Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs
Dec 6, 2020
Speakers
Lingxiao Zhao
Sprecher:in · 0 Follower:innen
Mark Heimann
Sprecher:in · 0 Follower:innen
Leman Akoglu
Sprecher:in · 0 Follower:innen
Danai Koutra
Sprecher:in · 1 Follower:in
Organizer
NeurIPS 2020
Konto · 11,5k Follower:innen
Categories
Webentwicklung und UX-/UI
Kategorie · 1,2k Präsentationen
Bildende Kunst und Grafikdesign
Kategorie · 333 Präsentationen
KI und Datenwissenschaft
Kategorie · 10,8k Präsentationen
About NeurIPS 2020
Neural Information Processing Systems (NeurIPS) is a multi-track machine learning and computational neuroscience conference that includes invited talks, demonstrations, symposia and oral and poster presentations of refereed papers. Following the conference, there are workshops which provide a less formal setting.
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
No-Regret Learning Dynamics for Extensive-Form Correlated Equilibrium
Später ansehen
Andrea Celli, …
Ewigspeicher-Fortschrittswert: 0 = 0.0%
Hidden Physics Models
Später ansehen
Ewigspeicher-Fortschrittswert: 0 = 0.0%
Emergence of compositional abstractions in human collaborative assembly
Später ansehen
Ewigspeicher-Fortschrittswert: 0 = 0.0%
Applying Graph Neural Networks to Molecular Design
Später ansehen
Ewigspeicher-Fortschrittswert: 1 = 0.1%
Online Sinkhorn: Optimal Transport distances from sample streams
Später ansehen
Ewigspeicher-Fortschrittswert: 0 = 0.0%
Towards Interpretable Representation Learning and Evaluation
Später ansehen
Ewigspeicher-Fortschrittswert: 0 = 0.0%