1 code implementation • 5 Oct 2023 • Hyunsik Jeon, Jong-eun Lee, Jeongin Yun, U Kang
To estimate the user-bundle relationship more accurately, CoHeat addresses the highly skewed distribution of bundle interactions through a popularity-based coalescence approach, which incorporates historical and affiliation information based on the bundle's popularity.
1 code implementation • 19 Oct 2022 • Jongjin Kim, Hyunsik Jeon, Jaeri Lee, U Kang
However, it is challenging to tackle aggregate-level diversity with a matrix factorization (MF), one of the most common recommendation model, since skewed real world data lead to skewed recommendation results of MF.
1 code implementation • 19 Oct 2022 • Hyunsik Jeon, Jun-Gi Jang, Taehun Kim, U Kang
BundleMage effectively mixes user preferences of items and bundles using an adaptive gate technique to achieve high accuracy for the bundle matching.
1 code implementation • 12 Aug 2022 • Hyunsik Jeon, Jongjin Kim, Hoyoung Yoon, Jaeri Lee, U Kang
SmartSense then summarizes sequences of users considering queried contexts in a query-attentive manner to extract the query-related patterns from the sequential actions.
1 code implementation • 9 Jun 2022 • Jaemin Yoo, Hyunsik Jeon, Jinhong Jung, U Kang
Given a graph with partial observations of node features, how can we estimate the missing features accurately?
no code implementations • 1 Jan 2021 • Seongmin Lee, Hyunsik Jeon, U Kang
Given multiple source datasets with labels, how can we train a target model with no labeled data?
no code implementations • 29 Sep 2020 • Seongmin Lee, Hyunsik Jeon, U Kang
Multi-source domain adaptation (MSDA) aims to train a model using multiple source datasets different from a target dataset in the absence of target data labels.
no code implementations • 22 Aug 2019 • Hyunsik Jeon, Bonhun Koo, U Kang
Given a sparse rating matrix and an auxiliary matrix of users or items, how can we accurately predict missing ratings considering different data contexts of entities?