Differentiable Meta Multigraph Search with Partial Message Propagation on Heterogeneous Information Networks

11/27/2022
by   Chao Li, et al.
0

Heterogeneous information networks (HINs) are widely employed for describing real-world data with intricate entities and relationships. To automatically utilize their semantic information, graph neural architecture search has recently been developed on various tasks of HINs. Existing works, on the other hand, show weaknesses in instability and inflexibility. To address these issues, we propose a novel method called Partial Message Meta Multigraph search (PMMM) to automatically optimize the neural architecture design on HINs. Specifically, to learn how graph neural networks (GNNs) propagate messages along various types of edges, PMMM adopts an efficient differentiable framework to search for a meaningful meta multigraph, which can capture more flexible and complex semantic relations than a meta graph. The differentiable search typically suffers from performance instability, so we further propose a stable algorithm called partial message search to ensure that the searched meta multigraph consistently surpasses the manually designed meta-structures, i.e., meta-paths. Extensive experiments on six benchmark datasets over two representative tasks, including node classification and recommendation, demonstrate the effectiveness of the proposed method. Our approach outperforms the state-of-the-art heterogeneous GNNs, finds out meaningful meta multigraphs, and is significantly more stable.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/03/2021

Edge-featured Graph Neural Architecture Search

Graph neural networks (GNNs) have been successfully applied to learning ...
research
09/23/2022

Relation Embedding based Graph Neural Networks for Handling Heterogeneous Graph

Heterogeneous graph learning has drawn significant attentions in recent ...
research
02/21/2021

Genetic Meta-Structure Search for Recommendation on Heterogeneous Information Network

In the past decade, the heterogeneous information network (HIN) has beco...
research
07/16/2020

Self-supervised Auxiliary Learning with Meta-paths for Heterogeneous Graphs

Graph neural networks have shown superior performance in a wide range of...
research
05/18/2023

Seq-HGNN: Learning Sequential Node Representation on Heterogeneous Graph

Recent years have witnessed the rapid development of heterogeneous graph...
research
01/08/2023

AutoAC: Towards Automated Attribute Completion for Heterogeneous Graph Neural Network

Many real-world data can be modeled as heterogeneous graphs that contain...
research
09/07/2021

Hyper Meta-Path Contrastive Learning for Multi-Behavior Recommendation

User purchasing prediction with multi-behavior information remains a cha...

Please sign up or login with your details

Forgot password? Click here to reset