Graph structure learning

37 papers with code • 1 benchmarks • 2 datasets

Semi-supervised node classification when a graph structure is not available.

Most implemented papers

Graph Structure Learning for Robust Graph Neural Networks

DSE-MSU/DeepRobust 20 May 2020

A natural idea to defend adversarial attacks is to clean the perturbed graph.

Graph-Bert: Only Attention is Needed for Learning Graph Representations

jwzhanggy/Graph-Bert 15 Jan 2020

We have tested the effectiveness of GRAPH-BERT on several graph benchmark datasets.

DBGSL: Dynamic Brain Graph Structure Learning

Kaleidophon/deep-significance 27 Sep 2022

Recently, graph neural networks (GNNs) have shown success at learning representations of brain graphs derived from functional magnetic resonance imaging (fMRI) data.

GraphFlow: Exploiting Conversation Flow with Graph Neural Networks for Conversational Machine Comprehension

hugochan/GraphFlow 31 Jul 2019

The proposed GraphFlow model can effectively capture conversational flow in a dialog, and shows competitive performance compared to existing state-of-the-art methods on CoQA, QuAC and DoQA benchmarks.

Variationally Regularized Graph-based Representation Learning for Electronic Health Records

NYUMedML/GNN_for_EHR 8 Dec 2019

A feasible approach to improving the representation learning of EHR data is to associate relevant medical concepts and utilize these connections.

Deep Iterative and Adaptive Learning for Graph Neural Networks

hugochan/IDGL 17 Dec 2019

In this paper, we propose an end-to-end graph learning framework, namely Deep Iterative and Adaptive Learning for Graph Neural Networks (DIAL-GNN), for jointly learning the graph structure and graph embeddings simultaneously.

Reasoning Visual Dialog with Sparse Graph Learning and Knowledge Transfer

gicheonkang/sglkt-visdial Findings (EMNLP) 2021

Visual dialog is a task of answering a sequence of questions grounded in an image using the previous dialog history as context.

Node Classification on Graphs with Few-Shot Novel Labels via Meta Transformed Network Embedding

llan-ml/MetaTNE NeurIPS 2020

We study the problem of node classification on graphs with few-shot novel labels, which has two distinctive properties: (1) There are novel labels to emerge in the graph; (2) The novel labels have only a few representative nodes for training a classifier.

Learning Attribute-Structure Co-Evolutions in Dynamic Graphs

DM2-ND/CoEvoGNN 25 Jul 2020

In this work, we present a novel framework called CoEvoGNN for modeling dynamic attributed graph sequence.

Dynamic Structure Learning through Graph Neural Network for Forecasting Soil Moisture in Precision Agriculture

anoushkavyas/dglr 7 Dec 2020

Soil moisture is an important component of precision agriculture as it directly impacts the growth and quality of vegetation.