Evolutionary Router Feature Generation for Zero-Shot Graph Anomaly Detection with Mixture-of-Experts

2026-02-12

AI Summary

Existing single-graph neural network (GNN) approaches struggle to handle the heterogeneity in graph structure, node features, and anomaly patterns, while conventional Mixture-of-Experts (MoE) architectures suffer from distributional shifts in zero-shot graph anomaly detection, leading to routing bias and poor generalization. To address these challenges, this work proposes a novel MoE framework featuring evolution-based routing with feature generation. It pioneers the integration of large language models (LLMs) and iterative Shapley value computation to generate and evaluate structure-aware features, and introduces a memory-augmented router optimized via a domain-invariant learning objective to refine expert assignment. Extensive experiments on six benchmark datasets demonstrate that the proposed method significantly outperforms current state-of-the-art approaches, achieving stable and robust performance in zero-shot graph anomaly detection.

Technology Category

• Machine Learning: Mixture of Experts (MoE)
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Models for Web evolution

Abstract

Zero-shot graph anomaly detection (GAD) has attracted increasing attention recent years, yet the heterogeneity of graph structures, features, and anomaly patterns across graphs make existing single GNN methods insufficiently expressive to model diverse anomaly mechanisms. In this regard, Mixture-of-experts (MoE) architectures provide a promising paradigm by integrating diverse GNN experts with complementary inductive biases, yet their effectiveness in zero-shot GAD is severely constrained by distribution shifts, leading to two key routing challenges. First, nodes often carry vastly different semantics across graphs, and straightforwardly performing routing based on their features is prone to generating biased or suboptimal expert assignments. Second, as anomalous graphs often exhibit pronounced distributional discrepancies, existing router designs fall short in capturing domain-invariant routing principles that generalize beyond the training graphs. To address these challenges, we propose a novel MoE framework with evolutionary router feature generation (EvoFG) for zero-shot GAD. To enhance MoE routing, we propose an evolutionary feature generation scheme that iteratively constructs and selects informative structural features via an LLM-based generator and Shapley-guided evaluation. Moreover, a memory-enhanced router with an invariant learning objective is designed to capture transferable routing patterns under distribution shifts. Extensive experiments on six benchmarks show that EvoFG consistently outperforms state-of-the-art baselines, achieving strong and stable zero-shot GAD performance.

Problem

• zero-shot graph anomaly detection
• Mixture-of-Experts
• distribution shift
• graph heterogeneity
• routing challenge

Innovation

• Evolutionary Feature Generation
• Mixture-of-Experts
• Zero-Shot Graph Anomaly Detection
• Invariant Routing
• LLM-based Feature Construction