# H-ensemble: An Information Theoretic Approach to Reliable Few-Shot Multi-Source-Free Transfer

arXiv: https://arxiv.org/abs/2312.12489 · HTML: https://mlsanity.com/paper/2312.12489/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 39 references that are in the map.
- First posted on arXiv 19 Dec 2023.

## Builds on (most cited first, 13 of 13)

- [Moment Matching for Multi-Source Domain Adaptation](https://mlsanity.com/paper/1812.01754/) (2018)
- [Deep Hashing Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1706.07522/) (2017)
- [A Comprehensive Survey on Transfer Learning](https://mlsanity.com/paper/1911.02685/) (2019)
- [CyCADA: Cycle-Consistent Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.03213/) (2017)
- [VisDA: The Visual Domain Adaptation Challenge](https://mlsanity.com/paper/1710.06924/) (2017)
- [An Information-Theoretic Approach to Transferability in Task Transfer Learning](https://mlsanity.com/paper/2212.10082/) (2022)
- [Source-Free Unsupervised Domain Adaptation: A Survey](https://mlsanity.com/paper/2301.00265/) (2022)
- [Unsupervised Multi-source Domain Adaptation Without Access to Source Data](https://mlsanity.com/paper/2104.01845/) (2021)
- [Aggregating From Multiple Target-Shifted Sources](https://mlsanity.com/paper/2105.04051/) (2021)
- [On Universal Features for High-Dimensional Learning and Inference](https://mlsanity.com/paper/1911.09105/) (2019)
- [An Information Theoretic Interpretation to Deep Neural Networks](https://mlsanity.com/paper/1905.06600/) (2019)
- [Algorithm-Dependent Bounds for Representation Learning of Multi-Source Domain Adaptation](https://mlsanity.com/paper/2304.02064/) (2023)
- [Adapted tree boosting for Transfer Learning](https://mlsanity.com/paper/2002.11982/) (2020)

## Built on by (most cited first, 6 of 6)

- [A High-Dimensional Statistical Method for Optimizing Transfer Quantities in Multi-Source Transfer Learning](https://mlsanity.com/paper/2502.04242/) (2025)
- [Exploiting Task Relationships in Continual Learning via Transferability-Aware Task Embeddings](https://mlsanity.com/paper/2502.11609/) (2025)
- [Unified Optimization of Source Weights and Transfer Quantities in Multi-Source Transfer Learning: An Asymptotic Framework](https://mlsanity.com/paper/2601.10779/) (2026)
- [Learning Optimal Prompt Ensemble for Multi-source Visual Prompt Transfer](https://mlsanity.com/paper/2504.12311/) (2025)
- [Model Recycling Framework for Multi-Source Data-Free Supervised Transfer Learning](https://mlsanity.com/paper/2508.02039/) (2025)
- [Beyond Non-IID: Learner--Client Distribution Mismatch in Federated Learning](https://mlsanity.com/paper/2608.27715/) (2026)

## Abstract (arXiv)

Multi-source transfer learning is an effective solution to data scarcity by utilizing multiple source tasks for the learning of the target task. However, access to source data and model details is limited in the era of commercial models, giving rise to the setting of multi-source-free (MSF) transfer learning that aims to leverage source domain knowledge without such access. As a newly defined problem paradigm, MSF transfer learning remains largely underexplored and not clearly formulated. In this work, we adopt an information theoretic perspective on it and propose a framework named H-ensemble, which dynamically learns the optimal linear combination, or ensemble, of source models for the target task, using a generalization of maximal correlation regression. The ensemble weights are optimized by maximizing an information theoretic metric for transferability. Compared to previous works, H-ensemble is characterized by: 1) its adaptability to a novel and realistic MSF setting for few-shot target tasks, 2) theoretical reliability, 3) a lightweight structure easy to interpret and adapt. Our method is empirically validated by ablation studies, along with extensive comparative analysis with other task ensemble and transfer learning methods. We show that the H-ensemble can successfully learn the optimal task ensemble, as well as outperform prior arts.