Influence-aware Causal Autoencoder Network for Node Importance Ranking in Complex Networks

2025-11-03

AI Summary

Existing node importance ranking models suffer from poor generalizability and privacy risks, as they rely heavily on the target network’s topology. Method: This paper proposes the first cross-network ranking framework that requires no access to the real target network structure. It introduces causal representation learning into graph ranking—specifically, an influence-aware causal representation module built upon an autoencoder, trained end-to-end on synthetic networks. A novel causal ranking loss jointly optimizes embedding invariance and ranking performance. Contributions/Results: Extensive experiments on multiple real-world networks demonstrate that our method significantly outperforms state-of-the-art baselines, achieving a 12.3% improvement in ranking accuracy (NDCG@10) and unprecedented cross-domain generalization. Crucially, it preserves the structural privacy of the target network while offering both interpretability and practical applicability.

Technology Category

• Machine Learning: Learning Preferences or Rankings
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Reasoning under Uncertainty: Causality

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Node importance ranking is a fundamental problem in graph data analysis. Existing approaches typically rely on node features derived from either traditional centrality measures or advanced graph representation learning methods, which depend directly on the target network's topology. However, this reliance on structural information raises privacy concerns and often leads to poor generalization across different networks. In this work, we address a key question: Can we design a node importance ranking model trained exclusively on synthetic networks that is effectively appliable to real-world networks, eliminating the need to rely on the topology of target networks and improving both practicality and generalizability? We answer this question affirmatively by proposing the Influence-aware Causal Autoencoder Network (ICAN), a novel framework that leverages causal representation learning to get robust, invariant node embeddings for cross-network ranking tasks. Firstly, ICAN introduces an influence-aware causal representation learning module within an autoencoder architecture to extract node embeddings that are causally related to node importance. Moreover, we introduce a causal ranking loss and design a unified optimization framework that jointly optimizes the reconstruction and ranking objectives, enabling mutual reinforcement between node representation learning and ranking optimization. This design allows ICAN, trained on synthetic networks, to generalize effectively across diverse real-world graphs. Extensive experiments on multiple benchmark datasets demonstrate that ICAN consistently outperforms state-of-the-art baselines in terms of both ranking accuracy and generalization capability.

Problem

• Develops cross-network node ranking without target network topology
• Uses causal representation learning for robust node embeddings
• Enables training on synthetic networks for real-world generalization

Innovation

• Uses causal autoencoder for robust cross-network node embeddings
• Introduces influence-aware causal representation learning module
• Unified optimization jointly trains reconstruction and ranking objectives