Yue Yu, Zhiwei Zeng, Chunyan Miao, Xu Guo, Yongjie Wang, Xiaoqi Qiu, Yuhong Feng
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.
Counterfactually Augmented Data (CAD) involves creating new data samples by applying minimal yet sufficient modifications to flip the label of existing data samples to other classes. Training with CAD enhances model robustness against spurious features that happen to correlate with labels by spreading the casual relationships across different classes. Yet, recent research reveals that training with CAD may lead models to overly focus on modified features while ignoring other important contextual information, inadvertently introducing biases that may impair performance on out-ofdistribution (OOD) datasets. To mitigate this issue, we employ contrastive learning to promote global feature alignment in addition to learning counterfactual clues. We theoretically prove that contrastive loss can encourage models to leverage a broader range of features beyond those modified ones. Comprehensive experiments on two human-edited CAD datasets demonstrate that our proposed method outperforms the state-of-the-art on OOD datasets.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2406.06633")
get_code_for_paper("2406.06633")
have("2406.06633")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2406.06633.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2406.06633)
Connect an agent — have() is free.