홈 › Papers

Inductive and Unsupervised Representation Learning on Graph Structured Objects

2020-05-01 · ICLR 2020 1 · Lichen Wang, Bo Zong, Qianqian Ma, Wei Cheng, Jingchao Ni, Wenchao Yu, Yanchi Liu, Dongjin Song, Haifeng Chen, Yun Fu

Inductive and unsupervised graph learning is a critical technique for predictive or information retrieval tasks where label information is difficult to obtain. It is also challenging to make graph learning inductive and unsupervised at the same time, as learning processes guided by reconstruction error based loss functions inevitably demand graph similarity evaluation that is usually computationally intractable. In this paper, we propose a general framework SEED (Sampling, Encoding, and Embedding Distributions) for inductive and unsupervised representation learning on graph structured objects. Instead of directly dealing with the computational challenges raised by graph similarity evaluation, given an input graph, the SEED framework samples a number of subgraphs whose reconstruction errors could be efficiently evaluated, encodes the subgraph samples into a collection of subgraph vectors, and employs the embedding of the subgraph vector distribution as the output vector representation for the input graph. By theoretical analysis, we demonstrate the close connection between SEED and graph isomorphism. Using public benchmark datasets, our empirical study suggests the proposed SEED framework is able to achieve up to 10% improvement, compared with competitive baseline methods.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Graph Learning Graph Similarity Information Retrieval Representation Learning Retrieval

Graph Attention Auto-Encoders

2019-05-26 · Amin Salehi, Hasan Davulcu

Auto-encoders have emerged as a successful framework for unsupervised learning. However, conventional auto-encoders are incapable of utilizing explicit relations in structured data. To take advantage of relations in grap…

Decoder Graph Attention Inductive Learning Node Classification+1

HGATE: Heterogeneous Graph Attention Auto-Encoders

2021-11-28 · IEEE Transactions on Knowledge and Data Engineering 2021 11 · Wei Wang, Xiaoyang Suo, Xiangyu Wei, Bin Wang 외

Graph auto-encoder is considered a framework for unsupervised learning on graph-structured data by representing graphs in a low dimensional space. It has been proved very powerful for graph analytics. In the real world, …

Graph Attention Graph Representation Learning Inductive Learning Link Prediction+3

Investigating Object Compositionality in Generative Adversarial Networks

2018-10-17 · ICLR 2019 5 · Sjoerd van Steenkiste, Karol Kurach, Jürgen Schmidhuber, Sylvain Gelly

Deep generative models seek to recover the process with which the observed data was generated. They may be used to synthesize new samples or to subsequently extract representations. Successful approaches in the domain of…

Image Generation Inductive Bias Instance Segmentation Object+3

Deep Graph Infomax

2018-09-27 · ICLR 2019 5 · Petar Veličković, William Fedus, William L. Hamilton, Pietro Liò 외

We present Deep Graph Infomax (DGI), a general approach for learning node representations within graph-structured data in an unsupervised manner. DGI relies on maximizing mutual information between patch representations …

General Classification Inductive Learning Node Classification

Unsupervised Joint k-node Graph Representations with Compositional Energy-Based Models

2020-12-01 · NeurIPS 2020 12 · Leonardo Cotta, Carlos H. C. Teixeira, Ananthram Swami, Bruno Ribeiro

Existing Graph Neural Network (GNN) methods that learn inductive unsupervised graph representations focus on learning node and edge representations by predicting observed edges in the graph. Although such approaches have…

Graph Neural Network Node Classification