# Self-Supervised Generalisation with Meta Auxiliary Learning

arXiv: https://arxiv.org/abs/1901.08933 · HTML: https://mlsanity.com/paper/1901.08933/

## Key facts

- Cited by 88 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Jan 2019.

## Built on by (most cited first, 30 of 88)

- [Multi-Task Learning as a Bargaining Game](https://mlsanity.com/paper/2202.01017/) (2022)
- [Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Prediction](https://mlsanity.com/paper/2111.00064/) (2021)
- [Leveraging Auxiliary Tasks with Affinity Learning for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2107.11787/) (2021)
- [Auto-Lambda: Disentangling Dynamic Task Relationships](https://mlsanity.com/paper/2202.03091/) (2022)
- [Fast Multi-Resolution Transformer Fine-tuning for Extreme Multi-label Text Classification](https://mlsanity.com/paper/2110.00685/) (2021)
- [Learning Auxiliary Monocular Contexts Helps Monocular 3D Object Detection](https://mlsanity.com/paper/2112.04628/) (2021)
- [A Survey on Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2304.08130/) (2023)
- [MetaGCD: Learning to Continually Learn in Generalized Category Discovery](https://mlsanity.com/paper/2308.11063/) (2023)
- [MetaBalance: Improving Multi-Task Recommendations via Adapting Gradient Magnitudes of Auxiliary Tasks](https://mlsanity.com/paper/2203.06801/) (2022)
- [Sketch3T: Test-Time Training for Zero-Shot SBIR](https://mlsanity.com/paper/2203.14691/) (2022)
- [Adaptive Transfer Learning on Graph Neural Networks](https://mlsanity.com/paper/2107.08765/) (2021)
- [Prismer: A Vision-Language Model with Multi-Task Experts](https://mlsanity.com/paper/2303.02506/) (2023)
- [Meta-Learning to Improve Pre-Training](https://mlsanity.com/paper/2111.01754/) (2021)
- [Continuous MDP Homomorphisms and Homomorphic Policy Gradient](https://mlsanity.com/paper/2209.07364/) (2022)
- [Point-TTA: Test-Time Adaptation for Point Cloud Registration Using Multitask Meta-Auxiliary Learning](https://mlsanity.com/paper/2308.16481/) (2023)
- [Cross-Task Knowledge Distillation in Multi-Task Recommendation](https://mlsanity.com/paper/2202.09852/) (2022)
- [Taxonomy Completion via Triplet Matching Network](https://mlsanity.com/paper/2101.01896/) (2021)
- [XVO: Generalized Visual Odometry via Cross-Modal Self-Training](https://mlsanity.com/paper/2309.16772/) (2023)
- [MetAug: Contrastive Learning via Meta Feature Augmentation](https://mlsanity.com/paper/2203.05119/) (2022)
- [MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models](https://mlsanity.com/paper/2303.13009/) (2023)
- [Tree Structure-Aware Few-Shot Image Classification via Hierarchical Aggregation](https://mlsanity.com/paper/2207.06989/) (2022)
- [Improving Generalization in Meta-RL with Imaginary Tasks from Latent Dynamics Mixture](https://mlsanity.com/paper/2105.13524/) (2021)
- [AANG: Automating Auxiliary Learning](https://mlsanity.com/paper/2205.14082/) (2022)
- [Auxiliary Learning as an Asymmetric Bargaining Game](https://mlsanity.com/paper/2301.13501/) (2023)
- [Image Quality-aware Diagnosis via Meta-knowledge Co-embedding](https://mlsanity.com/paper/2303.15038/) (2023)
- [MANTRA: The Manifold Triangulations Assemblage](https://mlsanity.com/paper/2410.02392/) (2024)
- [Test-Time Adaptation for Point Cloud Upsampling Using Meta-Learning](https://mlsanity.com/paper/2308.16484/) (2023)
- [EvoGrad: Efficient Gradient-Based Meta-Learning and Hyperparameter Optimization](https://mlsanity.com/paper/2106.10575/) (2021)
- [Policy Gradient Methods in the Presence of Symmetries and State Abstractions](https://mlsanity.com/paper/2305.05666/) (2023)
- [Recent Advances in Embedding Methods for Multi-Object Tracking: A Survey](https://mlsanity.com/paper/2205.10766/) (2022)

## Abstract (arXiv)

Learning with auxiliary tasks can improve the ability of a primary task to generalise. However, this comes at the cost of manually labelling auxiliary data. We propose a new method which automatically learns appropriate labels for an auxiliary task, such that any supervised learning task can be improved without requiring access to any further data. The approach is to train two neural networks: a label-generation network to predict the auxiliary labels, and a multi-task network to train the primary task alongside the auxiliary task. The loss for the label-generation network incorporates the loss of the multi-task network, and so this interaction between the two networks can be seen as a form of meta learning with a double gradient. We show that our proposed method, Meta AuXiliary Learning (MAXL), outperforms single-task learning on 7 image datasets, without requiring any additional data. We also show that MAXL outperforms several other baselines for generating auxiliary labels, and is even competitive when compared with human-defined auxiliary labels. The self-supervised nature of our method leads to a promising new direction towards automated generalisation. Source code can be found at https://github.com/lorenmt/maxl.