Graph Representation Learning

Attentive Walk-Aggregating Graph Neural Network

We propose to theoretically and empirically examine the effect of incorporating weighting schemes into walk-aggregating GNNs. To this end, we propose a simple, interpretable, and end-to-end supervised GNN model, called AWARE (Attentive Walk-Aggregating GRaph Neural NEtwork), for graph-level prediction. AWARE aggregates the walk information by means of weighting schemes at distinct levels (vertex-, walk-, and graph-level) in a principled manner. By virtue of the incorporated weighting schemes at these different levels, AWARE can emphasize the information important for prediction while diminishing the irrelevant ones—leading to representations that can improve learning performance.

Papers


Paper Code Results Date Stars

Tasks


Task Papers Share
Semantic Segmentation 33 4.51%
Quantization 23 3.15%
Federated Learning 19 2.60%
Object Detection 17 2.33%
Retrieval 16 2.19%
Language Modelling 16 2.19%
Autonomous Driving 16 2.19%
Fairness 12 1.64%
Classification 12 1.64%

Components


Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign

Categories