RECS: Robust Graph Embedding Using Connection Subgraphs

2018-05-03 · Saba A. Al-Sayouri, Danai Koutra, Evangelos E. Papalexakis, Sarah S. Lam

The success of graph embeddings or node representation learning in a variety of downstream tasks, such as node classification, link prediction, and recommendation systems, has led to their popularity in recent years. Representation learning algorithms aim to preserve local and global network structure by identifying node neighborhood notions. However, many existing algorithms generate embeddings that fail to properly preserve the network structure, or lead to unstable representations due to random processes (e.g., random walks to generate context) and, thus, cannot generate to multi-graph problems. In this paper, we propose RECS, a novel, stable graph embedding algorithmic framework. RECS learns graph representations using connection subgraphs by employing the analogy of graphs with electrical circuits. It preserves both local and global connectivity patterns, and addresses the issue of high-degree nodes. Further, it exploits the strength of weak ties and meta-data that have been neglected by baselines. The experiments show that RECS outperforms state-of-the-art algorithms by up to 36.85% on multi-label classification problem. Further, in contrast to baselines, RECS, being deterministic, is completely stable.

📄 PDF Abstract BibTeX arXiv:1805.01509

Code (0)

등록된 구현이 없습니다.

Tasks

General Classification Graph Embedding Link Prediction Multi-Label Classification MUlTI-LABEL-ClASSIFICATION Node Classification Recommendation Systems Representation Learning

Analysis and Optimization of GNN-Based Recommender Systems on Persistent Memory

2022-07-25 · Yuwei Hu, Jiajie Li, Zhongming Yu, Zhiru Zhang

Graph neural networks (GNNs), which have emerged as an effective method for handling machine learning tasks on graphs, bring a new approach to building recommender systems, where the task of recommendation can be formula…

Link Prediction Recommendation Systems

Metapath- and Entity-aware Graph Neural Network for Recommendation

2020-10-22 · Muhammad Umer Anwaar, Zhiwei Han, Shyam Arumugaswamy, Rayyan Ahmad Khan 외

In graph neural networks (GNNs), message passing iteratively aggregates nodes' information from their direct neighbors while neglecting the sequential nature of multi-hop node connections. Such sequential node connection…

Graph Neural Network Link Prediction Recommendation Systems

Graph Reasoning for Explainable Cold Start Recommendation

2024-06-11 · Jibril Frej, Marta Knezevic, Tanja Kaser

The cold start problem, where new users or items have no interaction history, remains a critical challenge in recommender systems (RS). A common solution involves using Knowledge Graphs (KG) to train entity embeddings or…

Entity Embeddings Knowledge Graphs Recommendation Systems

Do We Really Need Graph Convolution During Training? Light Post-Training Graph-ODE for Efficient Recommendation

2024-07-26 · Weizhi Zhang, Liangwei Yang, Zihe Song, Henry Peng Zou 외

The efficiency and scalability of graph convolution networks (GCNs) in training recommender systems (RecSys) have been persistent concerns, hindering their deployment in real-world applications. This paper presents a cri…

Recommendation Systems

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 Detection Node Classification