TAS-EGNN: Task-Aware Spectral Ego-Graphs for Efficient GNNs-Based Classification

Mebarka Allaoui, Rachid Hedjam, Sonia Gupta
Proceedings of The 29th International Conference on Artificial Intelligence and Statistics, PMLR 300:109-117, 2026.

Abstract

Graph Neural Networks (GNNs) achieve strong accuracy but remain costly to train on large graphs and in resource-constrained settings. Coreset selection mitigates this by training on a compact, representative node subset, yet many existing methods rely on expensive spectral routines or bilevel and iterative optimizations. We propose a Task-Aware Spectral Ego-Graph Neural Network (TAS-EGNN) that scores nodes within lightweight ego-graphs by combining (i) local spectral complexity, (ii) predictive uncertainty, and (iii) supervised error signals, followed by a greedy coverage step to avoid redundancy. TAS-EGNN circumvents heavy optimization, using only local spectra (or moment proxies) and a single model forward pass to obtain task signals. We evaluate TAS-EGNN across three benchmark tasks: citation networks, social networks, and graph-based bank transaction fraud detection. The third task, in particular, underscores the algorithm’s effectiveness in anomaly detection for highly imbalanced settings. TAS-EGNN matches or surpasses state-of-the-art reduction baselines, across \emph{budgets} (i.e., the allowed size of the selected training subset, controlled via the coreset ratio), including condensation, coarsening, and ego-graph selection, while delivering substantial wall-clock and peak-memory savings. Time and memory profiling show that TAS-EGNN tracks the lower envelope among structure-aware methods and scales to large graphs, whereas several other works reach OOT/OOM. These results indicate that efficiently encoded task-aware structural priors enable robust, scalable coreset selection for both standard node classification and fraud detection. The source code will be available on GitHub.

Cite this Paper

BibTeX
@InProceedings{pmlr-v300-allaoui26a, title = { TAS-EGNN: Task-Aware Spectral Ego-Graphs for Efficient GNNs-Based Classification }, author = {Allaoui, Mebarka and Hedjam, Rachid and Gupta, Sonia}, booktitle = {Proceedings of The 29th International Conference on Artificial Intelligence and Statistics}, pages = {109--117}, year = {2026}, editor = {Khan, Emtiyaz and Li, Yingzhen and Solin, Arno and Ramdas, Aaditya}, volume = {300}, series = {Proceedings of Machine Learning Research}, month = {02--05 May}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v300/main/assets/allaoui26a/allaoui26a.pdf}, url = {https://proceedings.mlr.press/v300/allaoui26a.html}, abstract = { Graph Neural Networks (GNNs) achieve strong accuracy but remain costly to train on large graphs and in resource-constrained settings. Coreset selection mitigates this by training on a compact, representative node subset, yet many existing methods rely on expensive spectral routines or bilevel and iterative optimizations. We propose a Task-Aware Spectral Ego-Graph Neural Network (TAS-EGNN) that scores nodes within lightweight ego-graphs by combining (i) local spectral complexity, (ii) predictive uncertainty, and (iii) supervised error signals, followed by a greedy coverage step to avoid redundancy. TAS-EGNN circumvents heavy optimization, using only local spectra (or moment proxies) and a single model forward pass to obtain task signals. We evaluate TAS-EGNN across three benchmark tasks: citation networks, social networks, and graph-based bank transaction fraud detection. The third task, in particular, underscores the algorithm’s effectiveness in anomaly detection for highly imbalanced settings. TAS-EGNN matches or surpasses state-of-the-art reduction baselines, across \emph{budgets} (i.e., the allowed size of the selected training subset, controlled via the coreset ratio), including condensation, coarsening, and ego-graph selection, while delivering substantial wall-clock and peak-memory savings. Time and memory profiling show that TAS-EGNN tracks the lower envelope among structure-aware methods and scales to large graphs, whereas several other works reach OOT/OOM. These results indicate that efficiently encoded task-aware structural priors enable robust, scalable coreset selection for both standard node classification and fraud detection. The source code will be available on GitHub. } }
Endnote
%0 Conference Paper %T TAS-EGNN: Task-Aware Spectral Ego-Graphs for Efficient GNNs-Based Classification %A Mebarka Allaoui %A Rachid Hedjam %A Sonia Gupta %B Proceedings of The 29th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2026 %E Emtiyaz Khan %E Yingzhen Li %E Arno Solin %E Aaditya Ramdas %F pmlr-v300-allaoui26a %I PMLR %P 109--117 %U https://proceedings.mlr.press/v300/allaoui26a.html %V 300 %X Graph Neural Networks (GNNs) achieve strong accuracy but remain costly to train on large graphs and in resource-constrained settings. Coreset selection mitigates this by training on a compact, representative node subset, yet many existing methods rely on expensive spectral routines or bilevel and iterative optimizations. We propose a Task-Aware Spectral Ego-Graph Neural Network (TAS-EGNN) that scores nodes within lightweight ego-graphs by combining (i) local spectral complexity, (ii) predictive uncertainty, and (iii) supervised error signals, followed by a greedy coverage step to avoid redundancy. TAS-EGNN circumvents heavy optimization, using only local spectra (or moment proxies) and a single model forward pass to obtain task signals. We evaluate TAS-EGNN across three benchmark tasks: citation networks, social networks, and graph-based bank transaction fraud detection. The third task, in particular, underscores the algorithm’s effectiveness in anomaly detection for highly imbalanced settings. TAS-EGNN matches or surpasses state-of-the-art reduction baselines, across \emph{budgets} (i.e., the allowed size of the selected training subset, controlled via the coreset ratio), including condensation, coarsening, and ego-graph selection, while delivering substantial wall-clock and peak-memory savings. Time and memory profiling show that TAS-EGNN tracks the lower envelope among structure-aware methods and scales to large graphs, whereas several other works reach OOT/OOM. These results indicate that efficiently encoded task-aware structural priors enable robust, scalable coreset selection for both standard node classification and fraud detection. The source code will be available on GitHub.
APA
Allaoui, M., Hedjam, R. & Gupta, S.. (2026). TAS-EGNN: Task-Aware Spectral Ego-Graphs for Efficient GNNs-Based Classification . Proceedings of The 29th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 300:109-117 Available from https://proceedings.mlr.press/v300/allaoui26a.html.

Related Material