Graph Star Net for Generalized Multi-Task Learning

2019-06-21 · Lu Haonan, Seth H. Huang, Tian Ye, Guo Xiuyan

In this work, we present graph star net (GraphStar), a novel and unified graph neural net architecture which utilizes message-passing relay and attention mechanism for multiple prediction tasks - node classification, graph classification and link prediction. GraphStar addresses many earlier challenges facing graph neural nets and achieves non-local representation without increasing the model depth or bearing heavy computational costs. We also propose a new method to tackle topic-specific sentiment analysis based on node classification and text classification as graph classification. Our work shows that 'star nodes' can learn effective graph-data representation and improve on current methods for the three tasks. Specifically, for graph classification and link prediction, GraphStar outperforms the current state-of-the-art models by 2-5% on several key benchmarks.

📄 PDF Abstract BibTeX arXiv:1906.12330

Code (1)

graph-star-team/graph_star pytorch

Tasks

Classification General Classification Graph Classification Link Prediction Multi-Task Learning Node Classification Prediction Sentiment Analysis text-classification Text Classification

On the Complexity of Connection Games

2016-05-16 · Édouard Bonnet, Florian Jamain, Abdallah Saffidine

In this paper, we study three connection games among the most widely played: Havannah, Twixt, and Slither. We show that determining the outcome of an arbitrary input position is PSPACE-complete in all three cases. Our re…

Position

Multi-Task Feature Learning for Knowledge Graph Enhanced Recommendation

2019-01-23 · Hongwei Wang, Fuzheng Zhang, Miao Zhao, Wenjie Li 외

Collaborative filtering often suffers from sparsity and cold start problems in real recommendation scenarios, therefore, researchers and engineers usually use side information to address the issues and improve the perfor…

Collaborative Filtering Graph Embedding Knowledge Graph Embedding Knowledge Graphs+3

Learning the hub graphical Lasso model with the structured sparsity via an efficient algorithm

2023-08-17 · Chengjing Wang, Peipei Tang, Wenling He, Meixia Lin

Graphical models have exhibited their performance in numerous tasks ranging from biological analysis to recommender systems. However, graphical models with hub nodes are computationally difficult to fit, particularly whe…

Recommendation Systems

Federated Learning on Non-IID Graphs via Structural Knowledge Sharing

2022-11-23 · Yue Tan, Yixin Liu, Guodong Long, Jing Jiang 외

Graph neural networks (GNNs) have shown their superiority in modeling graph data. Owing to the advantages of federated learning, federated graph learning (FGL) enables clients to train strong GNN models in a distributed …

Federated Learning Graph Learning

Black Start Operation of Grid-Forming Converters Based on Generalized Three-phase Droop Control Under Unbalanced Conditions

2024-05-23 · Zexian Zeng, Prajwal Bhagwat, Maryam Saeedifard, Dominic Groß

This paper focuses on the challenging task of bottom-up restoration in a complete blackout system using Grid-forming (GFM) converters. Challenges arise due to the limited current capability of power converters, resulting…