GOLD: Graph Out-of-Distribution Detection via Implicit Adversarial Latent Generation

2025-02-09

AI Summary

Graph Neural Networks (GNNs) face significant challenges in out-of-distribution (OOD) node detection, including the scarcity of authentic OOD samples and the difficulty of obtaining pre-trained generative models. To address these issues, we propose GOLD, the first implicit adversarial learning framework that requires neither real OOD samples nor external pre-trained generators. GOLD jointly optimizes a generator and a GNN in latent space to dynamically synthesize pseudo-OOD embeddings, while leveraging energy-based contrastive learning for robust OOD discrimination. This end-to-end paradigm eliminates reliance on explicit OOD data or external generative models. Evaluated on five benchmark graph datasets under a zero-real-OOD-sample setting, GOLD consistently outperforms both OOD-exposed and OOD-unexposed state-of-the-art methods, achieving new SOTA performance in OOD detection.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Data Mining & Knowledge Management: Anomaly/Outlier Detection

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Despite graph neural networks' (GNNs) great success in modelling graph-structured data, out-of-distribution (OOD) test instances still pose a great challenge for current GNNs. One of the most effective techniques to detect OOD nodes is to expose the detector model with an additional OOD node-set, yet the extra OOD instances are often difficult to obtain in practice. Recent methods for image data address this problem using OOD data synthesis, typically relying on pre-trained generative models like Stable Diffusion. However, these approaches require vast amounts of additional data, as well as one-for-all pre-trained generative models, which are not available for graph data. Therefore, we propose the GOLD framework for graph OOD detection, an implicit adversarial learning pipeline with synthetic OOD exposure without pre-trained models. The implicit adversarial training process employs a novel alternating optimisation framework by training: (1) a latent generative model to regularly imitate the in-distribution (ID) embeddings from an evolving GNN, and (2) a GNN encoder and an OOD detector to accurately classify ID data while increasing the energy divergence between the ID embeddings and the generative model's synthetic embeddings. This novel approach implicitly transforms the synthetic embeddings into pseudo-OOD instances relative to the ID data, effectively simulating exposure to OOD scenarios without auxiliary data. Extensive OOD detection experiments are conducted on five benchmark graph datasets, verifying the superior performance of GOLD without using real OOD data compared with the state-of-the-art OOD exposure and non-exposure baselines.

Problem

• Detects OOD nodes in graph neural networks
• Uses implicit adversarial learning for synthetic OOD
• Eliminates need for pre-trained generative models

Innovation

• Implicit adversarial learning pipeline
• Alternating optimization framework
• Synthetic OOD exposure simulation