用博弈论让模型主动关注罕见标签，提升长尾多标签预测性能。
Curiosity Meets Cooperation: A Game-Theoretic Approach to Long-Tail Multi-Label Learning
- 将标签学习建模为合作博弈，玩家共享全局奖励并获稀有标签激励。
- 在三个超大规模数据集上实现最高+4.3% Rare-F1和+1.6% P@3提升。
- 无需人工调权，自动发现标签分工，适合真实场景中稀有标签识别。
长尾分布是多标签学习中的普遍问题：少数头部标签主导梯度信号，而实际中重要的大量罕见标签被忽略。本文提出一种基于合作势博弈的框架（CD-GTMLL），将标签空间分配给多个协作玩家，它们共享全局准确率收益，并获得随标签稀有度与玩家间分歧上升的好奇心奖励。该奖励机制在不依赖人工权重的情况下，为低频标签注入有效梯度。理论证明，梯度最优响应更新会沿可微势函数上升，收敛至紧致逼近预期稀有标签F1下界的尾部感知平衡点。在传统基准及三个极端规模数据集上的实验表明，该方法持续达到领先性能，最大提升达+4.3% Rare-F1和+1.6% P@3；消融实验揭示了自发的标签分工与对罕见类别的更快共识。因此，该方法为多标签预测中的长尾鲁棒性提供了一个原则性且可扩展的解决方案。
原文摘要 · Abstract (English)
Long-tail imbalance is endemic to multi-label learning: a few head labels dominate the gradient signal, while the many rare labels that matter in practice are silently ignored. We tackle this problem by casting the task as a cooperative potential game. In our Curiosity-Driven Game-Theoretic Multi-Label Learning (CD-GTMLL) framework, the label space is split among several cooperating players that share a global accuracy payoff yet earn additional curiosity rewards that rise with label rarity and inter-player disagreement. These curiosity bonuses inject gradient on under-represented tags without hand-tuned class weights. We prove that gradient best-response updates ascend a differentiable potential and converge to tail-aware stationary points that tighten a lower bound on the expected Rare-F1. Extensive experiments on conventional benchmarks and three extreme-scale datasets show consistent state-of-the-art gains, delivering up to +4.3% Rare-F1 and +1.6% P@3 over the strongest baselines, while ablations reveal emergent division of labour and faster consensus on rare classes. CD-GTMLL thus offers a principled, scalable route to long-tail robustness in multi-label prediction.
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。