paper-with-me

홈 › Papers

Models and Benchmarks for Representation Learning of Partially Observed Subgraphs

2022-09-01 · Dongkwan Kim, Jiho Jin, Jaimeen Ahn, Alice Oh

Subgraphs are rich substructures in graphs, and their nodes and edges can be partially observed in real-world tasks. Under partial observation, existing node- or subgraph-level message-passing produces suboptimal representations. In this paper, we formulate a novel task of learning representations of partially observed subgraphs. To solve this problem, we propose Partial Subgraph InfoMax (PSI) framework and generalize existing InfoMax models, including DGI, InfoGraph, MVGRL, and GraphCL, into our framework. These models maximize the mutual information between the partial subgraph's summary and various substructures from nodes to full subgraphs. In addition, we suggest a novel two-stage model with $k$-hop PSI, which reconstructs the representation of the full subgraph and improves its expressiveness from different local-global structures. Under training and evaluation protocols designed for this problem, we conduct experiments on three real-world datasets and demonstrate that PSI models outperform baselines.

📄 PDF Abstract BibTeX arXiv:2209.00508

Code (1)

dongkwan-kim/psi 공식 구현 pytorch

Tasks

Representation Learning

Methods 이 논문이 사용한 방법론

InfoGraph 설명 없음
GraphCL 설명 없음
DGI 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…

Similar Papers 제목 키워드 기반

Graphon Estimation from Partially Observed Network Data

2019-06-02 · Soumendu Sundar Mukherjee, Sayak Chakrabarti

We consider estimating the edge-probability matrix of a network generated from a graphon model when the full network is not observed---only some overlapping subgraphs are. We extend the neighbourhood smoothing (NBS) algo…

Graphon EstimationMatrix Completion

Leveraging Graph Diffusion Models for Network Refinement Tasks

2023-11-29 · Puja Trivedi, Ryan Rossi, David Arbour, Tong Yu 외

Most real-world networks are noisy and incomplete samples from an unknown target distribution. Refining them by correcting corruptions or inferring unobserved regions typically improves downstream performance. Inspired b…

DenoisingStyle Transfer

Translating Subgraphs to Nodes Makes Simple GNNs Strong and Efficient for Subgraph Representation Learning

2022-04-09 · Dongkwan Kim, Alice Oh

Subgraph representation learning has emerged as an important problem, but it is by default approached with specialized graph neural networks on a large global graph. These models demand extensive memory and computational…

Representation LearningTranslation

Learning Graph Representation by Aggregating Subgraphs via Mutual Information Maximization

2021-03-24 · Chenguang Wang, Ziwen Liu

In this paper, we introduce a self-supervised learning method to enhance the graph-level representations with the help of a set of subgraphs. For this purpose, we propose a universal framework to generate subgraphs in an…

AttributeContrastive LearningGraph Representation LearningRepresentation Learning+1

Soft-mask: Adaptive Substructure Extractions for Graph Neural Networks

2022-06-11 · Mingqi Yang, Yanming Shen, Heng Qi, BaoCai Yin

For learning graph representations, not all detailed structures within a graph are relevant to the given graph tasks. Task-relevant structures can be $localized$ or $sparse$ which are only involved in subgraphs or charac…

Graph Neural NetworkRepresentation Learning