Link Prediction with Contextualized Self-Supervision
- URL: http://arxiv.org/abs/2201.10069v1
- Date: Tue, 25 Jan 2022 03:12:32 GMT
- Title: Link Prediction with Contextualized Self-Supervision
- Authors: Daokun Zhang, Jie Yin and Philip S. Yu
- Abstract summary: Link prediction aims to infer the existence of a link between two nodes in a network.
Traditional link prediction algorithms are hindered by three major challenges -- link sparsity, node attribute noise and network dynamics.
We propose a Contextualized Self-Supervised Learning framework that fully exploits structural context prediction for link prediction.
- Score: 63.25455976593081
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: Link prediction aims to infer the existence of a link between two nodes in a
network. Despite their wide application, the success of traditional link
prediction algorithms is hindered by three major challenges -- link sparsity,
node attribute noise and network dynamics -- that are faced by real-world
networks. To overcome these challenges, we propose a Contextualized
Self-Supervised Learning (CSSL) framework that fully exploits structural
context prediction for link prediction. The proposed CSSL framework forms edge
embeddings through aggregating pairs of node embeddings constructed via a
transformation on node attributes, which are used to predict the link existence
probability. To generate node embeddings tailored for link prediction,
structural context prediction is leveraged as a self-supervised learning task
to boost link prediction. Two types of structural contexts are investigated,
i.e., context nodes collected from random walks vs. context subgraphs. The CSSL
framework can be trained in an end-to-end manner, with the learning of node and
edge embeddings supervised by link prediction and the self-supervised learning
task. The proposed CSSL is a generic and flexible framework in the sense that
it can handle both transductive and inductive link prediction settings, and
both attributed and non-attributed networks. Extensive experiments and ablation
studies on seven real-world benchmark graph datasets demonstrate the superior
performance of the proposed self-supervision based link prediction algorithm
over state-of-the-art baselines on different types of networks under both
transductive and inductive settings. The proposed CSSL also yields competitive
performance in terms of its robustness to node attribute noise and scalability
over large-scale networks.
Related papers
- Can GNNs Learn Link Heuristics? A Concise Review and Evaluation of Link Prediction Methods [16.428742189544955]
This paper explores the ability of Graph Neural Networks (GNNs) in learning various forms of information for link prediction.
Our analysis reveals that GNNs cannot effectively learn structural information related to the number of common neighbors between two nodes.
Also, our extensive experiments indicate that trainable node embeddings can improve the performance of GNN-based link prediction models.
arXiv Detail & Related papers (2024-11-22T03:38:20Z) - Domain-adaptive Message Passing Graph Neural Network [67.35534058138387]
Cross-network node classification (CNNC) aims to classify nodes in a label-deficient target network by transferring the knowledge from a source network with abundant labels.
We propose a domain-adaptive message passing graph neural network (DM-GNN), which integrates graph neural network (GNN) with conditional adversarial domain adaptation.
arXiv Detail & Related papers (2023-08-31T05:26:08Z) - Variational Disentangled Graph Auto-Encoders for Link Prediction [10.390861526194662]
This paper proposes a novel framework with two variants, the disentangled graph auto-encoder (DGAE) and the variational disentangled graph auto-encoder (VDGAE)
The proposed framework infers the latent factors that cause edges in the graph and disentangles the representation into multiple channels corresponding to unique latent factors.
arXiv Detail & Related papers (2023-06-20T06:25:05Z) - Interpolation-based Correlation Reduction Network for Semi-Supervised
Graph Learning [49.94816548023729]
We propose a novel graph contrastive learning method, termed Interpolation-based Correlation Reduction Network (ICRN)
In our method, we improve the discriminative capability of the latent feature by enlarging the margin of decision boundaries.
By combining the two settings, we extract rich supervision information from both the abundant unlabeled nodes and the rare yet valuable labeled nodes for discnative representation learning.
arXiv Detail & Related papers (2022-06-06T14:26:34Z) - BSAL: A Framework of Bi-component Structure and Attribute Learning for
Link Prediction [33.488229191263564]
We propose a bicomponent structural and attribute learning framework (BSAL) that is designed to adaptively leverage information from topology and feature spaces.
BSAL constructs a semantic topology via the node attributes and then gets the embeddings regarding the semantic view.
It provides a flexible and easy-to-implement solution to adaptively incorporate the information carried by the node attributes.
arXiv Detail & Related papers (2022-04-18T03:12:13Z) - Learning Asymmetric Embedding for Attributed Networks via Convolutional
Neural Network [19.611523749659355]
We propose a novel deep asymmetric attributed network embedding model based on convolutional graph neural network, called AAGCN.
The main idea is to maximally preserve the asymmetric proximity and asymmetric similarity of directed attributed networks.
We test the performance of AAGCN on three real-world networks for network reconstruction, link prediction, node classification and visualization tasks.
arXiv Detail & Related papers (2022-02-13T13:35:15Z) - BScNets: Block Simplicial Complex Neural Networks [79.81654213581977]
Simplicial neural networks (SNN) have recently emerged as the newest direction in graph learning.
We present Block Simplicial Complex Neural Networks (BScNets) model for link prediction.
BScNets outperforms state-of-the-art models by a significant margin while maintaining low costs.
arXiv Detail & Related papers (2021-12-13T17:35:54Z) - Adversarial Robustness of Probabilistic Network Embedding for Link
Prediction [24.335469995826244]
We study adversarial robustness of Conditional Network Embedding (CNE) for link prediction.
We measure the sensitivity of the link predictions of the model to small adversarial perturbations of the network.
Our approach allows one to identify the links and non-links in the network that are most vulnerable to such perturbations.
arXiv Detail & Related papers (2021-07-05T11:07:35Z) - Interpretable Signed Link Prediction with Signed Infomax Hyperbolic
Graph [54.03786611989613]
signed link prediction in social networks aims to reveal the underlying relationships (i.e. links) among users (i.e. nodes)
We develop a unified framework, termed as Signed Infomax Hyperbolic Graph (textbfSIHG)
In order to model high-order user relations and complex hierarchies, the node embeddings are projected and measured in a hyperbolic space with a lower distortion.
arXiv Detail & Related papers (2020-11-25T05:09:03Z) - 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.