activity
20152026
most citedRepresentational Continuity for Unsupervised Continual Learning

28 citations · 296 across the 50 of their papers we have counts for

collaborators
Showing 2021Show all

11 papers · 1 filter

cs.CV2021★ 14 cited

MPViT: Multi-Path Vision Transformer for Dense Prediction

Youngwan Lee, Jonghee Kim, Jeff Willette +1

Dense computer vision tasks such as object detection and segmentation require effective multi-scale feature representation for detecting or classifying objects or regions with vary…

q-bio.QM2021★ 20 cited

Hit and Lead Discovery with Explorative RL and Fragment-based Molecule Generation

Soojung Yang, Doyeong Hwang, Seul Lee +2

Recently, utilizing reinforcement learning (RL) to generate molecules with desired properties has been highlighted as a promising strategy for drug design. A molecular docking prog…

cs.LG2021★ 28 cited

Representational Continuity for Unsupervised Continual Learning

Divyam Madaan, Jaehong Yoon, Yuanchun Li +2

Continual learning (CL) aims to learn a sequence of tasks without forgetting the previously acquired knowledge. However, recent CL advances are restricted to supervised continual l…

stat.ML2021

Meta Learning Low Rank Covariance Factors for Energy-Based Deterministic Uncertainty

Jeffrey Willette, Hae Beom Lee, Juho Lee +1

Numerous recent works utilize bi-Lipschitz regularization of neural network layers to preserve relative distances between data instances in the feature spaces of each layer. This d…

cs.LG2021★ 7 cited

RetCL: A Selection-based Approach for Retrosynthesis via Contrastive Learning

Hankook Lee, Sungsoo Ahn, Seung-Woo Seo +4

Retrosynthesis, of which the goal is to find a set of reactants for synthesizing a target product, is an emerging research area of deep learning. While the existing approaches have…

cs.LG2021★ 18 cited

Edge Representation Learning with Hypergraphs

Jaehyeong Jo, Jinheon Baek, Seul Lee +3

Graph neural networks have recently achieved remarkable success in representing graph-structured data, with rapid progress in both the node embedding and graph pooling methods. Yet…