output
20062025
most citedThe Gaia mission

7.1k citations

Showing cs.LGShow all

14 papers · 1 filter

cs.LG2024

Alleviating Over-Smoothing via Aggregation over Compact Manifolds

Dongzhuoran Zhou, Hui Yang, Bo Xiong +2

Graph neural networks (GNNs) have achieved significant success in various applications. Most GNNs learn the node features with information aggregation of its neighbors and feature…

cs.LG202314 cited

Deep learning based Meta-modeling for Multi-objective Technology Optimization of Electrical Machines

Vivek Parekh, Dominik Flore, Sebastian Schöps

Optimization of rotating electrical machines is both time- and computationally expensive. Because of the different parametrization, design optimization is commonly executed separat…

cs.LG202330 cited

PrecTime: A Deep Learning Architecture for Precise Time Series Segmentation in Industrial Manufacturing Operations

Stefan Gaugel, Manfred Reichert

The fourth industrial revolution creates ubiquitous sensor data in production plants. To generate maximum value out of these data, reliable and precise time series-based machine le…

cs.LG20228 cited

PAC-Bayesian Lifelong Learning For Multi-Armed Bandits

Hamish Flynn, David Reeb, Melih Kandemir +1

We present a PAC-Bayesian analysis of lifelong learning. In the lifelong learning problem, a sequence of learning tasks is observed one-at-a-time, and the goal is to transfer infor…

cs.LG202276 cited

SelfKG: Self-Supervised Entity Alignment in Knowledge Graphs

Xiao Liu, Haoyun Hong, Xinghao Wang +4

Entity alignment, aiming to identify equivalent entities across different knowledge graphs (KGs), is a fundamental problem for constructing Web-scale KGs. Over the course of its de…

cs.LG202214 cited

DeepHybrid: Deep Learning on Automotive Radar Spectra and Reflections for Object Classification

Adriana-Eliza Cozma, Lisa Morgan, Martin Stolz +2

Automated vehicles need to detect and classify objects and traffic participants accurately. Reliable object classification using automotive radar sensors has proved to be challengi…