34 papers with code ·
Graphs

We introduce the variational graph auto-encoder (VGAE), a framework for unsupervised learning on graph-structured data based on the variational auto-encoder (VAE).

#2 best model for Link Prediction on Pubmed (Accuracy metric)

Latent factor models for community detection aim to find a distributed and generally low-dimensional representation, or coding, that captures the structural regularity of network and reflects the community membership of nodes.

COMMUNITY DETECTION GRAPH CLUSTERING NETWORK EMBEDDING NODE CLASSIFICATION

Unlike NMF, however, SymNMF is based on a similarity measure between data points, and factorizes a symmetric matrix containing pairwise similarity values (not necessarily nonnegative).

This work considers the problem of computing distances between structured objects such as undirected graphs, seen as probability distributions in a specific metric space.

#2 best model for Graph Classification on ENZYMES

Furthermore, Cluster-GCN allows us to train much deeper GCN without much time and memory overhead, which leads to improved prediction accuracy---using a 5-layer Cluster-GCN, we achieve state-of-the-art test F1 score 99. 36 on the PPI dataset, while the previous best result was 98. 71 by [16].

SOTA for Node Classification on Amazon2M

Graph embedding is an effective method to represent graph data in a low dimensional space for graph analytics.

#4 best model for Link Prediction on Pubmed

In this paper, we are interested to design neural networks for graphs with variable length in order to solve learning problems such as vertex classification, graph classification, graph regression, and graph generative tasks.

We have tested the effectiveness of GRAPH-BERT on several graph benchmark datasets.

#12 best model for Node Classification on Cora

Local graph clustering and the closely related seed set expansion problem are primitives on graphs that are central to a wide range of analytic and learning tasks such as local clustering, community detection, nodes ranking and feature inference.

Possible reasons for this are: the steep learning curve for these algorithms; the lack of efficient and easy to use software; and the lack of detailed numerical experiments on real-world data that demonstrate their usefulness.