16 papers with code ·
Graphs

Second, for each pair of graphs, we train a cross-graph attention network which uses the node representations of an anchor graph to reconstruct another graph.

Ranked #2 on Graph Classification on D&D

Our model achieves better generalization on unseen graphs, and in the worst case runs in quadratic time with respect to the number of nodes in two graphs.

Ranked #1 on Graph Similarity on IMDb

Evaluating similarity between graphs is of major importance in several computer vision and pattern recognition problems, where graph representations are often used to model objects or interactions between elements.

However, existing graph-based methods either are limited in their ability to jointly model graph structures and data features, such as the classical label propagation methods, or require a considerable amount of labeled data for training and validation due to high model complexity, such as the recent neural-network-based methods.

Graph kernels are kernel methods measuring graph similarity and serve as a standard tool for graph classification.

GRAPH CLASSIFICATION GRAPH REPRESENTATION LEARNING GRAPH SIMILARITY NODE CLASSIFICATION

Graph kernels are kernel methods measuring graph similarity and serve as a standard tool for graph classification.

Ranked #4 on Link Prediction on Cora

GRAPH CLASSIFICATION GRAPH REPRESENTATION LEARNING GRAPH SIMILARITY NODE CLASSIFICATION

In this work we consider a privacy threat to a social network in which an attacker has access to a subset of random walk-based node similarities, such as effective resistances (i. e., commute times) or personalized PageRank scores.

We introduce a novel approach to graph-level representation learning, which is to embed an entire graph into a vector space where the embeddings of two graphs preserve their graph-graph proximity.

Ranked #1 on Graph Classification on Web

The first component is a kernel between vertices, while the second component is a kernel between graphs.