Link prediction
PulseAugur coverage of Link prediction — every cluster mentioning Link prediction across labs, papers, and developer communities, ranked by signal.
3 day(s) with sentiment data
-
New Research Benchmarks Hyperbolic Graph Embedders for Network Analysis
A new paper published on arXiv benchmarks thirteen unsupervised hyperbolic graph embedders from machine learning, network science, and algorithmics. The study evaluates these methods for link prediction and topology rec…
-
New nonlinear Laplacian operator enhances graph neural networks for signed-directed data
Researchers have developed a new non-linear Laplacian operator, termed NLSD, specifically designed for signed-directed graphs. This operator extends existing concepts for signed and directed graphs by calculating node-s…
-
New protocol for GNN cross-task transfer reveals directional predictability
Researchers have developed a new protocol to reliably evaluate cross-task transfer in Graph Neural Networks (GNNs) for node classification (NC) and link prediction (LP) tasks. Their findings indicate that transfer from …
-
Introduction to Graph Neural Networks for Link Prediction
This article provides an introduction to Graph Neural Networks (GNNs) and their application in link prediction. It discusses the advancements in technology and the rise of social media solutions, highlighting the compet…
-
New method enhances explainability of Temporal Graph Networks
Researchers have developed a new method to explain the predictions of Temporal Graph Networks (TGNs) by focusing on their memory modules. This approach utilizes a topology attribution tree to assess the influence of nei…
-
New PGRE Model Enhances Dynamic Knowledge Graph Analysis
Researchers have introduced PGRE (Poisson-Gamma Relational Evolution), a new probabilistic model designed to handle inter-relational dependencies in dynamic knowledge graphs. This model addresses challenges posed by the…
-
New GNN method speeds up link prediction with early exits
Researchers have developed early-exit strategies for Graph Neural Networks (GNNs) to improve inference speed in link prediction tasks. This approach allows GNNs to exit early without explicit auxiliary losses, potential…
-
New research explores faster GNNs and unified theory · 2 papers tracked
Two recent arXiv papers explore advancements in graph neural networks (GNNs). The first paper introduces early-exit strategies for GNNs to improve inference speed without significantly sacrificing prediction quality, de…
-
Aitchison geometry powers new compositional graph embeddings and flavor tagger calibration
Two new arXiv papers introduce novel approaches to representation learning using Aitchison geometry. One paper proposes a framework for calibrating flavor taggers in high-energy physics by formulating it as an optimal t…