← Core Methods
Machine Learning › Core Methods ›

Graph Neural Networks

1127 directly classified papers

Papers per year

Papers

Unsupervised Joint k-node Graph Representations with Compositional Energy-Based Models NIPS 2020
SAC: Accelerating and Structuring Self-Attention via Sparse Adaptive Connection NIPS 2020
Path Integral Based Convolution and Pooling for Graph Neural Networks NIPS 2020
Tensor Graph Convolutional Networks for Text Classification AAAI 2020
Syntax-aware Multi-task Graph Convolutional Networks for Biomedical Relation Extraction EMNLP 2019
Bayesian Graph Convolutional Neural Networks for Semi-Supervised Classification AAAI 2019
Geometric Hawkes Processes with Graph Convolutional Recurrent Neural Networks AAAI 2019
GeniePath: Graph Neural Networks with Adaptive Receptive Paths AAAI 2019
Gaussian-Induced Convolution for Graphs AAAI 2019
Robust Negative Sampling for Network Embedding AAAI 2019
Supervised User Ranking in Signed Social Networks AAAI 2019
Joint Type Inference on Entities and Relations via Graph Convolutional Networks ACL 2019
Inter-sentence Relation Extraction with Document-level Graph Convolutional Neural Network ACL 2019
Improving Textual Network Embedding with Global Attention via Optimal Transport ACL 2019
Random Walks on Hypergraphs with Edge-Dependent Vertex Weights ICML 2019
Structural Relational Reasoning of Point Clouds CVPR 2019
Heterogeneous Graph Attention Networks for Semi-supervised Short Text Classification EMNLP 2019
Aspect-based Sentiment Classification with Aspect-specific Graph Convolutional Networks EMNLP 2019
NumNet: Machine Reading Comprehension with Numerical Reasoning EMNLP 2019
Neural Conversation Recommendation with Online Interaction Modeling EMNLP 2019
Connecting the Dots: Document-level Neural Relation Extraction with Edge-oriented Graphs EMNLP 2019
Enhancing Dialogue Symptom Diagnosis with Global Attention and Symptom Graph EMNLP 2019
Dense Node Representation for Geolocation EMNLP 2019
Robust Graph Embedding with Noisy Link Weights AISTATS 2019
Connecting the Dots: Document-level Neural Relation Extraction with Edge-oriented Graphs IJCNLP 2019