Explainable AI for analyzing the decision of GNNs at predicting dynamic stability of complex oscillator networks.
Sign Up to like & getrecommendations! Published in 2025 at "Chaos"
DOI: 10.1063/5.0278469
Abstract: Understanding the synchronization of complex oscillator networks is a central question in complex systems research. Recent studies have shown that graph neural networks (GNNs) outperform a wide range of traditional network measures in predicting probabilistic… read more here.
Keywords: complex oscillator; stability; gnns; oscillator networks ... See more keywords
An Evidence-Based Paradigm for Financial GNNs: The Case for Principled Simplicity in Volatility Spillover Modeling
Sign Up to like & getrecommendations! Published in 2025 at "IEEE Access"
DOI: 10.1109/access.2025.3640928
Abstract: Financial Graph Neural Networks (GNNs) universally assume fully-connected topologies where every asset influences every other—an unvalidated architectural dogma that we empirically refute. Through rigorous ablation studies across two independent US equity markets (DOW30, SPY TOP40)… read more here.
Keywords: financial gnns; gnns; evidence based; based paradigm ... See more keywords
What Contributes More to the Robustness of Heterophilic Graph Neural Networks?
Sign Up to like & getrecommendations! Published in 2025 at "IEEE Transactions on Systems, Man, and Cybernetics: Systems"
DOI: 10.1109/tsmc.2025.3548860
Abstract: In recent years, graph neural networks (GNNs) have gained significant attention due to their outstanding performance on graph-related tasks by utilizing neighborhood aggregation. However, traditional GNNs are primarily designed based on the homophily assumption, which… read more here.
Keywords: contributes robustness; gnns; graph neural; heterophilic gnns ... See more keywords
Graph Information Vanishing Phenomenon in Implicit Graph Neural Networks
Sign Up to like & getrecommendations! Published in 2024 at "Mathematics"
DOI: 10.3390/math12172659
Abstract: Graph neural networks (GNNs) have been highly successful in graph representation learning. The goal of GNNs is to enrich node representations by aggregating information from neighboring nodes. Much work has attempted to improve the quality… read more here.
Keywords: information; gnns; graph neural; graph information ... See more keywords