DELTA: Dual Consistency Delving with Topological Uncertainty for Active Graph Domain Adaptation

2024-09-13

arXiv.org

AI Summary

This work addresses the performance degradation in graph domain adaptation caused by scarce semantic labels on target graphs. We propose an active learning–based dual-view graph subnetwork framework. Methodologically, we introduce a novel edge-guided and path-guided collaborative dual-subnetwork architecture to model higher-order topological structures; design a K-hop degree-aggregated topological uncertainty estimation mechanism; and integrate cross-domain node discrepancy scoring for fine-grained candidate node selection. Our core contribution lies in the organic unification of topological-semantic mining, consistency regularization, and uncertainty modeling to precisely identify the most informative nodes for labeling. Extensive experiments on multiple benchmark datasets demonstrate that our method achieves significantly higher target-domain accuracy with substantially fewer annotation costs compared to state-of-the-art approaches. The source code is publicly available.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Reasoning under Uncertainty: Graphical Models

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

Graph domain adaptation has recently enabled knowledge transfer across different graphs. However, without the semantic information on target graphs, the performance on target graphs is still far from satisfactory. To address the issue, we study the problem of active graph domain adaptation, which selects a small quantitative of informative nodes on the target graph for extra annotation. This problem is highly challenging due to the complicated topological relationships and the distribution discrepancy across graphs. In this paper, we propose a novel approach named Dual Consistency Delving with Topological Uncertainty (DELTA) for active graph domain adaptation. Our DELTA consists of an edge-oriented graph subnetwork and a path-oriented graph subnetwork, which can explore topological semantics from complementary perspectives. In particular, our edge-oriented graph subnetwork utilizes the message passing mechanism to learn neighborhood information, while our path-oriented graph subnetwork explores high-order relationships from sub-structures. To jointly learn from two subnetworks, we roughly select informative candidate nodes with the consideration of consistency across two subnetworks. Then, we aggregate local semantics from its K-hop subgraph based on node degrees for topological uncertainty estimation. To overcome potential distribution shifts, we compare target nodes and their corresponding source nodes for discrepancy scores as an additional component for fine selection. Extensive experiments on benchmark datasets demonstrate that DELTA outperforms various state-of-the-art approaches. The code implementation of DELTA is available at https://github.com/goose315/DELTA.

Problem

• Active graph domain adaptation for cross-graph knowledge transfer
• Addressing topological uncertainty in target graph node selection
• Mitigating distribution discrepancy between source and target graphs

Innovation

• Dual subnetworks explore topological semantics complementarily
• Topological uncertainty estimated via K-hop subgraph aggregation
• Discrepancy scores address potential distribution shifts