| 저자 | 양희윤, 김가형, 이지형 |
|---|---|
| 논문지 | Applied Sciences |
| Vol. | 12 |
| No. | 9 |
| pp. | 4256-4272 |
| 게재일 | 2022-04-22 |
Session-based recommendation predicts an anonymous user’s next action, whether she or he is likely to purchase based on the user’s behavior in the current session as sequences. Most recent research on session-based recommendations makes predictions based on a single-session without incorporating global relationships between sessions. It does not guarantee a better performance because item embeddings learned by solely utilizing a single session (inter-session) have less item transition information than utilizing both intra- and inter-session ones. Some existing methods tried to enhance recommendation performance by adopting memory modules and global transition graphs; however, those need more computation cost and time. We propose a novel algorithm called Logit Averaging (LA), utilizing both (i) local-level logits, which come from intra-sessions item transitions and (ii) global-level logits, which come from gathered logits of related sessions. The proposed method shows an improvement in recommendation performance in respect of accuracy and diversity through extensive experiments.
댓글 0
2023
Automation of Trimming Die Design Inspection by Zigzag Process Between AI and CAD Domains
2023.11.14
저자: Jin-Seop Lee, Tae-Hyun Kim, Sang-Hwan Jeon, Sung-Hyun Park, Sang-Hi Kim, Eun-Ho Lee, Jee-Hyong Lee
논문지: Engineering Applications of Artificial Intelligence (IF: 8.0, Engineering-Multidisceplinary 분야 Top 5)
게재일: 2024-01-01
Automatic defect classification using semi-supervised learning with defect localization
2023.05.18
저자: Yusung Kim , Jin-Seop Lee , Jee-Hyong Lee
논문지: IEEE Transactions on Semiconductor Manufacturing
게재일: 2023-05-18
READSUM: Retrieval-Augmented Adaptive Transformer for Source Code Summarization
2023.06.27
저자: YunSeok Choi, Cheolwon Na, Hyojun Kim, Jee-Hyong Lee
논문지: IEEE Access
Vol.: 11
pp.: 51155 - 51165
게재일: 2023-05-01
2022
Deep Reinforcement Learning Approach for Material Scheduling Considering High-Dimensional Environment of Hybrid Flow-Shop Problem
2022.12.05
저자: Chang-Bae Gil, Jee-Hyong Lee
논문지: Applied Sciences
Vol.: 12
No.: 9332
게재일: 2022-09-17
Weighted Averaging Federated Learning Based on Example Forgetting Events in Label Imbalanced Non-IID
2022.06.08
저자: 홍만수, 강석규, 이지형
논문지: Applied Sciences
Vol.: 12
No.: 5806
게재일: 2022-06-07
Logit Averaging: Capturing Global Relation for Session-Based Recommendation
2022.04.25
저자: 양희윤, 김가형, 이지형
논문지: Applied Sciences
Vol.: 12
No.: 9
pp.: 4256-4272
게재일: 2022-04-22
2021
Monte Carlo Tree Search-Based Recursive Algorithm for Feature Selection in High-Dimensional Datasets
2021.01.24
저자: Muhammad Umar Chaudhry, Muhammad Yasir ,Muhammad Nabeel Asghar ,Jee-Hyong Lee
논문지: Entropy
Vol.: 22
No.: 10
pp.: 1-15
게재일: 2020-10-01
2019
Adversarial Detection with Gaussian Process Regression-based Detector
2019.09.02
저자: Sangheon Lee, Noo-ri Kim, Youngwha Cho, Jae-Young Choi, Suntae Kim, Jeong-Ah Kim, Jee-Hyong Lee
논문지: KSII Transactions on Internet and Information Systems
Vol.: 13
No.: 8
pp.: 4285-4299
게재일: 2019-08-01
Neural attention model with keyword memory for abstractive document summarization
2019.09.02
저자: YunSeok Choi, Dahae Kim, Jee-Hyong Lee
논문지: Concurrency and Computation: Practice and Experience
게재일: 2019-08-01
A novel recommendation approach based on chronological cohesive units in content consuming logs
2019.01.02
저자: Jaekwang Kim, Jee-Hyong Lee
논문지: Information Science
Vol.: 470
pp.: 141-155
게재일: 2019-01-02
Feature Selection for High Dimensional Data using Monte Carlo Tree Search
2019.09.02
저자: Muhammad Umar Chaudhry, Jee-Hyong Lee
논문지: IEEE Access
Vol.: 6
pp.: 76036-76048
게재일: 2018-11-01
2018
A Television Recommender System Learning a User’s Time-Aware Watching Patterns Using Quadratic Programming
2018.09.03
저자: Noo-ri Kim, Sungtak Oh, Jee-Hyoung Lee
논문지: Applied Sciences
Vol.: 8
No.: 8
pp.: 1323, 1-14
게재일: 2018-08-08
MOTiFS: Monte Carlo Tree Search BasedMOTiFS: Monte Carlo Tree Search Based Feature Selection
2018.09.03
저자: Muhammad Umar Chaudhry, Jee-Hyong Lee
논문지: Entropy
Vol.: 20
No.: 5
pp.: 385
게재일: 2018-05-20
Improved Neighborhood Search for Collaborative Filtering
2018.09.03
저자: Yeounoh Chung, Noo-ri Kim, Chang-yong Park, Jee-Hyong Lee
논문지: International Journal of Fuzzy Logic and Intelligent Systems
게재일: 2018-03-21
Detection of document modification based on deep neural networks
2018.02.06
저자: Noo-ri Kim, YunSeok Choi, HyunSoo Lee, Jae-Young Choi, Suntae Kim, Jeong-Ah Kim, Youngwha Cho, Jee-Hyong Lee
논문지: Journal of Ambient Intelligence and Humanized Computing
게재일: 2017-11-01
Data-Driven Optimization of Incentive-based Demand Response System with Uncertain Responses of Customers
2018.02.06
저자: Jimyung Kang, Jee-Hyong Lee
논문지: Energies
게재일: 2017-10-04
A Machine-Learning Based Approach for Extracting Logical Structure of a Styled Document
2018.02.06
저자: Tae-young Kim, Suntae Kim, Sangchul Choi, Jeong-Ah Kim, Jae-Young Choi, Jong-Won Ko, Jee-Huong Lee, Youngwha Cho
논문지: KSII Transactions on Internet & Information Systems
게재일: 2017-02-28
2017
Detection of Content Changes based on Deep Neural Networks
2017.06.29
저자: Noo-ri KimYunSeok ChoiHyunSoo LeeJee-Hyong Lee
논문지: Lecture Notes in Electrical Engineering
게재일: 2016-11-23
2016
Accurate Lithography Hotspot Detection Using Deep Convolutional Neural Networks
2016.10.04
저자: Moojoon Shin, Jee-Hyong Lee
논문지: Journal of Micro/Nanolithography, MEMS, and MOEMS (Under Review)
게재일: 2016-10-04
Improved Post-Filtering Method Using Context Compensation
2016.08.10
저자: BeDeuRo Kim, Jee-Hyong Lee
논문지: International Journal of Fuzzy Logic and Intelligent Systems
Vol.: 16
No.: 2
pp.: 119-124
게재일: 2016-06-01