Oversmoothing in neural sheaf diffusion is reframed as representation degeneration in the incidence-quiver harmonic space, with moment-map regularizers and non-uniform stalk dimensions proposed to avoid it.
International Conference on Learning Representations , year =
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5representative citing papers
Under strict inductive protocols without temporal leakage, random forests on raw features achieve higher F1 scores than GNNs on Bitcoin fraud detection, and real graph structure can underperform random wiring.
A blackboard multi-agent system parses STEP B-Reps, injects GraphSAGE feature labels, and uses Claude plus GPT-4o to reorient and modify FDM parts for overhang-free printability.
A per-item Q-learning policy that explicitly decides which observed knowledge-graph facts to keep or drop outperforms fixed heuristics and sequence-memory baselines on the RoomKG benchmark at memory capacity 128.
UTOPYA fuses eight modalities via FiLM-conditioned attention and physics-informed regularization to reach AUROC 0.874 for anomaly detection in batch distillation, outperforming baselines by 0.147.
citing papers explorer
-
Oversmoothing as Representation Degeneracy in Neural Sheaf Diffusion
Oversmoothing in neural sheaf diffusion is reframed as representation degeneration in the incidence-quiver harmonic space, with moment-map regularizers and non-uniform stalk dimensions proposed to avoid it.
-
When Graph Structure Becomes a Liability: A Critical Re-Evaluation of Graph Neural Networks for Bitcoin Fraud Detection under Temporal Distribution Shift
Under strict inductive protocols without temporal leakage, random forests on raw features achieve higher F1 scores than GNNs on Bitcoin fraud detection, and real graph structure can underperform random wiring.
-
AgentsCAD: Automated Design for Manufacturing of FDM Parts via Multi-Agent LLM Reasoning and Geometric Feature Recognition
A blackboard multi-agent system parses STEP B-Reps, injects GraphSAGE feature labels, and uses Claude plus GPT-4o to reorient and modify FDM parts for overhang-free printability.
-
Short-Term-to-Long-Term Memory Transfer for Knowledge Graphs under Partial Observability
A per-item Q-learning policy that explicitly decides which observed knowledge-graph facts to keep or drop outperforms fixed heuristics and sequence-memory baselines on the RoomKG benchmark at memory capacity 128.
-
UTOPYA: A Multimodal Deep Learning Framework for Physics-Informed Anomaly Detection and Time-Series Prediction
UTOPYA fuses eight modalities via FiLM-conditioned attention and physics-informed regularization to reach AUROC 0.874 for anomaly detection in batch distillation, outperforming baselines by 0.147.