Search Results for author: Hyunsoo Kim

Found 5 papers, 2 papers with code

MARS: Matching Attribute-aware Representations for Text-based Sequential Recommendation

1 code implementation1 Sep 2024 Hyunsoo Kim, Junyoung Kim, Minjin Choi, Sunkyung Lee, Jongwuk Lee

MARS extracts detailed user and item representations through attribute-aware text encoding, capturing diverse user intents with multiple attribute-aware representations.

Attribute Sequential Recommendation +1

Node Embedding for Homophilous Graphs with ARGEW: Augmentation of Random walks by Graph Edge Weights

no code implementations11 Aug 2023 Jun Hee Kim, Jaeman Son, Hyunsoo Kim, EunJo Lee

In this paper, we propose ARGEW (Augmentation of Random walks by Graph Edge Weights), a novel augmentation method for random walks that expands the corpus in such a way that nodes with larger edge weights end up with closer embeddings.

Node Classification

Gradient-based Bit Encoding Optimization for Noise-Robust Binary Memristive Crossbar

no code implementations5 Jan 2022 Youngeun Kim, Hyunsoo Kim, Seijoon Kim, Sang Joon Kim, Priyadarshini Panda

In addition, we propose Gradient-based Bit Encoding Optimization (GBO) which optimizes a different number of pulses at each layer, based on our in-depth analysis that each layer has a different level of noise sensitivity.

$c$-axis transport in UTe$_{2}$: Evidence of Three Dimensional Conductivity Component

no code implementations8 Jan 2021 Yun Suk Eo, Shanta R. Saha, Hyunsoo Kim, Sheng Ran, Jarryd A. Horn, Halyna Hodovanets, John Collini, Wesley T. Fuhrman, Andriy H. Nevidomskyy, Nicholas P. Butch, Michael S. Fuhrer, Johnpierre Paglione

We study the temperature dependence of electrical resistivity for currents directed along all crystallographic axes of the spin-triplet superconductor UTe$_{2}$.

Strongly Correlated Electrons Superconductivity

Learning to Discover Cross-Domain Relations with Generative Adversarial Networks

19 code implementations ICML 2017 Taeksoo Kim, Moonsu Cha, Hyunsoo Kim, Jung Kwon Lee, Jiwon Kim

While humans easily recognize relations between data from different domains without any supervision, learning to automatically discover them is in general very challenging and needs many ground-truth pairs that illustrate the relations.

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