Lune

ACL Findings2023

Modeling the Q-Diversity in a Min-max Play Game for Robust Optimization

Ting Wu, Rui Zheng, Tao Gui, Qi Zhang, Xuanjing Huang

Abstract

Models trained via empirical risk minimization (ERM) are revealed to easily rely on spurious correlations, resulting in poor model generalization. Group distributionally robust optimization (group DRO) can alleviate this problem by minimizing the worst-case loss over pre-defined groups. While promising, in practice factors like expensive annotations and privacy preclude the availability of group labels. More crucially, when taking a closer look at the failure modes of out-of-distribution generalization, the typical procedure of reweighting in group DRO loses efficiency. Hinged on the limitations, in this work, we reformulate the group DRO framework by proposing Q-Diversity. Characterized by an interactive training mode, Q-Diversity relaxes the group identification from annotation into direct parameterization. Furthermore, a novel mixing strategy across groups is presented to diversify the under-represented groups. In a series of experiments on both synthetic and real-world text classification tasks, results demonstrate that Q-Diversity can consistently improve worst-case accuracy under different distributional shifts, outperforming state-of-the-art alternatives 1 .

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Adversarial NLI: A New Benchmark for Natural Language Understanding cites Learning The Difference That Makes A Difference With Counterfactually-Augmented Data
  • Just Train Twice: Improving Group Robustness without Training Group Information cites WILDS: A Benchmark of in-the-Wild Distribution Shifts
  • WILDS: A Benchmark of in-the-Wild Distribution Shifts cites Just Train Twice: Improving Group Robustness without Training Group Information
  • WILDS: A Benchmark of in-the-Wild Distribution Shifts cites Learning The Difference That Makes A Difference With Counterfactually-Augmented Data
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on18

  1. WILDS: A Benchmark of in-the-Wild Distribution ShiftsPang Wei Koh, Shiori Sagawa, Henrik Marklund, Sang Michael Xie et al.ICML 2021 · 1,773 citations
  2. Distributionally Robust Neural NetworksShiori Sagawa, Pang Wei Koh, Tatsunori B. Hashimoto, Percy LiangICLR 2020 · 1,578 citations
  3. Just Train Twice: Improving Group Robustness without Training Group InformationEvan Zheran Liu, Behzad Haghgoo, Annie S. Chen, Aditi Raghunathan et al.ICML 2021 · 683 citations
  4. Learning The Difference That Makes A Difference With Counterfactually-Augmented DataDivyansh Kaushik, Eduard H. Hovy, Zachary Chase LiptonICLR 2020 · 625 citations
  5. Adversarial NLI: A New Benchmark for Natural Language UnderstandingYixin Nie, Adina Williams, Emily Dinan, Mohit Bansal et al.ACL 2020 · 602 citations

Related papers

  1. Focus on the Common Good: Group Distributional Robustness FollowsVihari Piratla, Praneeth Netrapalli, Sunita SarawagiICLR 2022 · 32 citations
  2. Distributionally Robust Optimization with Probabilistic GroupSoumya Suvra Ghosal, Yixuan LiAAAI 2023 · 14 citations
  3. AGRO: Adversarial discovery of error-prone Groups for Robust OptimizationBhargavi Paranjape, Pradeep Dasigi, Vivek Srikumar, Luke Zettlemoyer et al.ICLR 2023
  4. Examining and Combating Spurious Features under Distribution ShiftChunting Zhou, Xuezhe Ma, Paul Michel, Graham NeubigICML 2021 · 78 citations
  5. Mitigating Spurious Correlation via Distributionally Robust Learning with Hierarchical Ambiguity SetsSung Ho Jo, Seonghwi Kim, Minwoo ChaeICLR 2026 · 6 citations
Dusk over the sea between two cliffs drawn in fine vertical lines