Deep Generative Models for Subgraph Prediction

2024-08-07 · Erfaneh Mahmoudzadeh, Parmis Naddaf, Kiarash Zahirnia, Oliver Schulte

Graph Neural Networks (GNNs) are important across different domains, such as social network analysis and recommendation systems, due to their ability to model complex relational data. This paper introduces subgraph queries as a new task for deep graph learning. Unlike traditional graph prediction tasks that focus on individual components like link prediction or node classification, subgraph queries jointly predict the components of a target subgraph based on evidence that is represented by an observed subgraph. For instance, a subgraph query can predict a set of target links and/or node labels. To answer subgraph queries, we utilize a probabilistic deep Graph Generative Model. Specifically, we inductively train a Variational Graph Auto-Encoder (VGAE) model, augmented to represent a joint distribution over links, node features and labels. Bayesian optimization is used to tune a weighting for the relative importance of links, node features and labels in a specific domain. We describe a deterministic and a sampling-based inference method for estimating subgraph probabilities from the VGAE generative graph distribution, without retraining, in zero-shot fashion. For evaluation, we apply the inference methods on a range of subgraph queries on six benchmark datasets. We find that inference from a model achieves superior predictive performance, surpassing independent prediction baselines with improvements in AUC scores ranging from 0.06 to 0.2 points, depending on the dataset.

📄 PDF Abstract BibTeX arXiv:2408.04053

Code (1)

erfmah/answering_graph_queries 공식 구현 pytorch

Tasks

Bayesian OptimizationGraph Learning Link Prediction Node Classification Prediction Recommendation Systems

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Focus 설명 없음

VGAE 설명 없음

Deconfounding to Explanation Evaluation in Graph Neural Networks

2022-01-21 · Ying-Xin Wu, Xiang Wang, An Zhang, Xia Hu 외

Explainability of graph neural networks (GNNs) aims to answer "Why the GNN made a certain prediction?", which is crucial to interpret the model prediction. The feature attribution framework distributes a GNN's prediction…

Prediction

Generative Graph Neural Networks for Link Prediction

2022-12-31 · Xingping Xian, Tao Wu, Xiaoke Ma, Shaojie Qiao 외

Inferring missing links or detecting spurious ones based on observed graphs, known as link prediction, is a long-standing challenge in graph data analysis. With the recent advances in deep learning, graph neural networks…

Link Prediction Prediction

Unbiased GNN Learning via Fairness-Aware Subgraph Diffusion

2024-12-31 · Abdullah Alchihabi, Yuhong Guo

Graph Neural Networks (GNNs) have demonstrated remarkable efficacy in tackling a wide array of graph-related tasks across diverse domains. However, a significant challenge lies in their propensity to generate biased pred…

Fairness

DAG Matters! GFlowNets Enhanced Explainer For Graph Neural Networks

2023-03-04 · Wenqian Li, Yinchuan Li, Zhigang Li, Jianye Hao 외

Uncovering rationales behind predictions of graph neural networks (GNNs) has received increasing attention over the years. Existing literature mainly focus on selecting a subgraph, through combinatorial optimization, to …

Combinatorial Optimization

Position-Aware Subgraph Neural Networks with Data-Efficient Learning

2022-11-01 · Chang Liu, Yuwen Yang, Zhe Xie, Hongtao Lu 외

Data-efficient learning on graphs (GEL) is essential in real-world applications. Existing GEL methods focus on learning useful representations for nodes, edges, or entire graphs with ``small'' labeled data. But the probl…

Contrastive Learning Position Representation Learning