# Enhancing Continuous Domain Adaptation with Multi-Path Transfer Curriculum

arXiv: https://arxiv.org/abs/2402.16681 · HTML: https://mlsanity.com/paper/2402.16681/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 19 references that are in the map.
- First posted on arXiv 26 Feb 2024.

## Builds on (most cited first, 10 of 10)

- [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (2013)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2002.08546/) (2020)
- [Optimal Transport for Domain Adaptation](https://mlsanity.com/paper/1507.00504/) (2015)
- [Understanding Self-Training for Gradual Domain Adaptation](https://mlsanity.com/paper/2002.11361/) (2020)
- [Correlation Alignment for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1612.01939/) (2016)
- [Forward-Backward Splitting with Bregman Distances](https://mlsanity.com/paper/1505.05198/) (2015)
- [Bregman Forward-Backward Operator Splitting](https://mlsanity.com/paper/1908.03878/) (2019)
- [Delving into the Continuous Domain Adaptation](https://mlsanity.com/paper/2208.13121/) (2022)
- [Forward-Backward Splitting for Optimal Transport based Problems](https://mlsanity.com/paper/1909.11448/) (2019)

## Built on by (most cited first, 3 of 3)

- [Understanding Knowledge Transferability for Transfer Learning: A Survey](https://mlsanity.com/paper/2507.03175/) (2025)
- [RAG or Learning? Understanding the Limits of LLM Adaptation under Continuous Knowledge Drift in the Real World](https://mlsanity.com/paper/2604.05096/) (2026)
- [CRoP: Context-wise Robust Static Human-Sensing Personalization](https://mlsanity.com/paper/2409.17994/) (2024)

## Abstract (arXiv)

Addressing the large distribution gap between training and testing data has long been a challenge in machine learning, giving rise to fields such as transfer learning and domain adaptation. Recently, Continuous Domain Adaptation (CDA) has emerged as an effective technique, closing this gap by utilizing a series of intermediate domains. This paper contributes a novel CDA method, W-MPOT, which rigorously addresses the domain ordering and error accumulation problems overlooked by previous studies. Specifically, we construct a transfer curriculum over the source and intermediate domains based on Wasserstein distance, motivated by theoretical analysis of CDA. Then we transfer the source model to the target domain through multiple valid paths in the curriculum using a modified version of continuous optimal transport. A bidirectional path consistency constraint is introduced to mitigate the impact of accumulated mapping errors during continuous transfer. We extensively evaluate W-MPOT on multiple datasets, achieving up to 54.1% accuracy improvement on multi-session Alzheimer MR image classification and 94.7% MSE reduction on battery capacity estimation.