In many real-world applications, graph-structured data used for training and testing have differences in distribution, such as in high energy physics (HEP) where simulation data used for training may not match real experiments. Graph domain adaptation (GDA) is a method used to address these differences. However, current GDA primarily works by aligning the distributions of node representations output by a single graph neural network encoder shared across the training and testing domains, which may often yield sub-optimal solutions. This work examines different impacts of distribution shifts caused by either graph structure or node attributes and identifies a new type of shift, named conditional structure shift (CSS), which current GDA approaches are provably sub-optimal to deal with. A novel approach, called structural reweighting (StruRW), is proposed to address this issue and is tested on synthetic graphs, four benchmark datasets, and a new application in HEP. StruRW has shown significant performance improvement over the baselines in the settings with large graph structure shifts, and reasonable performance improvement when node attribute shift dominates.
more »
« less
This content will become publicly available on November 20, 2026
Avoiding Structural Pitfalls: Self-Supervised Low-Rank Feature Tuning for Graph Test-Time Adaptation
Pre-trained graph neural networks (GNNs) have demonstrated significant success in leveraging large-scale graph data to learn transferable representations. However, their performance often degrades under distribution shifts, particularly in real-world scenarios where test labels are unavailable. To address this challenge, we propose Graph Optimization via Augmented Transformations (GOAT), a novel self-supervised test-time tuning paradigm that adapts pre-trained GNNs to distribution-shifted test data by focusing exclusively on node feature transformations. By avoiding complex and often suboptimal graph structure transformations, GOAT overcomes the limitations of existing data-centric methods. To further address the issue of transformation collapse, where feature transformations converge to trivial solutions—such as when the test-time learned data-centric transformation degenerates into a constant or identity mapping across different inputs, we introduce a parameter-efficient low-rank adapter that generates diverse transformations tailored to individual input graphs. This design not only enhances adaptation performance but also improves interpretability by avoiding modifications to the graph structure. Through extensive experiments on six real-world datasets with diverse distribution shifts, we demonstrate that GOAT achieves consistent performance improvements across different pre-trained GNN backbones, outperforming state-of-the-art test-time adaptation methods.
more »
« less
- Award ID(s):
- 2451605
- PAR ID:
- 10686291
- Publisher / Repository:
- Transactions on Machine Learning Research
- Date Published:
- Journal Name:
- Transactions on machine learning research
- ISSN:
- 2835-8856
- Subject(s) / Keyword(s):
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Vision–language models learn visual concepts from the supervision of natural language. It can significantly enhance the generalizability of real-time intelligent sensing, such as analyzing camera-captured real-time images for visually impaired users. However, adapting vision–language models to distribution shifts at test time, caused by several factors such as lighting or weather changes, remains challenging. In particular, most existing test-time adaptation methods rely on gradient-based fine-tuning and backpropagation, making them computationally expensive and unsuitable for real-time applications. To address this challenge, the Training-Free Dynamic Adapter (TDA) has recently been introduced as a lightweight alternative that uses a dynamic key–value cache and pseudo-label refinement for test-time adaptation without backpropagation. Building on this, we propose TDA-L, a new framework that integrates Low-Rank Adaptation (LoRA) to reduce the size of feature representations and related computational overhead at test time using pre-learned low-rank matrices. TDA-L applies LoRA transformations to both query and cached features during inference, cost-efficiently improving robustness to distribution shifts while maintaining the training-free nature of TDA. Experimental results on seven benchmarks show that TDA-L maintains accuracy but achieves lower latency, less memory consumption, and higher throughput, making it well-suited for AI-based real-time sensing.more » « less
-
Graph Neural Networks (GNNs) are neural models that leverage the dependency structure in graphical data via message passing among the graph nodes. GNNs have emerged as pivotal architectures in analyzing graph-structured data, and their expansive application in sensitive domains requires a comprehensive understanding of their decision-making processes — necessitating a framework for GNN explainability. An explanation function for GNNs takes a pre-trained GNN along with a graph as input, to produce a ‘sufficient statistic’ subgraph with respect to the graph label. A main challenge in studying GNN explainability is to provide fidelity measures that evaluate the performance of these explanation functions. This paper studies this foundational challenge, spotlighting the inherent limitations of prevailing fidelity metrics, including Fid+, Fid−, and Fid∆. Specifically, a formal, information-theoretic definition of explainability is introduced and it is shown that existing metrics often fail to align with this definition across various statistical scenarios. The reason is due to potential distribution shifts when subgraphs are removed in computing these fidelity measures. Subsequently, a robust class of fidelity measures are introduced, and it is shown analytically that they are resilient to distribution shift issues and are applicable in a wide range of scenarios. Extensive empirical analysis on both synthetic and real datasets are provided to illustrate that the proposed metrics are more coherent with gold standard metrics. The source code is available at https://trustai4s-lab.github.io/fidelity.more » « less
-
DOS-GNN: Dual-Feature Aggregations with Over-Sampling for Class-Imbalanced Fraud Detection On GraphsAs fraudulent activities have shot up manifolds, fraud detection has emerged as a pivotal process in different fields (e.g., e-commerce, online reviews, and social networks). Since interactions among entities provide valuable insights into fraudulent activities, such behaviors can be naturally represented as graph structures, where graph neural networks (GNNs) have been developed as prominent models to boost the efficacy of fraud detection. In graph-based fraud detection, handling imbalanced datasets poses a significant challenge, as the minority class often gets overshadowed, diminishing the performance of conventional GNNs. While oversampling has recently been adapted for imbalanced graphs, it contends with issues such as graph heterophily and noisy edge synthesis. To address these limitations, this paper introduces DOS-GNN, incorporating Dual-feature aggregation with Over-Sampling to advance GNNs for class-imbalanced fraud detection on graphs. This model exploits feature separation and dual-feature aggregation to mitigate the impact of heterophily and acquire refined node embeddings that facilitate fraud oversampling to balance class distribution without the need for edge synthesis. Extensive experiments on four large and real-world fraud datasets demonstrate that DOS-GNN can significantly improve fraud detection performance on graphs with different imbalance ratios and homophily ratios, outperforming state-of-the-art GNN models.more » « less
-
Graphs are a powerful medium for solving real-world problems, but graph neural networks (GNNs) face inherent limitations, driving the exploration of graph Transformers. While most existing graph Transformers focus on homogeneous graphs, methods for heterogeneous graphs remain underexplored. Current approaches often overlook edge semantics, essential for capturing diverse patterns, and rely on subgraph sampling, which limits the ability to model global graph patterns effectively. We propose EHFormer, a novel edge-centric heterogeneous graph Transformer. EHFormer encodes relational dependencies using edge-centric sequences and meta-path-aware positional features to capture multi-hop patterns. To address the trade-off between computational efficiency and global context modeling, we introduce a vector-quantized memory mechanism. This mechanism compresses global graph patterns into a compact codebook and empowers integration of global context with local subgraph modeling, enabling EHFormer to encode both local and global patterns. Extensive experiments on benchmark datasets demonstrate that EHFormer achieves state-of-the-art performance, validating its scalability and effectiveness.more » « less
An official website of the United States government
