DELTA: Dual Consistency Delving with Topological Uncertainty for Active Graph Domain Adaptation
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 44 of its 88 references that are in the map. First posted on arXiv 13 Sep 2024.
Builds on
44 of 88 references.
References · 44
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
- 2017Graph Attention Networkscited by 8,854
- 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,414
- 2019Simplifying Graph Convolutional Networkscited by 1,470
- 2018A Survey of Unsupervised Deep Domain Adaptationcited by 361
- 2017Mind the Class Weight Bias: Weighted Maximum Mean Discrepancy for Unsupervised Domain Adaptationcited by 151
- 2017Topology Adaptive Graph Convolutional Networkscited by 112
- 2020A survey on domain adaptation theory: learning bounds and theoretical guaranteescited by 109
- 2022A Comparative Survey of Deep Active Learningcited by 88
- 2019Active Adversarial Domain Adaptationcited by 73
32 more
- 2020Active Domain Adaptation via Clustering Uncertainty-weighted Embeddingscited by 71
- 2019Graph Transfer Learning via Adversarial Domain Adaptation with Graph Convolutioncited by 67
- 2022Does GNN Pretraining Help Molecular Representation?cited by 59
- 2017Active Learning for Graph Embeddingcited by 53
- 2021Active Learning for Domain Adaptation: An Energy-Based Approachcited by 53
- 2020Graph Policy Network for Transferable Active Learning on Graphscited by 49
- 2023CoCo: A Coupled Contrastive Framework for Unsupervised Domain Adaptive Graph Classificationcited by 46
- 2022Non-IID Transfer Learning on Graphscited by 43
- 2020Path Integral Based Convolution and Pooling for Graph Neural Networkscited by 35
- 2021Graph Domain Adaptation: A Generative Viewcited by 35
- 2022FP-GNN: a versatile deep learning architecture for enhanced molecular property predictioncited by 31
- 2022Cross-Domain Graph Anomaly Detection via Anomaly-aware Contrastive Alignmentcited by 31
- 2023Learning on Graphs with Out-of-Distribution Nodescited by 29
- 2023Semi-supervised Domain Adaptation in Graph Transfer Learningcited by 27
- 2019GraLSP: Graph Neural Networks with Local Structural Patternscited by 25
- 2018Domain Adaptation on Graphs by Learning Aligned Graph Basescited by 24
- 2022Information Gain Propagation: a new way to Graph Active Learning with Soft Labelscited by 16
- 2023MuSe-GNN: Learning Unified Gene Representation From Multimodal Biological Graph Datacited by 14
- 2023Half-Hop: A graph upsampling approach for slowing down message passingcited by 13
- 2021BridgeDPI: A Novel Graph Neural Network for Predicting Drug-Protein Interactionscited by 12
- 2022Partition-Based Active Learning for Graph Neural Networkscited by 12
- 2019ActiveHNE: Active Heterogeneous Network Embeddingcited by 11
- 2023ALEX: Towards Effective Graph Transfer Learning with Noisy Labelscited by 11
- 2024Graph Domain Adaptation: Challenges, Progress and Prospectscited by 11
- 2024Uncertainty for Active Learning on Graphscited by 11
- 2023Domain-adaptive Message Passing Graph Neural Networkcited by 10
- 2023Efficient Exact Subgraph Matching via GNN-based Path Dominance Embedding (Technical Report)cited by 9
- 2024Breaking the Barrier: Selective Uncertainty-based Active Learning for Medical Image Segmentationcited by 9
- 2020Supervised Domain Adaptation: A Graph Embedding Perspective and a Rectified Experimental Protocolcited by 8
- 2023Domain-adaptive Graph Attention-supervised Network for Cross-network Edge Classificationcited by 5
- 2022Dissimilar Nodes Improve Graph Active Learningcited by 3
- 2024Class-Balanced and Reinforced Active Learning on Graphscited by 1
Built on by
Citing papers per year: 2024: 1; 2025: 0; 2026: 1.
2 papers.