Graph Transfer Learning via Adversarial Domain Adaptation with Graph Convolution

Dai, Quanyu; Wu, Xiao-Ming; Xiao, Jiaren; Shen, Xiao; Wang, Dan

doi:10.1109/tkde.2022.3144250

Cited by 33 publications

(34 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, they describe two techniques to exploit node-level knowledge: context prediction and attribute masking; as well as two approaches for graph-level pretraining. More recently, Dai et al [24] present AdaGCN: a framework for transfer learning based on adversarial domain adaption with GCNs.…”

Section: Related Workmentioning

confidence: 99%

Investigating Transfer Learning in Graph Neural Networks

Nishai¹,

James²,

Zyl³

2022

Preprint

View full text Add to dashboard Cite

Graph neural networks (GNNs) build on the success of deep learning models by extending them for use in graph spaces. Transfer learning has proven extremely successful for traditional deep learning problems: resulting in faster training and improved performance. Despite the increasing interest in GNNs and their use cases, there is little research on their transferability. This research demonstrates that transfer learning is effective with GNNs, and describes how source tasks and the choice of GNN impact the ability to learn generalisable knowledge. We perform experiments using real-world and synthetic data within the contexts of node classification and graph classification. To this end, we also provide a general methodology for transfer learning experimentation and present a novel algorithm for generating synthetic graph classification tasks. We compare the performance of GCN, GraphSAGE and GIN across both the synthetic and real-world datasets. Our results demonstrate empirically that GNNs with inductive operations yield statistically significantly improved transfer. Further we show that similarity in community structure between source and target tasks support statistically significant improvements in transfer over and above the use of only the node attributes.

show abstract

Section: Related Workmentioning

confidence: 99%

Investigating Transfer Learning in Graph Neural Networks

Nishai¹,

James²,

Zyl³

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Graphbased domain adaptation is categorized based on the availability of cross-domain connections. For domain-exclusive graphs, approaches include SSL with GCNs (Shen and Chung, 2019) and domainadversarial learning (Dai et al, 2019). For crossdomain connected graphs, co-regularized training (Ni et al, 2018) and joint-embedding (Xu et al, 2017) have been explored.…”

Section: Domain-adversarialmentioning

confidence: 99%

KinGDOM: Knowledge-Guided DOMain Adaptation for Sentiment Analysis

Ghosal¹,

Hazarika²,

Roy³

et al. 2020

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

View full text Add to dashboard Cite

Cross-domain sentiment analysis has received significant attention in recent years, prompted by the need to combat the domain gap between different applications that make use of sentiment analysis. In this paper, we take a novel perspective on this task by exploring the role of external commonsense knowledge. We introduce a new framework, KinGDOM, which utilizes the ConceptNet knowledge graph to enrich the semantics of a document by providing both domain-specific and domain-general background concepts. These concepts are learned by training a graph convolutional autoencoder that leverages inter-domain concepts in a domain-invariant manner. Conditioning a popular domain-adversarial baseline method with these learned concepts helps improve its performance over state-of-the-art approaches, demonstrating the efficacy of our proposed framework.

show abstract

“…assumption [16]. There are a few recent studies addressing the challenging problem of cross-graph node classification, such as CDNE [6], ACDNE [7], AdaGCN [8], and UDA-GCN [9]. Although their performance is more preferable than those designed for singlegraph learning, three open questions remain to be further explored.…”

Section: Introductionmentioning

confidence: 99%

“…Although these methods reach a certain level of local or global consistency, they still lack consideration about the global structural role of a node. • Existing studies align the source and target representations by minimizing domain classification error [7], [9] or distribution discrepancy metrics such as the Wasserstein distance [8]. Since the domain alignment is category agnostic in these methods, the aligned node representations are possibly not classification friendly.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Domain Adaptive Graph Infomax via Conditional Adversarial Networks

Xiao

Dai

Xie

et al. 2023

IEEE Trans. Netw. Sci. Eng.

Self Cite

View full text Add to dashboard Cite

The emerging graph neural networks (GNNs) have demonstrated impressive performance on the node classification problem in complex networks. However, existing GNNs are mainly devised to classify nodes in a (partially) labeled graph. To classify nodes in a newly-collected unlabeled graph, it is desirable to transfer label information from an existing labeled graph. To address this cross-graph node classification problem, we propose a graph infomax method that is domain adaptive. Node representations are computed through neighborhood aggregation. Mutual information is maximized between node representations and global summaries, encouraging node representations to encode the global structural information. Conditional adversarial networks are employed to reduce the domain discrepancy by aligning the multimodal distributions of node representations. Experimental results in real-world datasets validate the performance of our method in comparison with the state-of-the-art baselines.

show abstract

Graph Transfer Learning via Adversarial Domain Adaptation with Graph Convolution

Cited by 33 publications

References 53 publications

Investigating Transfer Learning in Graph Neural Networks

Investigating Transfer Learning in Graph Neural Networks

KinGDOM: Knowledge-Guided DOMain Adaptation for Sentiment Analysis

Domain Adaptive Graph Infomax via Conditional Adversarial Networks

Contact Info

Product

Resources

About