# Autonomous Source Knowledge Selection in Multi-Domain Adaptation

arXiv: https://arxiv.org/abs/2512.14710 · HTML: https://mlsanity.com/paper/2512.14710/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 49 references that are in the map.
- First posted on arXiv 8 Dec 2025.

## Builds on (most cited first, 25 of 25)

- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2109.06165/) (2021)
- [FixBi: Bridging Domain Spaces for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2011.09230/) (2020)
- [Cross-domain Contrastive Learning for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2106.05528/) (2021)
- [Multi-source Distilling Domain Adaptation](https://mlsanity.com/paper/1911.11554/) (2019)
- [SAMGPT: Text-free Graph Foundation Model for Multi-domain Pre-training and Cross-domain Adaptation](https://mlsanity.com/paper/2502.05424/) (2025)
- [Safe Self-Refinement for Transformer-based Domain Adaptation](https://mlsanity.com/paper/2204.07683/) (2022)
- [Source-Free Domain Adaptation with Frozen Multimodal Foundation Model](https://mlsanity.com/paper/2311.16510/) (2023)
- [Prompt-based Distribution Alignment for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2312.09553/) (2023)
- [Text-image Alignment for Diffusion-based Perception](https://mlsanity.com/paper/2310.00031/) (2023)
- [Domain-Agnostic Mutual Prompting for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2403.02899/) (2024)
- [Multi-Prompt Alignment for Multi-Source Unsupervised Domain Adaptation](https://mlsanity.com/paper/2209.15210/) (2022)
- [LEAD: Learning Decomposition for Source-free Universal Domain Adaptation](https://mlsanity.com/paper/2403.03421/) (2024)
- [CALDA: Improving Multi-Source Time Series Domain Adaptation with Contrastive Adversarial Learning](https://mlsanity.com/paper/2109.14778/) (2021)
- [Proxy Denoising for Source-Free Domain Adaptation](https://mlsanity.com/paper/2406.01658/) (2024)
- [Adapting Multi-modal Large Language Model to Concept Drift From Pre-training Onwards](https://mlsanity.com/paper/2405.13459/) (2024)
- [Gradual Domain Adaptation: Theory and Algorithms](https://mlsanity.com/paper/2310.13852/) (2023)
- [Domain-Specificity Inducing Transformers for Source-Free Domain Adaptation](https://mlsanity.com/paper/2308.14023/) (2023)
- [Rethinking the Role of Pre-Trained Networks in Source-Free Domain Adaptation](https://mlsanity.com/paper/2212.07585/) (2022)
- [Multi-Source Domain Adaptation for Object Detection with Prototype-based Mean-teacher](https://mlsanity.com/paper/2309.14950/) (2023)
- [Gradual Source Domain Expansion for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2311.09599/) (2023)
- [Agile Multi-Source-Free Domain Adaptation](https://mlsanity.com/paper/2403.05062/) (2024)
- [UFDA: Universal Federated Domain Adaptation with Practical Assumptions](https://mlsanity.com/paper/2311.15570/) (2023)
- [Unified Source-Free Domain Adaptation](https://mlsanity.com/paper/2403.07601/) (2024)
- [Memory-Efficient Pseudo-Labeling for Online Source-Free Universal Domain Adaptation using a Gaussian Mixture Model](https://mlsanity.com/paper/2407.14208/) (2024)

## Abstract (arXiv)

Unsupervised multi-domain adaptation plays a key role in transfer learning by leveraging acquired rich source information from multiple source domains to solve target task from an unlabeled target domain. However, multiple source domains often contain much redundant or unrelated information which can harm transfer performance, especially when in massive-source domain settings. It is urgent to develop effective strategies for identifying and selecting the most transferable knowledge from massive source domains to address the target task. In this paper, we propose a multi-domain adaptation method named underlinetextitAutonomous Source Knowledge underlinetextitSelection (AutoS) to autonomosly select source training samples and models, enabling the prediction of target task using more relevant and transferable source information. The proposed method employs a density-driven selection strategy to choose source samples during training and to determine which source models should contribute to target prediction. Simulteneously, a pseudo-label enhancement module built on a pre-trained multimodal modal is employed to mitigate target label noise and improve self-supervision. Experiments on real-world datasets indicate the superiority of the proposed method.