You Only Transfer What You Share: Intersection-Induced Graph Transfer
Learning for Link Prediction
- URL: http://arxiv.org/abs/2302.14189v2
- Date: Mon, 19 Jun 2023 01:20:12 GMT
- Title: You Only Transfer What You Share: Intersection-Induced Graph Transfer
Learning for Link Prediction
- Authors: Wenqing Zheng, Edward W Huang, Nikhil Rao, Zhangyang Wang, Karthik
Subbian
- Abstract summary: We investigate a previously overlooked phenomenon: in many cases, a densely connected, complementary graph can be found for the original graph.
The denser graph may share nodes with the original graph, which offers a natural bridge for transferring selective, meaningful knowledge.
We identify this setting as Graph Intersection-induced Transfer Learning (GITL), which is motivated by practical applications in e-commerce or academic co-authorship predictions.
- Score: 79.15394378571132
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Link prediction is central to many real-world applications, but its
performance may be hampered when the graph of interest is sparse. To alleviate
issues caused by sparsity, we investigate a previously overlooked phenomenon:
in many cases, a densely connected, complementary graph can be found for the
original graph. The denser graph may share nodes with the original graph, which
offers a natural bridge for transferring selective, meaningful knowledge. We
identify this setting as Graph Intersection-induced Transfer Learning (GITL),
which is motivated by practical applications in e-commerce or academic
co-authorship predictions. We develop a framework to effectively leverage the
structural prior in this setting. We first create an intersection subgraph
using the shared nodes between the two graphs, then transfer knowledge from the
source-enriched intersection subgraph to the full target graph. In the second
step, we consider two approaches: a modified label propagation, and a
multi-layer perceptron (MLP) model in a teacher-student regime. Experimental
results on proprietary e-commerce datasets and open-source citation graphs show
that the proposed workflow outperforms existing transfer learning baselines
that do not explicitly utilize the intersection structure.
Related papers
- Against Multifaceted Graph Heterogeneity via Asymmetric Federated Prompt Learning [5.813912301780917]
We propose a Federated Graph Prompt Learning (FedGPL) framework to efficiently enable prompt-based asymmetric graph knowledge transfer.
We conduct theoretical analyses and extensive experiments to demonstrate the significant accuracy and efficiency effectiveness of FedGPL.
arXiv Detail & Related papers (2024-11-04T11:42:25Z) - Hypergraph-enhanced Dual Semi-supervised Graph Classification [14.339207883093204]
We propose a Hypergraph-Enhanced DuAL framework named HEAL for semi-supervised graph classification.
To better explore the higher-order relationships among nodes, we design a hypergraph structure learning to adaptively learn complex node dependencies.
Based on the learned hypergraph, we introduce a line graph to capture the interaction between hyperedges.
arXiv Detail & Related papers (2024-05-08T02:44:13Z) - Graph Transformer GANs with Graph Masked Modeling for Architectural
Layout Generation [153.92387500677023]
We present a novel graph Transformer generative adversarial network (GTGAN) to learn effective graph node relations.
The proposed graph Transformer encoder combines graph convolutions and self-attentions in a Transformer to model both local and global interactions.
We also propose a novel self-guided pre-training method for graph representation learning.
arXiv Detail & Related papers (2024-01-15T14:36:38Z) - Graph Relation Aware Continual Learning [3.908470250825618]
Continual graph learning (CGL) studies the problem of learning from an infinite stream of graph data.
We design a relation-aware adaptive model, dubbed as RAM-CG, that consists of a relation-discovery modular to explore latent relations behind edges.
RAM-CG provides significant 2.2%, 6.9% and 6.6% accuracy improvements over the state-of-the-art results on CitationNet, OGBN-arxiv and TWITCH dataset.
arXiv Detail & Related papers (2023-08-16T09:53:20Z) - Spectral Augmentations for Graph Contrastive Learning [50.149996923976836]
Contrastive learning has emerged as a premier method for learning representations with or without supervision.
Recent studies have shown its utility in graph representation learning for pre-training.
We propose a set of well-motivated graph transformation operations to provide a bank of candidates when constructing augmentations for a graph contrastive objective.
arXiv Detail & Related papers (2023-02-06T16:26:29Z) - Non-IID Transfer Learning on Graphs [35.84135001172101]
Transfer learning refers to the transfer of knowledge from a relevant source domain to a target domain.
We propose rigorous generalization bounds and algorithms for cross-network transfer learning from a source graph to a target graph.
arXiv Detail & Related papers (2022-12-15T22:29:29Z) - CGMN: A Contrastive Graph Matching Network for Self-Supervised Graph
Similarity Learning [65.1042892570989]
We propose a contrastive graph matching network (CGMN) for self-supervised graph similarity learning.
We employ two strategies, namely cross-view interaction and cross-graph interaction, for effective node representation learning.
We transform node representations into graph-level representations via pooling operations for graph similarity computation.
arXiv Detail & Related papers (2022-05-30T13:20:26Z) - Co-embedding of Nodes and Edges with Graph Neural Networks [13.020745622327894]
Graph embedding is a way to transform and encode the data structure in high dimensional and non-Euclidean feature space.
CensNet is a general graph embedding framework, which embeds both nodes and edges to a latent feature space.
Our approach achieves or matches the state-of-the-art performance in four graph learning tasks.
arXiv Detail & Related papers (2020-10-25T22:39:31Z) - Line Graph Neural Networks for Link Prediction [71.00689542259052]
We consider the graph link prediction task, which is a classic graph analytical problem with many real-world applications.
In this formalism, a link prediction problem is converted to a graph classification task.
We propose to seek a radically different and novel path by making use of the line graphs in graph theory.
In particular, each node in a line graph corresponds to a unique edge in the original graph. Therefore, link prediction problems in the original graph can be equivalently solved as a node classification problem in its corresponding line graph, instead of a graph classification task.
arXiv Detail & Related papers (2020-10-20T05:54:31Z) - Learning to Extrapolate Knowledge: Transductive Few-shot Out-of-Graph
Link Prediction [69.1473775184952]
We introduce a realistic problem of few-shot out-of-graph link prediction.
We tackle this problem with a novel transductive meta-learning framework.
We validate our model on multiple benchmark datasets for knowledge graph completion and drug-drug interaction prediction.
arXiv Detail & Related papers (2020-06-11T17:42:46Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.