CVAIOct 26, 2023

SPA: A Graph Spectral Alignment Perspective for Domain Adaptation

arXiv:2310.17594v250 citationsh-index: 17Has Code
Originality Highly original
AI Analysis

This addresses the problem of adapting machine learning models to new domains with different data distributions, which is incremental as it builds on prior work by incorporating intra-domain structures.

The paper tackles the tradeoff between inter-domain transferability and intra-domain discriminability in unsupervised domain adaptation by proposing a graph spectral alignment framework, achieving state-of-the-art performance on standardized benchmarks.

Unsupervised domain adaptation (UDA) is a pivotal form in machine learning to extend the in-domain model to the distinctive target domains where the data distributions differ. Most prior works focus on capturing the inter-domain transferability but largely overlook rich intra-domain structures, which empirically results in even worse discriminability. In this work, we introduce a novel graph SPectral Alignment (SPA) framework to tackle the tradeoff. The core of our method is briefly condensed as follows: (i)-by casting the DA problem to graph primitives, SPA composes a coarse graph alignment mechanism with a novel spectral regularizer towards aligning the domain graphs in eigenspaces; (ii)-we further develop a fine-grained message propagation module -- upon a novel neighbor-aware self-training mechanism -- in order for enhanced discriminability in the target domain. On standardized benchmarks, the extensive experiments of SPA demonstrate that its performance has surpassed the existing cutting-edge DA methods. Coupled with dense model analysis, we conclude that our approach indeed possesses superior efficacy, robustness, discriminability, and transferability. Code and data are available at: https://github.com/CrownX/SPA.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes