1k citations · 4.2k across the 120 of their papers we have counts for
4 papers · 1 filter
Diffusion Improves Graph Learning
Johannes Gasteiger, Stefan Weißenberger, Stephan Günnemann
Graph convolution is the core of most Graph Neural Networks (GNNs) and usually approximated by message passing between direct (one-hop) neighbors. In this work, we remove the restr…
GhostLink: Latent Network Inference for Influence-aware Recommendation
Subhabrata Mukherjee, Stephan Guennemann
Social influence plays a vital role in shaping a user's behavior in online communities dealing with items of fine taste like movies, food, and beer. For online recommendation, this…
Hyperbolae Are No Hyperbole: Modelling Communities That Are Not Cliques
Saskia Metzler, Stephan Günnemann, Pauli Miettinen
Cliques are frequently used to model communities: a community is a set of nodes where each pair is equally likely to be connected. But studying real-world communities reveals that…
EdgeCentric: Anomaly Detection in Edge-Attributed Networks
Neil Shah, Alex Beutel, Bryan Hooi +5
Given a network with attributed edges, how can we identify anomalous behavior? Networks with edge attributes are commonplace in the real world. For example, edges in e-commerce net…