works on

From the 1 of 1.2k papers with an AI index.

output
20022024
most citedObservation of electron-antineutrino disappearance at Daya Bay

2.2k citations

Showing 2021 · cs.LGShow all

14 papers · 2 filters

cs.LG20216 cited

Probabilistic Entity Representation Model for Reasoning over Knowledge Graphs

Nurendra Choudhary, Nikhil Rao, Sumeet Katariya +2

Logical reasoning over Knowledge Graphs (KGs) is a fundamental technique that can provide efficient querying mechanism over large and incomplete databases. Current approaches emplo…

cs.LG2021

Two-Bit Aggregation for Communication Efficient and Differentially Private Federated Learning

Mohammad Aghapour, Aidin Ferdowsi, Walid Saad

In federated learning (FL), a machine learning model is trained on multiple nodes in a decentralized manner, while keeping the data local and not shared with other nodes. However,…

cs.LG20212 cited

Learning Compact Representations of Neural Networks using DiscriminAtive Masking (DAM)

Jie Bu, Arka Daw, M. Maruf +1

A central goal in deep learning is to learn compact representations of features at every layer of a neural network, which is useful for both unsupervised representation learning an…

cs.LG2021

Automated Feature-Topic Pairing: Aligning Semantic and Embedding Spaces in Spatial Representation Learning

Dongjie Wang, Kunpeng Liu, David Mohaisen +3

Automated characterization of spatial data is a kind of critical geographical intelligence. As an emerging technique for characterization, Spatial Representation Learning (SRL) use…

cs.LG2021

Investigation of Nonlinear Model Order Reduction of the Quasigeostrophic Equations through a Physics-Informed Convolutional Autoencoder

Rachel Cooper, Andrey A. Popov, Adrian Sandu

Reduced order modeling (ROM) is a field of techniques that approximates complex physics-based models of real-world processes by inexpensive surrogates that capture important dynami…

cs.LG2021

Zero-Round Active Learning

Si Chen, Tianhao Wang, Ruoxi Jia

Active learning (AL) aims at reducing labeling effort by identifying the most valuable unlabeled data points from a large pool. Traditional AL frameworks have two limitations: Firs…