01:36Z)
• Predict then Interpolate: A Simple Algorithm to Learn Stable Classifiers [59.06169363181417]
  Predict then Interpolate (PI) is an algorithm for learning correlations that are stable across environments. We prove that by interpolating the distributions of the correct predictions and the wrong predictions, we can uncover an oracle distribution where the unstable correlation vanishes.
  arXiv  Detail & Related papers  (2021-05-26T15:37:48Z)
• Environment Inference for Invariant Learning [9.63004099102596]
  We propose EIIL, a framework for domain-invariant learning that incorporates Environment Inference. We show that EIIL outperforms invariant learning methods on the CMNIST benchmark without using environment labels. We also establish connections between EIIL and algorithmic fairness, which enables EIIL to improve accuracy and calibration in a fair prediction problem.
  arXiv  Detail & Related papers  (2020-10-14T17:11:46Z)
• Strictly Batch Imitation Learning by Energy-based Distribution Matching [104.33286163090179]
  Consider learning a policy purely on the basis of demonstrated behavior -- that is, with no access to reinforcement signals, no knowledge of transition dynamics, and no further interaction with the environment. One solution is simply to retrofit existing algorithms for apprenticeship learning to work in the offline setting. But such an approach leans heavily on off-policy evaluation or offline model estimation, and can be indirect and inefficient. We argue that a good solution should be able to explicitly parameterize a policy, implicitly learn from rollout dynamics, and operate in an entirely offline fashion.
  arXiv  Detail & Related papers  (2020-06-25T03:27:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.