# Curiosity Meets Cooperation: A Game-Theoretic Approach to Long-Tail Multi-Label Learning

arXiv: https://arxiv.org/abs/2510.17520 · HTML: https://mlsanity.com/paper/2510.17520/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 70 references that are in the map.
- First posted on arXiv 20 Oct 2025.

## Builds on (most cited first, 30 of 39)

- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [Curiosity-driven Exploration by Self-supervised Prediction](https://mlsanity.com/paper/1705.05363/) (2017)
- [Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss](https://mlsanity.com/paper/1906.07413/) (2019)
- [Decoupling Representation and Classifier for Long-Tailed Recognition](https://mlsanity.com/paper/1910.09217/) (2019)
- [Counterfactual Multi-Agent Policy Gradients](https://mlsanity.com/paper/1705.08926/) (2017)
- [Long-tail learning via logit adjustment](https://mlsanity.com/paper/2007.07314/) (2020)
- [Asymmetric Loss For Multi-Label Classification](https://mlsanity.com/paper/2009.14119/) (2020)
- [Multi-Label Image Recognition with Graph Convolutional Networks](https://mlsanity.com/paper/1904.03582/) (2019)
- [Deep Learning without Poor Local Minima](https://mlsanity.com/paper/1605.07110/) (2016)
- [Parametric Contrastive Learning](https://mlsanity.com/paper/2107.12028/) (2021)
- [CNN-RNN: A Unified Framework for Multi-label Image Classification](https://mlsanity.com/paper/1604.04573/) (2016)
- [Seesaw Loss for Long-Tailed Instance Segmentation](https://mlsanity.com/paper/2008.10032/) (2020)
- [Query2Label: A Simple Transformer Way to Multi-Label Classification](https://mlsanity.com/paper/2107.10834/) (2021)
- [General Multi-label Image Classification with Transformers](https://mlsanity.com/paper/2011.14027/) (2020)
- [Distribution-Balanced Loss for Multi-Label Classification in Long-Tailed Datasets](https://mlsanity.com/paper/2007.09654/) (2020)
- [The Mechanics of n-Player Differentiable Games](https://mlsanity.com/paper/1802.05642/) (2018)
- [The Emerging Trends of Multi-Label Learning](https://mlsanity.com/paper/2011.11197/) (2020)
- [Equalization Loss v2: A New Gradient Balance Approach for Long-tailed Object Detection](https://mlsanity.com/paper/2012.08548/) (2020)
- [NDC-Scene: Boost Monocular 3D Semantic Scene Completion in Normalized Device Coordinates Space](https://mlsanity.com/paper/2309.14616/) (2023)
- [ML-Decoder: Scalable and Versatile Classification Head](https://mlsanity.com/paper/2111.12933/) (2021)
- [DiSMEC - Distributed Sparse Machines for Extreme Multi-label Classification](https://mlsanity.com/paper/1609.02521/) (2016)
- [GradientDICE: Rethinking Generalized Offline Estimation of Stationary Values](https://mlsanity.com/paper/2001.11113/) (2020)
- [Fast Multi-Resolution Transformer Fine-tuning for Extreme Multi-label Text Classification](https://mlsanity.com/paper/2110.00685/) (2021)
- [Bonsai -- Diverse and Shallow Trees for Extreme Multi-label Classification](https://mlsanity.com/paper/1904.08249/) (2019)
- [LightXML: Transformer with Dynamic Negative Sampling for High-Performance Extreme Multi-label Text Classification](https://mlsanity.com/paper/2101.03305/) (2021)
- [Transformer-based Dual Relation Graph for Multi-label Image Recognition](https://mlsanity.com/paper/2110.04722/) (2021)
- [Large-scale Multi-label Text Classification - Revisiting Neural Networks](https://mlsanity.com/paper/1312.5419/) (2013)
- [Balancing Methods for Multi-label Text Classification with Long-Tailed Class Distribution](https://mlsanity.com/paper/2109.04712/) (2021)
- [Swift Sampler: Efficient Learning of Sampler by 10 Parameters](https://mlsanity.com/paper/2410.05578/) (2024)

## Built on by (most cited first, 4 of 4)

- [Self-Paced Learning for Images of Antinuclear Antibodies](https://mlsanity.com/paper/2511.21519/) (2025)
- [Synergy over Discrepancy: A Partition-Based Approach to Multi-Domain LLM Fine-Tuning](https://mlsanity.com/paper/2511.07198/) (2025)
- [Dynamic Graph Neural Networks for Physiological Based Pharmacokinetic Modeling: A Novel Data Driven Approach to Drug Concentration Prediction](https://mlsanity.com/paper/2510.22096/) (2025)
- [Aligning by Misaligning: Boundary-aware Curriculum Learning for Multimodal Alignment](https://mlsanity.com/paper/2511.08399/) (2025)

## Abstract (arXiv)

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.