HiGDA: Hierarchical Graph of Nodes to Learn Local-to-Global Topology for Semi-Supervised Domain Adaptation

Ba Hung Ngo, Doanh C. Bui, Nhat-Tuong Do-Tran, Tae Jong ChoiAAAI 2025 · DOI

Deep learning models often struggle with "domain shift"—the performance drop when a model trained on one dataset (source) is applied to a different but related dataset (target). In a paper presented at AAAI-25, researchers introduced HiGDA (Hierarchical Graph of Nodes), a novel framework that leverages graph theory to bridge this gap in Semi-Supervised Domain Adaptation (SSDA).

The Challenge of SSDA

SSDA involves a large labeled source dataset and a target dataset with very few labeled samples. Traditional architectures face distinct hurdles:

  • CNNs excel at local textures but often fail to capture the global structure of complex objects.
  • Vision Transformers (ViTs) capture global relationships but are prone to incorporating irrelevant background noise.
  • Structural Gaps exist because most models process images in isolation, failing to explicitly model category-level relationships across domains during feature extraction.

Methodology: The Hierarchical Approach

HiGDA addresses these issues by treating images and batches as a two-level hierarchical graph structure.

1. Local Graph (LoG)

At the feature level, HiGDA represents an image as a graph of patches. Unlike the all-to-all attention of Transformers, each patch node only connects to its $k$-nearest neighbors in the feature space. This selective connectivity acts as a natural saliency mask, allowing the model to "cluster" the main object and effectively ignore background noise.

2. Global Graph (GoG) and Graph Active Learning

At the category level, HiGDA constructs a graph where each image in a training mini-batch is a node. Edges are established between images of the same category, forcing the model to learn domain-invariant representations. To leverage unlabeled target data, the framework employs Graph Active Learning (GAL), which uses high-confidence pseudo-labels to dynamically integrate unlabeled samples into the global graph.

Overview of the HiGDA framework, illustrating the transition from local patch-based graphs to a global category-level graph within a mini-batch.

Key Insights and Qualitative Analysis

A significant advantage of HiGDA is its inherent ability to filter noise without requiring explicit attention maps. By restricting connectivity to feature-similar patches, the local graph naturally links different parts of a semantic object (e.g., the body and tail of a dolphin) while excluding complex backgrounds.

Visualization of the local graph connectivity, demonstrating the model's ability to focus on semantic objects while ignoring background noise across various categories.

Experimental Results

The researchers evaluated HiGDA on three major benchmarks: Office-Home, DomainNet, and VisDA2017. The results demonstrate a new state-of-the-art for SSDA:

  • Office-Home: In 1-shot settings, HiGDA outperformed previous leaders by 5.3%.
  • DomainNet: Combined with minimax entropy (MME) techniques, HiGDA achieved 90.5% accuracy in 1-shot tasks, significantly surpassing the ResNet-34 baseline of 56.8%.
  • Efficiency: The LoG-Tiny backbone uses only 9.5M parameters—less than half of a standard ResNet-34 (21.6M)—while delivering superior accuracy.

Conclusion

HiGDA represents a shift from "image-wise" to "graph-wise" learning in domain adaptation. By modeling the topological structure of categories across domains and using local graphs to filter noise, it provides a robust and efficient solution for SSDA. Future work will focus on mitigating the impact of noisy pseudo-labels in the global graph to further enhance stability.

Summary updated

BibTeX
@inproceedings{ngo2025higda,
  author = {Ba Hung Ngo and Doanh C. Bui and Nhat-Tuong Do-Tran and Tae Jong Choi},
  title = {{HiGDA: Hierarchical Graph of Nodes to Learn Local-to-Global Topology for Semi-Supervised Domain Adaptation}},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year = {2025},
  doi = {10.1609/aaai.v39i6.32662},
}
Figure