Search Results for author: Sungsu Lim

Found 6 papers, 2 papers with code

SiReN: Sign-Aware Recommendation Using Graph Neural Networks

1 code implementation19 Aug 2021 Changwon Seo, Kyeong-Joong Jeong, Sungsu Lim, Won-Yong Shin

In recent years, many recommender systems using network embedding (NE) such as graph neural networks (GNNs) have been extensively studied in the sense of improving recommendation accuracy.

Network Embedding Recommendation Systems

Greedification Operators for Policy Optimization: Investigating Forward and Reverse KL Divergences

no code implementations17 Jul 2021 Alan Chan, Hugo Silva, Sungsu Lim, Tadashi Kozuno, A. Rupam Mahmood, Martha White

Approximate Policy Iteration (API) algorithms alternate between (approximate) policy evaluation and (approximate) greedification.

Policy Gradient Methods

TornadoAggregate: Accurate and Scalable Federated Learning via the Ring-Based Architecture

no code implementations6 Dec 2020 Jin-woo Lee, Jaehoon Oh, Sungsu Lim, Se-Young Yun, Jae-Gil Lee

Federated learning has emerged as a new paradigm of collaborative machine learning; however, many prior studies have used global aggregation along a star topology without much consideration of the communication scalability or the diurnal property relied on clients' local time variety.

Federated Learning

SSumM: Sparse Summarization of Massive Graphs

1 code implementation1 Jun 2020 Kyuhan Lee, Hyeonsoo Jo, Jihoon Ko, Sungsu Lim, Kijung Shin

SSumM not only merges nodes together but also sparsifies the summary graph, and the two strategies are carefully balanced based on the minimum description length principle.

Databases Social and Information Networks H.2.8

Maximizing Information Gain in Partially Observable Environments via Prediction Reward

no code implementations11 May 2020 Yash Satsangi, Sungsu Lim, Shimon Whiteson, Frans Oliehoek, Martha White

Information gathering in a partially observable environment can be formulated as a reinforcement learning (RL), problem where the reward depends on the agent's uncertainty.

Question Answering

Actor-Expert: A Framework for using Q-learning in Continuous Action Spaces

no code implementations22 Oct 2018 Sungsu Lim, Ajin Joseph, Lei Le, Yangchen Pan, Martha White

A common strategy has been to restrict the functional form of the action-values to be concave in the actions, to simplify the optimization.

Global Optimization Q-Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.