SIAILGSep 28, 2025

Node Classification via Simplicial Interaction with Augmented Maximal Clique Selection

arXiv:2509.23568v1h-index: 7Neurocomputing
Originality Incremental advance
AI Analysis

This work addresses computational challenges in network analysis for researchers and practitioners, though it is incremental as it builds on existing clique-based methods.

The paper tackles the problem of computational inefficiency and imbalanced training in higher-order network learning by proposing an augmented maximal clique strategy, which outperforms existing methods on synthetic and real-world datasets and improves predictive accuracy when integrated into GNN-based semi-supervised learning.

Considering higher-order interactions allows for a more comprehensive understanding of network structures beyond simple pairwise connections. While leveraging all cliques in a network to handle higher-order interactions is intuitive, it often leads to computational inefficiencies due to overlapping information between higher-order and lower-order cliques. To address this issue, we propose an augmented maximal clique strategy. Although using only maximal cliques can reduce unnecessary overlap and provide a concise representation of the network, certain nodes may still appear in multiple maximal cliques, resulting in imbalanced training data. Therefore, our augmented maximal clique approach selectively includes some non-maximal cliques to mitigate the overrepresentation of specific nodes and promote more balanced learning across the network. Comparative analyses on synthetic networks and real-world citation datasets demonstrate that our method outperforms approaches based on pairwise interactions, all cliques, or only maximal cliques. Finally, by integrating this strategy into GNN-based semi-supervised learning, we establish a link between maximal clique-based methods and GNNs, showing that incorporating higher-order structures improves predictive accuracy. As a result, the augmented maximal clique strategy offers a computationally efficient and effective solution for higher-order network learning.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes