paper-with-me

Papers

Is a Single Embedding Enough? Learning Node Representations that Capture Multiple Social Contexts

2019-05-06 · Alessandro Epasto, Bryan Perozzi

Recent interest in graph embedding methods has focused on learning a single representation for each node in the graph. But can nodes really be best described by a single vector representation? In this work, we propose a method for learning multiple representations of the nodes in a graph (e.g., the users of a social network). Based on a principled decomposition of the ego-network, each representation encodes the role of the node in a different local community in which the nodes participate. These representations allow for improved reconstruction of the nuanced relationships that occur in the graph -- a phenomenon that we illustrate through state-of-the-art results on link prediction tasks on a variety of graphs, reducing the error by up to $90\%$. In addition, we show that these embeddings allow for effective visual analysis of the learned community structure.

📄 PDF Abstract BibTeX arXiv:1905.02138

Code (2)

google-research/google-research/tree/master/graph_embedding/persona 공식 구현 tf
benedekrozemberczki/Splitter pytorch

Tasks

Graph EmbeddingLink Prediction

Similar Papers 제목 키워드 기반

Persona2vec: A Flexible Multi-role Representations Learning Framework for Graphs

2020-06-04 · Jisung Yoon, Kai-Cheng Yang, Woo-Sung Jung, Yong-Yeol Ahn

Graph embedding techniques, which learn low-dimensional representations of a graph, are achieving state-of-the-art performance in many graph mining tasks. Most existing embedding algorithms assign a single vector to each…

Graph EmbeddingGraph MiningLink Prediction

Neighbor2vec: an efficient and effective method for Graph Embedding

2022-01-07 · Zhiming Lin

Graph embedding techniques have led to significant progress in recent years. However, present techniques are not effective enough to capture the patterns of networks. This paper propose neighbor2vec, a neighbor-based sam…

Graph EmbeddingLink PredictionNode Classification

Network Together: Node Classification via Cross-Network Deep Network Embedding

2020-06-04 · Xiao Shen, Quanyu Dai, Sitong Mao, Fu-Lai Chung 외

Network embedding is a highly effective method to learn low-dimensional node vector representations with original network structures being well preserved. However, existing network embedding algorithms are mostly develop…

Domain AdaptationGeneral ClassificationNetwork EmbeddingNode Classification

PersonaSAGE: A Multi-Persona Graph Neural Network

2022-12-28 · Gautam Choudhary, Iftikhar Ahamath Burhanuddin, Eunyee Koh, Fan Du 외

Graph Neural Networks (GNNs) have become increasingly important in recent years due to their state-of-the-art performance on many important downstream applications. Existing GNNs have mostly focused on learning a single …

Graph Neural NetworkLink PredictionManagementNode Classification

Splitter: Learning Node Representations that Capture Multiple Social Contexts

2019-03-18 · WWW 2019 3 · Alessandro Epasto, Bryan Perozzi

Recent interest in graph embedding methods has focused on learning a single representation for each node in the graph. But can nodes really be best described by a single vector representation? In this work, we propose a …

Graph EmbeddingLink PredictionNetwork Embedding