CiteSeerX
PulseAugur coverage of CiteSeerX — every cluster mentioning CiteSeerX across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
TRON framework uses biological networks to improve AI architecture search
Researchers have developed TRON (TRansfer Of Natural networks), a novel neuroevolution framework that leverages biological protein-protein interaction (PPI) networks as architectural priors for artificial neural network…
-
New benchmark Lethe evaluates edge unlearning in graph neural networks
Researchers have introduced Lethe, a new benchmark designed to evaluate edge unlearning methods for graph neural networks. Current evaluations for edge unlearning are limited, often using datasets where node features ov…
-
New fractional heat kernel improves graph learning with minimal training data
Researchers have developed a novel fractional heat-kernel framework for semi-supervised graph learning, designed to improve performance even with limited training data. This method combines nonlocal propagation with sus…
-
New method constructs diverse decision sources for improved pseudo-label learning
Researchers have developed a method to improve pseudo-label learning by constructing more informative decision sources. Instead of relying on multiple identical models, this approach modifies the internal structure of a…
-
New N-GNAS framework enhances Graph Neural Networks by optimizing node-level architectures
Researchers have developed a novel Node-Level Graph Neural Architecture Search (N-GNAS) framework designed to improve the performance of Graph Neural Networks (GNNs). Unlike traditional methods that apply uniform operat…
-
LLM Features Can Harm GNN Performance on Homophilous Graphs
A new research paper reveals that incorporating features generated by large language models (LLMs) into graph neural networks (GNNs) can sometimes decrease performance on specific benchmarks. This effect, termed 'concat…
-
Gravity-GraphSAGE advances link prediction for directed attributed graphs
Researchers have introduced Gravity-GraphSAGE (GG-SAGE), a novel approach to link prediction in directed attributed graphs. This modified GraphSAGE model incorporates a gravity-inspired decoder, addressing a gap in exis…