# Online Meta-Learning for Multi-Source and Semi-Supervised Domain Adaptation

arXiv: https://arxiv.org/abs/2004.04398 · HTML: https://mlsanity.com/paper/2004.04398/

## Key facts

- Cited by 64 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Apr 2020.

## Built on by (most cited first, 30 of 64)

- [Cross-Domain Adaptive Clustering for Semi-Supervised Domain Adaptation](https://mlsanity.com/paper/2104.09415/) (2021)
- [MetaAlign: Coordinating Domain Alignment and Classification for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2103.13575/) (2021)
- [CLDA: Contrastive Learning for Semi-Supervised Domain Adaptation](https://mlsanity.com/paper/2107.00085/) (2021)
- [Multi-Objective Meta Learning](https://mlsanity.com/paper/2102.07121/) (2021)
- [BMD: A General Class-balanced Multicentric Dynamic Prototype Strategy for Source-free Domain Adaptation](https://mlsanity.com/paper/2204.02811/) (2022)
- [Test-Time Training on Video Streams](https://mlsanity.com/paper/2307.05014/) (2023)
- [Subspace Identification for Multi-Source Domain Adaptation](https://mlsanity.com/paper/2310.04723/) (2023)
- [GIPSO: Geometrically Informed Propagation for Online Adaptation in 3D LiDAR Segmentation](https://mlsanity.com/paper/2207.09763/) (2022)
- [ToAlign: Task-oriented Alignment for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2106.10812/) (2021)
- [ECACL: A Holistic Framework for Semi-Supervised Domain Adaptation](https://mlsanity.com/paper/2104.09136/) (2021)
- [Dynamic Transfer for Multi-Source Domain Adaptation](https://mlsanity.com/paper/2103.10583/) (2021)
- [Meta-UDA: Unsupervised Domain Adaptive Thermal Object Detection using Meta-Learning](https://mlsanity.com/paper/2110.03143/) (2021)
- [Semi-supervised Domain Adaptation via Sample-to-Sample Self-Distillation](https://mlsanity.com/paper/2111.14353/) (2021)
- [Multi-Source Domain Adaptation for Object Detection](https://mlsanity.com/paper/2106.15793/) (2021)
- [Multi-level Consistency Learning for Semi-supervised Domain Adaptation](https://mlsanity.com/paper/2205.04066/) (2022)
- [Surprisingly Simple Semi-Supervised Domain Adaptation with Pretraining and Consistency](https://mlsanity.com/paper/2101.12727/) (2021)
- [S3VAADA: Submodular Subset Selection for Virtual Adversarial Active Domain Adaptation](https://mlsanity.com/paper/2109.08901/) (2021)
- [Contrastive Vicinal Space for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2111.13353/) (2021)
- [When Meta-Learning Meets Online and Continual Learning: A Survey](https://mlsanity.com/paper/2311.05241/) (2023)
- [Graph Domain Adaptation: Challenges, Progress and Prospects](https://mlsanity.com/paper/2402.00904/) (2024)
- [Inter-Domain Mixup for Semi-Supervised Domain Adaptation](https://mlsanity.com/paper/2401.11453/) (2024)
- [Trinity: A No-Code AI platform for complex spatial datasets](https://mlsanity.com/paper/2106.11756/) (2021)
- [Adaptive Betweenness Clustering for Semi-Supervised Domain Adaptation](https://mlsanity.com/paper/2401.11448/) (2024)
- [More is Better: Deep Domain Adaptation with Multiple Sources](https://mlsanity.com/paper/2405.00749/) (2024)
- [Dual-Teacher++: Exploiting Intra-domain and Inter-domain Knowledge with Reliable Transfer for Cardiac Segmentation](https://mlsanity.com/paper/2101.02375/) (2021)
- [Gradual Domain Adaptation via Self-Training of Auxiliary Models](https://mlsanity.com/paper/2106.09890/) (2021)
- [Graphical Modeling for Multi-Source Domain Adaptation](https://mlsanity.com/paper/2104.13057/) (2021)
- [Meta Self-Learning for Multi-Source Domain Adaptation: A Benchmark](https://mlsanity.com/paper/2108.10840/) (2021)
- [Probabilistic Contrastive Learning for Domain Adaptation](https://mlsanity.com/paper/2111.06021/) (2021)
- [Unsupervised Domain Adaptation for RF-based Gesture Recognition](https://mlsanity.com/paper/2111.10602/) (2021)

## Abstract (arXiv)

Domain adaptation (DA) is the topical problem of adapting models from labelled source datasets so that they perform well on target datasets where only unlabelled or partially labelled data is available. Many methods have been proposed to address this problem through different ways to minimise the domain shift between source and target datasets. In this paper we take an orthogonal perspective and propose a framework to further enhance performance by meta-learning the initial conditions of existing DA algorithms. This is challenging compared to the more widely considered setting of few-shot meta-learning, due to the length of the computation graph involved. Therefore we propose an online shortest-path meta-learning framework that is both computationally tractable and practically effective for improving DA performance. We present variants for both multi-source unsupervised domain adaptation (MSDA), and semi-supervised domain adaptation (SSDA). Importantly, our approach is agnostic to the base adaptation algorithm, and can be applied to improve many techniques. Experimentally, we demonstrate improvements on classic (DANN) and recent (MCD and MME) techniques for MSDA and SSDA, and ultimately achieve state of the art results on several DA benchmarks including the largest scale DomainNet.