Contents

Residual2Vec: Debiasing graph embedding with random graphs

Kojaku, Sadamori / Yoon, Jisung / Constantino, Isabel / Ahn, Yong-Yeol

  • 381 ITEM VIEW
  • 0 DOWNLOAD
Abstract

Graph embedding maps a graph into a convenient vector-space representation for graph analysis and machine learning applications. Many graph embedding methods hinge on a sampling of context nodes based on random walks. However, random walks can be a biased sampler due to the structural properties of graphs. Most notably, random walks are biased by the degree of each node, where a node is sampled proportionally to its degree. The implication of such biases has not been clear, particularly in the context of graph representation learning. Here, we investigate the impact of the random walks' bias on graph embedding and propose residual2vec, a general graph embedding method that can debias various structural biases in graphs by using random graphs. We demonstrate that this debiasing not only improves link prediction and clustering performance but also allows us to explicitly model salient structural properties in graph embedding.

Issue Date
2021-12
Publisher
NeurIPS
URI
https://archives.kdischool.ac.kr/handle/11125/54416
URL
https://proceedings.neurips.cc/paper/2021/hash/ca9541826e97c4530b07dda2eba0e013-Abstract.html
Conf. Name
35th Conference on Neural Information Processing Systems (NeurIPS 2021)
Place
US
Conference Date
2021-12-06
Files in This Item:
    There are no files associated with this item.

Click the button and follow the links to connect to the full text. (KDI CL members only)

qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

상단으로 이동