Rethinking the Flow-Based Gradual Domain Adaption: A Semi-Dual Optimal Transport Perspective

TL;DR

This paper introduces a novel semi-dual optimal transport framework for gradual domain adaptation that improves stability and performance by directly constructing intermediate domains without relying on likelihood estimation.

Contribution

It reformulates flow-based GDA as a semi-dual problem, introduces entropy regularization for stability, and provides theoretical analysis and extensive experiments demonstrating its effectiveness.

Findings

Enhanced stability in GDA training process.

Improved domain adaptation performance in experiments.

Theoretical guarantees for stability and generalization.

Abstract

Gradual domain adaptation (GDA) aims to mitigate domain shift by progressively adapting models from the source domain to the target domain via intermediate domains. However, real intermediate domains are often unavailable or ineffective, necessitating the synthesis of intermediate samples. Flow-based models have recently been used for this purpose by interpolating between source and target distributions; however, their training typically relies on sample-based log-likelihood estimation, which can discard useful information and thus degrade GDA performance. The key to addressing this limitation is constructing the intermediate domains via samples directly. To this end, we propose an Entropy-regularized Semi-dual Unbalanced Optimal Transport (E-SUOT) framework to construct intermediate domains. Specifically, we reformulate flow-based GDA as a Lagrangian dual problem and derive an equivalent semi-dual objective that circumvents the need for likelihood estimation. However, the dual problem leads to an unstable min-max training procedure. To alleviate this issue, we further introduce entropy regularization to convert it into a more stable alternative optimization procedure. Based on this, we propose a novel GDA training framework and provide theoretical analysis in terms of stability and generalization. Finally, extensive experiments are conducted to demonstrate the efficacy of the E-SUOT framework.