Local Weighted-Degree Entropy Serves as a Diagnostic and Routing Signal for Temporal GNN Aggregation
Entropy · 18.11.2026 · 28 (11) · 1270
DOI: 10.3390/e28111270 ↗Kurz gefasst
Fachartikel in der Zeitschrift Entropy, online erschienen am 18.11.2026. Verfasst von Wei He. Die Arbeit nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Temporal link prediction is usually scored by a single outer-test average, which treats predictive risk as exchangeable across dyads. Contact and online-learning streams violate that assumption: recurrent motifs coexist with sparse, weakly recurrent edges. We study whether the relative out-of-sample risk of snapshot message passing is heterogeneous across local weighted-degree-entropy states, and whether an entropy-conditioned router yields selective rather than uniform risk reductions. On SocioPatterns school/workplace contacts, BenchTemp massive open online course (MOOC) and contact-like panels, and synthetic temporal graphs, we compare a calendar–recency logistic baseline, protocol-matched temporal graph neural network (GNN) controls, an ungated temporal graph convolutional network (GCN), and an entropy-gated dual-head model under a chronological 50/25/25 split. Normalized local weighted-degree entropy serves as both an evaluation stratum and a soft gate between message-passing and calendar–recency logits. In a fixed medium protocol (12 units), gating improves mean outer-test log-loss relative to the ungated GCN on school (Δ=−0.015) and workplace (Δ=−0.003), with school gains concentrated in the highest-entropy quintile (mean Δ=−0.071). These gains are relative to a weaker ungated GCN; a calendar–recency logistic baseline often remains competitive or better in absolute log-loss. Heterogeneous-exponential synthetics favor gating, whereas memory-free and homogeneous-exponential controls can produce harm; multi-seed and transfer screens bound stability. The contribution is diagnostic: entropy-conditioned errors matter when risk is uneven, but the effect is neither universal across domains nor stable under all generators.
Zitieren
APA
He, W. (2026). Local Weighted-Degree Entropy Serves as a Diagnostic and Routing Signal for Temporal GNN Aggregation. Entropy, 28(11), 1270. https://doi.org/10.3390/e28111270
Vancouver
He W. Local Weighted-Degree Entropy Serves as a Diagnostic and Routing Signal for Temporal GNN Aggregation. Entropy. 2026;28(11):1270. doi:10.3390/e28111270
BibTeX
@article{He2026,
author = {He, Wei},
title = {Local Weighted-Degree Entropy Serves as a Diagnostic and Routing Signal for Temporal GNN Aggregation},
journal = {Entropy},
year = {2026},
volume = {28},
number = {11},
pages = {1270},
doi = {10.3390/e28111270}
}
EUVIMED