SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2309.12559 · 2023

Invariant Learning via Probability of Sufficient and Necessary Causes

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 4 functions out of this paper's own repositories and ran 3 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
ymy4323460/casn canonical 3 of 4
FunctionStatusWhere it lives
Classifier Ran ymy4323460/casn/domainbed/networks.py
pointer only (licence: NONE) · get_code("ce7990d7ad5821ff")
get_test_records Ran ymy4323460/casn/domainbed/model_selection.py
pointer only (licence: NONE) · get_code("53fac8d8d949e72b")
remove_batch_norm_from_resnet Ran ymy4323460/casn/domainbed/networks.py
pointer only (licence: NONE) · get_code("196cab71d7129d62")
get_algorithm_class Not yet run ymy4323460/casn/domainbed/algorithms.py
pointer only (licence: NONE) · get_code("b0bc80b1655a6802")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

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 \textit{sufficiency} and \textit{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 details of the implementation can be found at the GitHub repository: https://github.com/ymy4323460/CaSN.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2309.12559")
get_code_for_paper("2309.12559")
have("2309.12559")

Connect an agent — have() is free.