GravityGraphSAGE adapts GraphSAGE with a gravity-inspired decoder to outperform prior graph deep learning methods on directed link prediction across citation networks and 16 real-world graphs.
Journal of the American Society for Information Science and Technology , volume =
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 6roles
background 1polarities
background 1representative citing papers
Phantom collaborators—topically similar authors distant in the coauthor graph—become actual coauthors 16-33 times more often than baselines, with a 68-fold similarity gradient.
RoleMAG learns neighbor roles in multimodal graphs to route shared, complementary, and heterophilous signals through separate channels, improving propagation without modality interference.
Matrix factorization on a literature-mined concept-object graph predicts future associations in astronomy better than neighborhood similarity or recency heuristics.
Improper use of test data during hyperparameter tuning in link prediction inflates performance estimates by an average of 3.6 percent across 60 networks, as measured by a new Loss Ratio metric.
Determines the exact wirelength of embedding 3-ary n-cubes into cylinders and certain trees.
citing papers explorer
-
GravityGraphSAGE: Link Prediction in Directed Attributed Graphs
GravityGraphSAGE adapts GraphSAGE with a gravity-inspired decoder to outperform prior graph deep learning methods on directed link prediction across citation networks and 16 real-world graphs.
-
Beyond coauthorship: semantic structure and phantom collaborators in transportation research, 1967--2025
Phantom collaborators—topically similar authors distant in the coauthor graph—become actual coauthors 16-33 times more often than baselines, with a 68-fold similarity gradient.
-
RoleMAG: Learning Neighbor Roles in Multimodal Graphs
RoleMAG learns neighbor roles in multimodal graphs to route shared, complementary, and heterophilous signals through separate channels, improving propagation without modality interference.
-
Predicting New Concept-Object Associations in Astronomy by Mining the Literature
Matrix factorization on a literature-mined concept-object graph predicts future associations in astronomy better than neighborhood similarity or recency heuristics.
-
Impacts of Data Splitting Strategies on Parameterized Link Prediction Algorithms
Improper use of test data during hyperparameter tuning in link prediction inflates performance estimates by an average of 3.6 percent across 60 networks, as measured by a new Loss Ratio metric.
-
Exact Wirelength of Embedding 3-Ary n-Cubes into certain Cylinders and Trees
Determines the exact wirelength of embedding 3-ary n-cubes into cylinders and certain trees.