Yang, M; Fang, Z; Zhang, Y; Du, Y; Liu, F; Ton, JF; Wang, J; Yang, M; Fang, Z; Zhang, Y; Du, Y; Liu, F; Ton, JF; Wang, J; Wang, J; - view fewer (2023) Invariant Learning via Probability of Sufficient and Necessary Causes. In: Advances in Neural Information Processing Systems 36 (NeurIPS 2023). NeurIPS

Preview

Text NeurIPS-2023-invariant-learning-via-probability-of-sufficient-and-necessary-causes-Paper-Conference.pdf - Published Version Download (789kB) | Preview

Abstract

Out-of-distribution (OOD) generalization is indispensable for learning models in the wild, where testing distribution typically unknown and different from the training. Recent methods derived from causality have shown great potential in achieving OOD generalization. However, existing methods mainly focus on the invariance property of causes, while largely overlooking the property of sufficiency and necessity conditions. Namely, a necessary but insufficient cause (feature) is invariant to distribution shift, yet it may not have required accuracy. By contrast, a sufficient yet unnecessary cause (feature) tends to fit specific data well but may have a risk of adapting to a new domain. To capture the information of sufficient and necessary causes, we employ a classical concept, the probability of sufficiency and necessary causes (PNS), which indicates the probability of whether one is the necessary and sufficient cause. To associate PNS with OOD generalization, we propose PNS risk and formulate an algorithm to learn representation with a high PNS value. We theoretically analyze and prove the generalizability of the PNS risk. Experiments on both synthetic and real-world benchmarks demonstrate the effectiveness of the proposed method. The detailed implementation can be found at the GitHub repository: https://github.com/ymy4323460/CaSN.

Download activity - last month

Export as XMLCSVJSON

Download activity - last 12 months

Export as XMLCSVJSON

Downloads by country - last 12 months

Export as CSVXMLJSON

Archive Staff Only

View Item