paper-with-me

홈 › Papers

Can Subnetwork Structure be the Key to Out-of-Distribution Generalization?

2021-06-05 · Dinghuai Zhang, Kartik Ahuja, Yilun Xu, Yisen Wang, Aaron Courville

Can models with particular structure avoid being biased towards spurious correlation in out-of-distribution (OOD) generalization? Peters et al. (2016) provides a positive answer for linear cases. In this paper, we use a functional modular probing method to analyze deep model structures under OOD setting. We demonstrate that even in biased models (which focus on spurious correlation) there still exist unbiased functional subnetworks. Furthermore, we articulate and demonstrate the functional lottery ticket hypothesis: full network contains a subnetwork that can achieve better OOD performance. We then propose Modular Risk Minimization to solve the subnetwork selection problem. Our algorithm learns the subnetwork structure from a given dataset, and can be combined with any other OOD regularization methods. Experiments on various OOD generalization tasks corroborate the effectiveness of our method.

📄 PDF Abstract BibTeX arXiv:2106.02890

Code (0)

등록된 구현이 없습니다.

Tasks

Out-of-Distribution Generalization

Similar Papers 제목 키워드 기반

A Combinatorial Theory of Dropout: Subnetworks, Graph Geometry, and Generalization

2025-04-20 · Sahil Rajesh Dhayalkar

We propose a combinatorial and graph-theoretic theory of dropout by modeling training as a random walk over a high-dimensional graph of binary subnetworks. Each node represents a masked version of the network, and dropou…

Exploring Optimal Substructure for Out-of-distribution Generalization via Feature-targeted Model Pruning

2022-12-19 · Yingchun Wang, Jingcai Guo, Song Guo, Weizhan Zhang 외

Recent studies show that even highly biased dense networks contain an unbiased substructure that can achieve better out-of-distribution (OOD) generalization than the original model. Existing works usually search the inva…

Out-of-Distribution Generalization

The Heuristic Core: Understanding Subnetwork Generalization in Pretrained Language Models

2024-03-06 · Adithya Bhaskar, Dan Friedman, Danqi Chen

Prior work has found that pretrained language models (LMs) fine-tuned with different random seeds can achieve similar in-domain performance but generalize differently on tests of syntactic generalization. In this work, w…

Winning Prize Comes from Losing Tickets: Improve Invariant Learning by Exploring Variant Parameters for Out-of-Distribution Generalization

2023-10-25 · Zhuo Huang, Muyang Li, Li Shen, Jun Yu 외

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)…

Out-of-Distribution Generalization

Network Pruning Spaces

2023-04-19 · Xuanyu He, Yu-I Yang, Ran Song, Jiachen Pu 외

Network pruning techniques, including weight pruning and filter pruning, reveal that most state-of-the-art neural networks can be accelerated without a significant performance drop. This work focuses on filter pruning wh…

Network Pruning