# Learning by Association - A versatile semi-supervised training method for neural networks

arXiv: https://arxiv.org/abs/1706.00909 · HTML: https://mlsanity.com/paper/1706.00909/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Jun 2017.

## Built on by (most cited first, 19 of 19)

- [Collaborative Learning for Hand and Object Reconstruction with Attention-guided Graph Convolution](https://mlsanity.com/paper/2204.13062/) (2022)
- [Parameterized Temperature Scaling for Boosting the Expressive Power in Post-Hoc Uncertainty Calibration](https://mlsanity.com/paper/2102.12182/) (2021)
- [Mine Your Own vieW: Self-Supervised Learning Through Across-Sample Prediction](https://mlsanity.com/paper/2102.10106/) (2021)
- [Learning Pixel Trajectories with Multiscale Contrastive Random Walks](https://mlsanity.com/paper/2201.08379/) (2022)
- [Towards Label-efficient Automatic Diagnosis and Analysis: A Comprehensive Survey of Advanced Deep Learning-based Weakly-supervised, Semi-supervised and Self-supervised Techniques in Histopathological Image Analysis](https://mlsanity.com/paper/2208.08789/) (2022)
- [Data Harmonisation for Information Fusion in Digital Healthcare: A State-of-the-Art Systematic Review, Meta-Analysis and Future Research Directions](https://mlsanity.com/paper/2201.06505/) (2022)
- [TriCoLo: Trimodal Contrastive Loss for Text to Shape Retrieval](https://mlsanity.com/paper/2201.07366/) (2022)
- [Shepherding Slots to Objects: Towards Stable and Robust Object-Centric Learning](https://mlsanity.com/paper/2303.17842/) (2023)
- [Text-to-3D Shape Generation](https://mlsanity.com/paper/2403.13289/) (2024)
- [Self-Supervised Any-Point Tracking by Contrastive Random Walks](https://mlsanity.com/paper/2409.16288/) (2024)
- [Semantic Clustering based Deduction Learning for Image Recognition and Classification](https://mlsanity.com/paper/2112.13165/) (2021)
- [Adapting to the Long Tail: A Meta-Analysis of Transfer Learning Research for Language Understanding Tasks](https://mlsanity.com/paper/2111.01340/) (2021)
- [Revisiting consistency for semi-supervised semantic segmentation](https://mlsanity.com/paper/2106.07075/) (2021)
- [Imaginative Walks: Generative Random Walk Deviation Loss for Improved Unseen Learning Representation](https://mlsanity.com/paper/2104.09757/) (2021)
- [Dealing with Distribution Mismatch in Semi-supervised Deep Learning for Covid-19 Detection Using Chest X-ray Images: A Novel Approach Using Feature Densities](https://mlsanity.com/paper/2109.00889/) (2021)
- [Continual Zero-Shot Learning through Semantically Guided Generative Random Walks](https://mlsanity.com/paper/2308.12366/) (2023)
- [Lifting the Convex Conjugate in Lagrangian Relaxations: A Tractable Approach for Continuous Markov Random Fields](https://mlsanity.com/paper/2107.06028/) (2021)
- ['Labelling the Gaps': A Weakly Supervised Automatic Eye Gaze Estimation](https://mlsanity.com/paper/2208.01840/) (2022)
- [An information-Theoretic Approach to Semi-supervised Transfer Learning](https://mlsanity.com/paper/2306.06731/) (2023)

## Abstract (arXiv)

In many real-world scenarios, labeled data for a specific machine learning task is costly to obtain. Semi-supervised training methods make use of abundantly available unlabeled data and a smaller number of labeled examples. We propose a new framework for semi-supervised training of deep neural networks inspired by learning in humans. "Associations" are made from embeddings of labeled samples to those of unlabeled ones and back. The optimization schedule encourages correct association cycles that end up at the same class from which the association was started and penalizes wrong associations ending at a different class. The implementation is easy to use and can be added to any existing end-to-end training setup. We demonstrate the capabilities of learning by association on several data sets and show that it can improve performance on classification tasks tremendously by making use of additionally available unlabeled data. In particular, for cases with few labeled data, our training scheme outperforms the current state of the art on SVHN.