Yimeng Chen, Ruibin Xiong, Zhiming Ma, Yanyan Lan
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
By inferring latent groups in the training data, recent works introduce invariant learning to the case where environment annotations are unavailable. Typically, learning group invariance under a majority/minority split is empirically shown to be effective in improving out-of-distribution generalization on many datasets. However, theoretical guarantee for these methods on learning invariant mechanisms is lacking. In this paper, we reveal the insufficiency of existing group invariant learning methods in preventing classifiers from depending on spurious correlations in the training set. Specifically, we propose two criteria on judging such sufficiency. Theoretically and empirically, we show that existing methods can violate both criteria and thus fail in generalizing to spurious correlation shifts. Motivated by this, we design a new group invariant learning method, which constructs groups with statistical independence tests, and reweights samples by group label proportion to meet the criteria. Experiments on both synthetic and real data demonstrate that the new method significantly outperforms existing group invariant learning methods in generalizing to spurious correlation shifts.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2206.14534")
get_code_for_paper("2206.14534")
have("2206.14534")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2206.14534.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2206.14534)
Connect an agent — have() is free.