Explaining Temporal Graph Neural Networks via Feature-induced Information Flow

• URL: http://arxiv.org/abs/2606.27201v1
• Date: Thu, 25 Jun 2026 16:00:11 GMT
• Title: Explaining Temporal Graph Neural Networks via Feature-induced Information Flow
• Abstract summary: Event-based Temporal Graph Neural Networks (ETGNNs) have demonstrated strong performance across a wide range of applications.<n>We propose a novel attribution method that analyzes the emphentire information flow through all event-associated variables.<n>We evaluate our approach on two synthetic datasets for epidemic tracing and social dynamics, as well as a real-world dataset of political event networks.
• Score: 20.91154042249583
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Event-based Temporal Graph Neural Networks (ETGNNs) have demonstrated strong performance across a wide range of applications, including social network analysis, epidemic tracing, recommender systems, and political event forecasting. However, their increasing complexity poses significant challenges for explainability. Existing explanation methods focus only on a subset of the information flow within ETGNNs, typically tracing contributions from the event-related embeddings to the output. Consequently, they overlook the important pathways through event-induced variables, which mediate interactions between nodes and thereby play a central role in capturing long-range temporal dependencies. To overcome this limitation, we propose a novel attribution method that analyzes the \emph{entire} information flow through all event-associated variables. Our method is built upon the recent Normalized Relevance Measure (NRM) framework, which enables explicit quantification of information flow originating from event embeddings as well as information flow passing through event-induced variables. It also ensures comparability of latent variables across layers, and supports higher-order analysis of interactions between events. To handle the architectural complexity of ETGNNs, we extend the NRM framework with a modular decomposition procedure that facilitates the systematic construction of relevance structure for complex neural architectures. We evaluate our approach on two synthetic datasets for epidemic tracing and social dynamics, as well as a real-world dataset of political event networks. Our qualitative and quantitative experiments show that our method consistently outperforms existing explanation approaches while producing more human-interpretable explanations.

Related papers

• Learning Structural Convergence: A Neuro-Symbolic Benchmark for Temporal Reasoning [2.7644691581661287]
  This paper introduces TRACTA, a benchmark for temporal structural reasoning in high-complexity event-driven systems.<n>The benchmark includes three tasks: early_warning, pattern_detection, and run_classification.<n>Results show that raw event-level learning remains informative, but learned temporal modeling over semantic capability achieves the highest aggregate point estimates.
  arXiv  Detail & Related papers  (2026-07-24T14:50:19Z)
• Structured Neural Marked Point Processes for Interpretable Event Interaction Modeling [12.453735847515006]
  Multi-class event streams arise in numerous real-world applications, where uncovering structured, interpretable inter-event relationships, together with accurate prediction, remains a central challenge.<n>Existing neural point process models are highly expressive but encode event interactions in a black-box manner, preventing explicit discovery of structured dependencies.<n>We propose a structured neural marked point process (SNMPP) that achieves high modeling flexibility while enabling explicit event-wise and class-wise relationship discovery from data.
  arXiv  Detail & Related papers  (2026-05-17T17:56:22Z)
• Time Series Analysis of Spiking Neural Systems via Transfer Entropy and Directed Persistent Homology [0.0]
  We present a framework for analysing neural time series that integrates Transfer Entropy (TE) with Persistent Homology (PH)<n>TE quantifies directional influence between neurons, producing weighted, directed graphs that reflect dynamic interactions.<n>We apply this framework to synthetic spiking networks trained on logic gate tasks, image-classification networks exposed to structured and perturbed inputs, and mouse cortical recordings annotated with behavioral events.
  arXiv  Detail & Related papers  (2025-08-26T14:01:53Z)
• XG-NID: Dual-Modality Network Intrusion Detection using a Heterogeneous Graph Neural Network and Large Language Model [5.298018090482744]
  "XG-NID" is the first to fuse flow-level and packet-level data within a heterogeneous graph structure.<n>XG-NID uniquely enables real-time inference while effectively capturing the intricate relationships between flow and packet payload data.
  arXiv  Detail & Related papers  (2024-08-27T01:14:34Z)
• SFANet: Spatial-Frequency Attention Network for Weather Forecasting [54.470205739015434]
  Weather forecasting plays a critical role in various sectors, driving decision-making and risk management. Traditional methods often struggle to capture the complex dynamics of meteorological systems. We propose a novel framework designed to address these challenges and enhance the accuracy of weather prediction.
  arXiv  Detail & Related papers  (2024-05-29T08:00:15Z)
• Amortized Network Intervention to Steer the Excitatory Point Processes [8.15558505134853]
  Excitatory point processes (i.e., event flows) occurring over dynamic graphs provide a fine-grained model to capture how discrete events may spread over time and space. How to effectively steer the event flows by modifying the dynamic graph structures presents an interesting problem, motivated by curbing the spread of infectious diseases. We design an Amortized Network Interventions framework, allowing for the pooling of optimal policies from history and other contexts.
  arXiv  Detail & Related papers  (2023-10-06T11:17:28Z)
• Over-Squashing in Graph Neural Networks: A Comprehensive survey [0.0]
  This survey delves into the challenge of over-squashing in Graph Neural Networks (GNNs)<n>It comprehensively explores the causes, consequences, and mitigation strategies for over-squashing.<n>Various methodologies are reviewed, including graph rewiring, novel normalization, spectral analysis, and curvature-based strategies.<n>The survey also discusses the interplay between over-squashing and other GNN limitations, such as over-smoothing.
  arXiv  Detail & Related papers  (2023-08-29T18:46:15Z)
• Contextualizing MLP-Mixers Spatiotemporally for Urban Data Forecast at Scale [54.15522908057831]
  We propose an adapted version of the computationally-Mixer for STTD forecast at scale. Our results surprisingly show that this simple-yeteffective solution can rival SOTA baselines when tested on several traffic benchmarks. Our findings contribute to the exploration of simple-yet-effective models for real-world STTD forecasting.
  arXiv  Detail & Related papers  (2023-07-04T05:19:19Z)
• Deep Architecture Connectivity Matters for Its Convergence: A Fine-Grained Analysis [94.64007376939735]
  We theoretically characterize the impact of connectivity patterns on the convergence of deep neural networks (DNNs) under gradient descent training. We show that by a simple filtration on "unpromising" connectivity patterns, we can trim down the number of models to evaluate.
  arXiv  Detail & Related papers  (2022-05-11T17:43:54Z)
• Learning Neural Causal Models with Active Interventions [83.44636110899742]
  We introduce an active intervention-targeting mechanism which enables a quick identification of the underlying causal structure of the data-generating process. Our method significantly reduces the required number of interactions compared with random intervention targeting. We demonstrate superior performance on multiple benchmarks from simulated to real-world data.
  arXiv  Detail & Related papers  (2021-09-06T13:10:37Z)
• Influence Estimation and Maximization via Neural Mean-Field Dynamics [60.91291234832546]
  We propose a novel learning framework using neural mean-field (NMF) dynamics for inference and estimation problems. Our framework can simultaneously learn the structure of the diffusion network and the evolution of node infection probabilities.
  arXiv  Detail & Related papers  (2021-06-03T00:02:05Z)
• Inter-layer Information Similarity Assessment of Deep Neural Networks Via Topological Similarity and Persistence Analysis of Data Neighbour Dynamics [93.4221402881609]
  The quantitative analysis of information structure through a deep neural network (DNN) can unveil new insights into the theoretical performance of DNN architectures. Inspired by both LS and ID strategies for quantitative information structure analysis, we introduce two novel complimentary methods for inter-layer information similarity assessment. We demonstrate their efficacy in this study by performing analysis on a deep convolutional neural network architecture on image data.
  arXiv  Detail & Related papers  (2020-12-07T15:34:58Z)
• Network Diffusions via Neural Mean-Field Dynamics [52.091487866968286]
  We propose a novel learning framework for inference and estimation problems of diffusion on networks. Our framework is derived from the Mori-Zwanzig formalism to obtain an exact evolution of the node infection probabilities. Our approach is versatile and robust to variations of the underlying diffusion network models.
  arXiv  Detail & Related papers  (2020-06-16T18:45:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.