TRiCo: Triadic Game-Theoretic Co-Training for Robust Semi-Supervised Learning

Hongyang He, Xinyuan Song, Yangfan He, Zeyu Zhang, Yanshu Li, Haochen You, Lifan Sun, Wenqiao Zhang

University of Warwick· Emory University· University of Minnesota Twin Cities· Australian National University· Brown University· Columbia University· University of California San Diego· Zhejiang University

Semi-supervised learning

⋅ NeurIPS ⋅ Project Page ⋅Poster ⋅OpenReview

Abstract

We introduce TRiCo, a novel triadic game-theoretic co-training framework that rethinks the structure of semi-supervised learning by incorporating a teacher, two students, and an adversarial generator into a unified training paradigm.

Unlike existing co-training or teacher-student approaches, TRiCo formulates SSL as a structured interaction among three roles:

two student classifiers trained on frozen, complementary representations,
a meta-learned teacher that adaptively regulates pseudo-label selection and loss balancing via validation-based feedback, and
a non-parametric generator that perturbs embeddings to uncover decision boundary weaknesses.

Pseudo-labels are selected based on mutual information rather than confidence, providing a more robust measure of epistemic uncertainty. This triadic interaction is formalized as a Stackelberg game, where the teacher leads strategy optimization and students follow under adversarial perturbations.

By addressing key limitations in existing SSL frameworks—such as static view interactions, unreliable pseudo-labels, and lack of hard sample modeling—TRiCo provides a principled and generalizable solution.

Extensive experiments on CIFAR-10, SVHN, STL-10, and ImageNet demonstrate that TRiCo consistently achieves state-of-the-art performance in low-label regimes, while remaining architecture-agnostic and compatible with frozen vision backbones.