PSP-HDC encodes a directed PSP graph into hyperdimensional vectors via a trainable encoder and graph-aligned operations to predict sheet-resistance regimes with 0.91 accuracy and intrinsic explanations.
Composition- based multi-relational graph convolutional networks
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 5verdicts
UNVERDICTED 5roles
background 1polarities
background 1representative citing papers
DiffTSP applies discrete diffusion to knowledge graph triple set prediction, recovering all missing triples simultaneously via edge-masking noise reversal and a structure-aware transformer, achieving SOTA on three datasets.
SAGE-Nav decouples LLM global planning from reactive control via hierarchical scene graphs and alignment fusion, reporting SOTA results on i-THOR and RoboTHOR with improved efficiency and zero-shot generalization.
The Rule Violation Score (RVS) is proposed to quantify logical rule compliance of predictive models on relational data, with automatic SQL computation for Horn rules, and shown to distinguish models that accuracy metrics treat as equivalent.
A spectral graph RL model learns near-optimal outage restoration policies and is evaluated on modified IEEE 13-, 34-, and 123-bus test systems.
citing papers explorer
-
Graph-Structured Hyperdimensional Computing for Data-Efficient and Explainable Process-Structure-Property Prediction
PSP-HDC encodes a directed PSP graph into hyperdimensional vectors via a trainable encoder and graph-aligned operations to predict sheet-resistance regimes with 0.91 accuracy and intrinsic explanations.
-
One Pass for All: A Discrete Diffusion Model for Knowledge Graph Triple Set Prediction
DiffTSP applies discrete diffusion to knowledge graph triple set prediction, recovering all missing triples simultaneously via edge-masking noise reversal and a structure-aware transformer, achieving SOTA on three datasets.
-
SAGE-Nav: Leveraging LLM Planning and Alignment Fusion for Hierarchical Scene Graph-Guided Navigation
SAGE-Nav decouples LLM global planning from reactive control via hierarchical scene graphs and alignment fusion, reporting SOTA results on i-THOR and RoboTHOR with improved efficiency and zero-shot generalization.
-
Beyond Accuracy: Measuring Logical Compliance of Predictive Models
The Rule Violation Score (RVS) is proposed to quantify logical rule compliance of predictive models on relational data, with automatic SQL computation for Horn rules, and shown to distinguish models that accuracy metrics treat as equivalent.
-
Outage Detection in Self-Healing Smart Grids Using Reinforcement Learning with Spectral Graph Neural Networks
A spectral graph RL model learns near-optimal outage restoration policies and is evaluated on modified IEEE 13-, 34-, and 123-bus test systems.