Graph structure learning

52 papers with code • 1 benchmarks • 2 datasets

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

Libraries

Use these libraries to find Graph structure learning models and implementations
3 papers
147

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.

Compact Graph Structure Learning via Mutual Information Compression

liun-online/cogsl 14 Jan 2022

Furthermore, we maintain the performance of estimated views and the final view and reduce the mutual information of every two views.

Detecting Multivariate Time Series Anomalies with Zero Known Label

zqhang/detecting-multivariate-time-series-anomalies-with-zero-known-label 3 Aug 2022

Multivariate time series anomaly detection has been extensively studied under the semi-supervised setting, where a training dataset with all normal instances is required.

DynDepNet: Learning Time-Varying Dependency Structures from fMRI Data via Dynamic Graph Structure Learning

Kaleidophon/deep-significance 27 Sep 2022

Graph neural networks (GNNs) have demonstrated success in learning representations of brain graphs derived from functional magnetic resonance imaging (fMRI) data.

A Tale of Two Graphs: Freezing and Denoising Graph Structures for Multimodal Recommendation

enoche/freedom 13 Nov 2022

Based on this finding, we propose a simple yet effective model, dubbed as FREEDOM, that FREEzes the item-item graph and DenOises the user-item interaction graph simultaneously for Multimodal recommendation.

SE-GSL: A General and Effective Graph Structure Learning Framework through Structural Entropy Optimization

ringbdstack/se-gsl 17 Mar 2023

Graph Neural Networks (GNNs) are de facto solutions to structural data learning.

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.