Search Results for author:
Found 10 papers, 3 papers with code
KGTrust: Evaluating Trustworthiness of SIoT via Knowledge Enhanced Graph Neural Networks
Graph neural networks for trust evaluation typically adopt a straightforward way such as one-hot or node2vec to comprehend node characteristics, which ignores the valuable semantic knowledge attached to nodes.
One-shot Network Pruning at Initialization with Discriminative Image Patches
Recently, there is a growing belief that data is unnecessary in OPaI.
NodeTrans: A Graph Transfer Learning Approach for Traffic Prediction
First, a spatial-temporal graph neural network is proposed, which can capture the node-specific spatial-temporal traffic patterns of different road networks.
Soft-mask: Adaptive Substructure Extractions for Graph Neural Networks
Task-relevant structures can be $localized$ or $sparse$ which are only involved in subgraphs or characterized by the interactions of subgraphs (a hierarchical perspective).
A New Perspective on the Effects of Spectrum in Graph Neural Networks
Many improvements on GNNs can be deemed as operations on the spectrum of the underlying graph matrix, which motivates us to directly study the characteristics of the spectrum and their effects on GNN performance.
Ranked #1 on
Graph Regression
on ZINC-500k
Federated Unlearning via Class-Discriminative Pruning
Evaluated on CIFAR10 dataset, our method accelerates the speed of unlearning by 8. 9x for the ResNet model, and 7. 9x for the VGG model under no degradation in accuracy, compared to retraining from scratch.
Breaking the Expressive Bottlenecks of Graph Neural Networks
Recently, the Weisfeiler-Lehman (WL) graph isomorphism test was used to measure the expressiveness of graph neural networks (GNNs), showing that the neighborhood aggregation GNNs were at most as powerful as 1-WL test in distinguishing graph structures.
Ranked #1 on
Graph Property Prediction
on ogbg-ppa
Deep Learning on Traffic Prediction: Methods, Analysis and Future Directions
The purpose of this paper is to provide a comprehensive survey on deep learning-based approaches in traffic prediction from multiple perspectives.
An efficient deep learning hashing neural network for mobile visual search
Mobile visual search applications are emerging that enable users to sense their surroundings with smart phones.
Revisiting the Effectiveness of Off-the-shelf Temporal Modeling Approaches for Large-scale Video Classification
Experiment results on the challenging Kinetics dataset demonstrate that our proposed temporal modeling approaches can significantly improve existing approaches in the large-scale video recognition tasks.
Ranked #137 on
Action Classification
on Kinetics-400
