用注意力机制自动识别并避开偏见样本，提升对比学习的公平性。
An Attention-based Framework for Fair Contrastive Learning
- 通过注意力机制动态建模偏见来源，不依赖预设假设。
- 在多个数据集上显著降低表示中的偏见，且下游任务准确率不变。
- 适合需要公平性保障的图像、文本等多模态学习场景。
对比学习在复杂环境中学习无偏表示方面表现优异，尤其面对高基数、高维敏感信息时。然而，现有方法依赖预设的偏见成因模型，限制了去偏表示的学习能力。本文提出一种基于注意力机制的公平对比学习新方法，通过自动识别并避开导致偏见的样本，聚焦于有助于学习语义丰富表示的样本，从而构建更公平、更具语义信息的嵌入空间。实验表明，该方法在多个基准上显著提升了去偏效果，且未牺牲下游任务的准确性。
原文摘要 · Abstract (English)
Contrastive learning has proven instrumental in learning unbiased representations of data, especially in complex environments characterized by high-cardinality and high-dimensional sensitive information. However, existing approaches within this setting require predefined modelling assumptions of bias-causing interactions that limit the model's ability to learn debiased representations. In this work, we propose a new method for fair contrastive learning that employs an attention mechanism to model bias-causing interactions, enabling the learning of a fairer and semantically richer embedding space. In particular, our attention mechanism avoids bias-causing samples that confound the model and focuses on bias-reducing samples that help learn semantically meaningful representations. We verify the advantages of our method against existing baselines in fair contrastive learning and show that our approach can significantly boost bias removal from learned representations without compromising downstream accuracy.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。