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

arXiv: https://arxiv.org/abs/2509.21526 · HTML: https://mlsanity.com/paper/2509.21526/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 48 references that are in the map.
- First posted on arXiv 25 Sep 2025.

## Builds on (most cited first, 18 of 18)

- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [Big Self-Supervised Models are Strong Semi-Supervised Learners](https://mlsanity.com/paper/2006.10029/) (2020)
- [Unsupervised Data Augmentation for Consistency Training](https://mlsanity.com/paper/1904.12848/) (2019)
- [Deep Clustering for Unsupervised Learning of Visual Features](https://mlsanity.com/paper/1807.05520/) (2018)
- [FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling](https://mlsanity.com/paper/2110.08263/) (2021)
- [Self-labelling via simultaneous clustering and representation learning](https://mlsanity.com/paper/1911.05371/) (2019)
- [Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning](https://mlsanity.com/paper/1908.02983/) (2019)
- [FreeMatch: Self-adaptive Thresholding for Semi-supervised Learning](https://mlsanity.com/paper/2205.07246/) (2022)
- [Learning Customized Visual Models with Retrieval-Augmented Knowledge](https://mlsanity.com/paper/2301.07094/) (2023)
- [Semi-supervised Vision Transformers at Scale](https://mlsanity.com/paper/2208.05688/) (2022)
- [Smooth Neighbors on Teacher Graphs for Semi-supervised Learning](https://mlsanity.com/paper/1711.00258/) (2017)
- [Semi-Supervised Vision Transformers](https://mlsanity.com/paper/2111.11067/) (2021)
- [Approximating mutual information of high-dimensional variables using learned representations](https://mlsanity.com/paper/2409.02732/) (2024)
- [Semi-supervised learning made simple with self-supervised clustering](https://mlsanity.com/paper/2306.07483/) (2023)
- [Data driven semi-supervised learning](https://mlsanity.com/paper/2103.10547/) (2021)
- [The information-theoretic value of unlabeled data in semi-supervised learning](https://mlsanity.com/paper/1901.05515/) (2019)
- [Meta Co-Training: Two Views are Better than One](https://mlsanity.com/paper/2311.18083/) (2023)

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

- [Triple Expert Learning from Noisy Labels for Semi-Supervised Vision Foundation Model Adaptation](https://mlsanity.com/paper/2608.09052/) (2026)
- [Geometric Regularization for Long-Tailed Semi-Supervised Learning via Gaussian Feature Bridges](https://mlsanity.com/paper/2608.20710/) (2026)
- [Generalized Radius and Integrated Codebook Transforms for Differentiable Vector Quantization](https://mlsanity.com/paper/2602.01140/) (2026)
- [ReCalMatch:Reliability-Calibrated Semantic Guidance for Semi-Supervised Fine-Grained Recognition](https://mlsanity.com/paper/2609.29678/) (2026)

## Abstract (arXiv)

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.Code:https://github.com/HoHongYeung/NeurIPS25-TRiCo.