9.8k citations
- University of MinnesotaUS458 papers
- California Institute of TechnologyUS301 papers
- Fermi National Accelerator LaboratoryUS270 papers
- Massachusetts Institute of TechnologyUS269 papers
- University of FloridaUS266 papers
- University of Maryland, College ParkUS262 papers
- University of WarsawPL260 papers
- Tata Institute of Fundamental ResearchIN253 papers
- Seoul National UniversityKR250 papers
- Cornell UniversityUS249 papers
- University of PerugiaIT248 papers
- Carnegie Mellon UniversityUS244 papers
15 papers · 2 filters
Characteristic Neural Ordinary Differential Equations
Xingzi Xu, Ali Hasan, Khalil Elkhalil +2
We propose Characteristic-Neural Ordinary Differential Equations (C-NODEs), a framework for extending Neural Ordinary Differential Equations (NODEs) beyond ODEs. While NODEs model…
Distributionally Robust Semi-Supervised Learning Over Graphs
Alireza Sadeghi, Meng Ma, Bingcong Li +1
Semi-supervised learning (SSL) over graph-structured data emerges in many network science applications. To efficiently manage learning over graphs, variants of graph neural network…
A Semi-Supervised Approach for Abnormal Event Prediction on Large Operational Network Time-Series Data
Yijun Lin, Yao-Yi Chiang
Large network logs, recording multivariate time series generated from heterogeneous devices and sensors in a network, can often reveal important information about abnormal activiti…
Knowledge Sheaves: A Sheaf-Theoretic Framework for Knowledge Graph Embedding
Thomas Gebhart, Jakob Hansen, Paul Schrater
Knowledge graph embedding involves learning representations of entities -- the vertices of the graph -- and relations -- the edges of the graph -- such that the resulting represent…
HeMI: Multi-view Embedding in Heterogeneous Graphs
Costas Mavromatis, George Karypis
Many real-world graphs involve different types of nodes and relations between nodes, being heterogeneous by nature. The representation learning of heterogeneous graphs (HGs) embeds…
Incentivizing Compliance with Algorithmic Instruments
Daniel Ngo, Logan Stapleton, Vasilis Syrgkanis +1
Randomized experiments can be susceptible to selection bias due to potential non-compliance by the participants. While much of the existing work has studied compliance as a static…