paper-with-me

Papers

NESS: Node Embeddings from Static SubGraphs

2023-03-15 · Talip Ucar

We present a framework for learning Node Embeddings from Static Subgraphs (NESS) using a graph autoencoder (GAE) in a transductive setting. NESS is based on two key ideas: i) Partitioning the training graph to multiple static, sparse subgraphs with non-overlapping edges using random edge split during data pre-processing, ii) Aggregating the node representations learned from each subgraph to obtain a joint representation of the graph at test time. Moreover, we propose an optional contrastive learning approach in transductive setting. We demonstrate that NESS gives a better node representation for link prediction tasks compared to current autoencoding methods that use either the whole graph or stochastic subgraphs. Our experiments also show that NESS improves the performance of a wide range of graph encoders and achieves state-of-the-art results for link prediction on multiple real-world datasets with edge homophily ratio ranging from strong heterophily to strong homophily.

📄 PDF Abstract BibTeX arXiv:2303.08958

Code (1)

AstraZeneca/NESS 공식 구현 pytorch

Tasks

Contrastive LearningGraph EmbeddingLink Prediction

Methods 이 논문이 사용한 방법론

Test 설명 없음
Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

Distributed Representation of Subgraphs

2017-02-22 · Bijaya Adhikari, Yao Zhang, Naren Ramakrishnan, B. Aditya Prakash

Network embeddings have become very popular in learning effective feature representations of networks. Motivated by the recent successes of embeddings in natural language processing, researchers have tried to find networ…

Community DetectionNode Classification

Learn to Cluster Faces with Better Subgraphs

2023-04-21 · Yuan Cao, Di Jiang, Guanqun Hou, Fan Deng 외

Face clustering can provide pseudo-labels to the massive unlabeled face data and improve the performance of different face recognition models. The existing clustering methods generally aggregate the features within subgr…

ClusteringFace ClusteringFace Recognition

AdaGCL: Adaptive Subgraph Contrastive Learning to Generalize Large-scale Graph Training

2022-10-17 · ACM International Conference on Information & Knowledge Management (CIKM) 2022 10 · Yili Wang, Kaixiong Zhou, Rui Miao, Ninghao Liu 외

Training graph neural networks (GNNs) with good generalizability on large-scale graphs is a challenging problem. Existing methods mainly divide the input graph into multiple subgraphs and train them in different batches …

Contrastive LearningData AugmentationNode Classification

Self-Supervised Learning of Contextual Embeddings for Link Prediction in Heterogeneous Networks

2020-07-22 · Ping Wang, Khushbu Agarwal, Colby Ham, Sutanay Choudhury 외

Representation learning methods for heterogeneous networks produce a low-dimensional vector embedding for each node that is typically fixed for all tasks involving the node. Many of the existing methods focus on obtainin…

Link PredictionRepresentation LearningSelf-Supervised Learning

Subgraph Frequency Distribution Estimation using Graph Neural Networks

2022-07-14 · Zhongren Chen, Xinyue Xu, Shengyi Jiang, Hao Wang 외

Small subgraphs (graphlets) are important features to describe fundamental units of a large network. The calculation of the subgraph frequency distributions has a wide application in multiple domains including biology an…