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.


Paper Code Results Date Stars


Task Papers Share
Language Modelling 22 3.12%
Semantic Segmentation 21 2.97%
Federated Learning 18 2.55%
Quantization 17 2.41%
Object Detection 14 1.98%
Sentence 12 1.70%
Retrieval 12 1.70%
Speech Recognition 12 1.70%
Decision Making 11 1.56%


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