arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.17144cs.LGstat.ML
收藏

当更多专家损害:多专家学习延迟中的欠拟合

When More Experts Hurt: Underfitting in Multi-Expert Learning to Defer

Nanyang Technological University(南洋理工大学);Southeast University(东南大学)

Shuqi Liu, Yuzhou Cao, Lei Feng, Bo An, Luke Ong

AI总结:

本文提出PiCCE方法,解决多专家学习延迟中的欠拟合问题,通过自适应识别可靠专家提升预测性能。

摘要:

学习延迟(L2D)使分类器能够避免预测并转交给专家,最近已被扩展到多专家设置。在本文中,我们证明多专家L2D本质上比单专家情况更具挑战性。在多个专家的情况下,分类器的欠拟合成为固有属性,这严重降低了预测性能,而单专家情况下仅在特定条件下出现。我们理论揭示,这源于一个内在的专家可识别性问题:从多样化的专家池中学习信任哪个专家,这在单专家情况下不存在,并使现有欠拟合缓解方法失效。为解决这个问题,我们提出了PiCCE(选择自信和正确的专家),一种基于替代的 方法,根据经验证据自适应地识别可靠的专家。PiCCE有效地将多专家L2D转换为单专家-like学习问题,从而解决多专家欠拟合问题。我们进一步证明了其统计一致性以及恢复类别概率和专家准确性的能力。在各种各样的设置中,包括现实世界专家场景中,进行了广泛的实验,验证了我们的理论结果,并展示了改进的性能。

英文摘要:

Learning to Defer (L2D) enables a classifier to abstain from predictions and defer to an expert, and has recently been extended to multi-expert settings. In this work, we show that multi-expert L2D is fundamentally more challenging than the single-expert case. With multiple experts, the classifier's underfitting becomes inherent, which seriously degrades prediction performance, whereas in the single-expert setting it arises only under specific conditions. We theoretically reveal that this stems from an intrinsic expert identifiability issue: learning which expert to trust from a diverse pool, a problem absent in the single-expert case and renders existing underfitting remedies failed. To tackle this issue, we propose PiCCE (Pick the Confident and Correct Expert), a surrogate-based method that adaptively identifies a reliable expert based on empirical evidence. PiCCE effectively reduces multi-expert L2D to a single-expert-like learning problem, thereby resolving multi expert underfitting. We further prove its statistical consistency and ability to recover class probabilities and expert accuracies. Extensive experiments across diverse settings, including real-world expert scenarios, validate our theoretical results and demonstrate improved performance.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑