TRiCo: Triadic Game-Theoretic Co-Training for Robust Semi-Supervised Learning
This provides a principled solution for robust semi-supervised learning, addressing key limitations in existing frameworks for computer vision tasks.
The paper tackles the problem of unreliable pseudo-labels and static view interactions in semi-supervised learning by introducing TRiCo, a triadic game-theoretic co-training framework with a teacher, two students, and an adversarial generator; it achieves state-of-the-art performance on datasets like CIFAR-10 and ImageNet in low-label regimes.
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: (i) two student classifiers trained on frozen, complementary representations, (ii) a meta-learned teacher that adaptively regulates pseudo-label selection and loss balancing via validation-based feedback, and (iii) 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.