Recommender Systems

추천 시스템은 영화/음악 스트리밍, E-commerce, 뉴스 포털 등의 플랫폼에서, 각 사용자에게 사용자 개개인의 취향이 잘 반영된 아이템(컨텐츠 또는 상품)을 제공하기 위한 기술입니다. 이를 위해, 추천 시스템은 각 사용자, 아이템의 프로필 정보와 사용자의 과거 아이템 이용/평가 내역을 고려하여, 해당 사용자가 선호할 가능성이 높은 아이템들을 예측합니다. 최근, 플랫폼 상에서 사용자들에게 제공되는 아이템의 종류와 수가 크게 증가함에 따라, 정확도 높은 추천 시스템을 위한 연구 및 이를 통한 사용자 맞춤형 서비스, 마케팅 등이 Netflix, YouTube, Amazon 등의 다양한 플랫폼들에서 활발히 진행되고 있습니다.
빅데이터 사이언스 연구실에서는 데이터 마이닝 및 인공 지능 기술을 기반으로, 다양한 추천 시스템과 이와 연관된 응용 기술들을 연구하고 있습니다. 특히, 사용자의 아이템 이용 패턴을 분석하여 각 사용자의 무관심 아이템을 도출한 뒤, 이를 통해 각 사용자에게 최적화된 아이템만을 추천해주는 기술은, 그 우수성을 인정받아 빅데이터공학 분야의 탑 컨퍼런스인 IEEE ICDE 2016에 발표되었으며, 이후 다양한 관련 기술들을 진일보시키는 기반이 되었습니다.

  • (SW 스타랩) 과학기술정보통신부, 실세계의 다양한 다운스트림 태스크를 위한 고성능 빅 하이퍼그래프 마이닝 플랫폼 개발, 2022.04 - 2029.12
  • 과학기술정보통신부, 인공지능대학원 지원사업, 2020.04 - 2030.08
  • 한국연구재단, BK21 FOUR 인공지능혁신인재교육연구단, 2020.09 - 2027.08
  • 과학기술정보통신부, 암시적 정보 기반 스마트 미디어 추천 기술 개발, 2022.04 - 2025.12
  • 한국전자통신연구원 (ETRI), 지능형 개인맞춤 재활운동 서비스 기술개발, 2021.04 - 2023.10

Publications

  • Jeewon Ahn*, Hong-Kyun Bae* and Sang-Wook Kim, “Is the Impression Log Beneficial to Effective Model Training in News Recommender Systems? No, It’s NOT”, In Proceedings of the ACM Web Conference 2023 (WWW 2023), pp., Texas, USA, April 30 – May 4, 2023 (short paper). (*co-first authors with equal contribution) (accepted to appear).
  • Hong-Kyun Bae, Yeon-Chang Lee, Kyungsik Han, and Sang-Wook Kim, “A Competition-Aware Approach to Accurate TV Show Recommendation,” In Proc. of the 39th IEEE Int’l. Conf. on Data Engineering (IEEE ICDE 2023), pp., Anaheim, California, USA, April 3-7, 2023 (full paper). (accepted to appear).
  • Hong-Kyun Bae, Jeewon Ahn, Dongwon Lee, Sang-Wook Kim, “LANCER: A Lifetime-Aware News Recommender System”, In Proc. of the Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI 2023), pp., Washington D.C., USA. February 7-14, 2023 (full paper). (accepted to appear).
  • Deniz CANTURK, Pinar Karagoz, Kim Sang-Wook, Ismail Hakki Toroslu, “Trust-Aware Location Recommendation in Location-Based Social Networks: A Graph-Based Approach”, Expert Systems With Applications, 2023. (accepted to appear)
  • Taeri Kim*, Yeon-Chang Lee*, Kijung Shin, and Sang-Wook Kim, “MARIO: Modality-Aware Attention and Modality-Preserving Decoders for Multimedia Recommendation”, In Proc. of the 31st ACM Int’l Conf. on Information and Knowledge Management (ACM CIKM 2022), pp.993–1002, Atlanta, GA, USA, Oct. 17-21, 2022 (full paper). (*co-first authors with equal contribution)
  • Taeho Kim*, Yungi Kim*, Yeon-Chang Lee, Won-Yong Shin, and Sang-Wook Kim, “Is It Enough Just Looking at the Title?: Leveraging Body Text To Enrich Title Words Towards Accurate News Recommendation”, In Proc. of the 31st ACM Int’l. Conf. on Information and Knowledge Management (ACM CIKM 2022), pp.4138–4142, Atlanta, GA, USA, Oct. 17-21, 2022 (short paper). (*co-first authors with equal contribution)
  • Hongjun Lim*, Yeon-Chang Lee*, Jin-Seo Lee, Sanggyu Han, Seunghyeon Kim, Yeongjong Jeong, Changbong Kim, Jaehun Kim, Sunghoon Han, Solbi Choi, Hanjong Ko, Dokyeong Lee, Jaeho Choi, Yungi Kim, Hong-Kyun Bae, Taeho Kim, Jeewon Ahn, Hyun-Soung You and Sang-Wook Kim, “AiRS: A Large-Scale Recommender System at NAVER News”, In Proc. of the 38th IEEE International Conference on Data Engineering (IEEE ICDE 2022), pp. 3386-3398, Virtual Event, May 9-12, 2022 (full paper). (*co-first authors with equal contribution)
  • Sung-Jun Park*, Dong-Kyu Chae*, Hong-Kyun Bae, Sumin Park and Sang-Wook Kim, “Reinforcement Learning over Sentiment-Augmented Knowledge Graphs towards Accurate and Explainable Recommendation”, In Proc. of the 15th ACM International Conference on Web Search and Data Mining (ACM WSDM 2022), pp. 784-793, Virtual Event, Tempe, Arizona, USA, Feb. 21-25, 2022 (full paper). (*co-first authors with equal contribution)
  • Junha Park*, Yeon-Chang Lee* and Sang-Wook Kim, “Effective and Efficient Negative Sampling in Metric Learning based Recommendation”, Information Sciences, Vol. 605, pp. 351-365, Aug. 2022. (*co-first authors with equal contribution)
  • Yunyong Ko*, Jae-Seo Yu*, Hong-Kyun Bae, Yongjun Park, Dongwon Lee and Sang-Wook Kim, “MASCOT: A Quantization Framework for Efficient Matrix Factorization in Recommender Systems”, In Proc. of the 21st IEEE International Conference on Data Mining (IEEE ICDM 2021), pp. 290-299, New Zealand, Dec. 7-10, 2021 (full paper). (*co-first authors with equal contribution)
  • Hong-Kyun Bae, Hyung-Ook Kim, Won-Yong Shin and Sang-Wook Kim, ““How to Get Consensus with Neighbors?”: Rating Standardization for Accurate Collaborative Filtering”, Knowledge-Based Systems, Vol. 234, pp. 1-13, Dec 25, 2021.
  • Yeon-Chang Lee*, Taeho Kim*, Jaeho Choi, Xiangnan He and Sang-Wook Kim, “M-BPR: A Novel Approach to Improving BPR for Recommendation with Multi-type Pair-wise Preferences”, Information Sciences, Vol. 547, pp. 255-270, Feb. 2021.
  • Kyung-Jae Cho*, Yeon-Chang Lee*, Kyungsik Han, Jaeho Choi and Sang-Wook Kim, “No, That’s Not My Feedback: TV Show Recommendation Using Watchable Interval”, In Proc. of the 35th IEEE Int’l Conf. on Data Engineering (IEEE ICDE 2019), pp. 316-327, Macau SAR, China, Apr. 8-12, 2019 (full paper).
  • Cong Tran, Jang Young Kim, Won Yong Shin and Sang-Wook Kim, “Clustering-Based Collaborative Filtering Using an Incentivized/Penalized User Model,” IEEE Access, Vol. 7, pp. 62115-62125, May 2019.
  • Dong-Kyu Chae, Jung Ah Shin and Sang-Wook Kim, “Collaborative Adversarial Autoencoders: An Effective Collaborative Filtering Model under the GAN Framework,” IEEE Access, Vol. 7, No. 1, pp. 37650-37663, Dec. 2019.
  • Jongwuk Lee, Won-Seok Hwang, Juan Parc, Sang-Wook Kim, Dongwon Lee, and YoungNam Lee, “l-Injection: Toward Effective Collaborative Filtering Using Uninteresting Items”, IEEE Transactions on Knowledge and Data Engineering, Vol. 31, No. 1, pp. 3-16, Jan. 2019.
  • Dong-Gyun Hong*, Yeon-Chang Lee*, Jongwuk Lee and Sang-Wook Kim, “CrowdStart: Warming up Cold-Start Items using Crowdsourcing”, Expert Systems With Applications, Vol. 138, pp. 1-15, Dec. 2019.
  • Dong-Kyu Chae, Sang-Wook Kim and Jung-Tae Lee, “Autoencoder-based Personalized Ranking Framework Unifying Explicit and Implicit Feedback for Accurate Top-N Recommendation”, Knowledge-Based Systems, Vol. 176, pp. 110-121, July 2019.
  • Youngnam Lee, Sang-Wook Kim, Sunju Park and Xing Xie, “How to Impute Missing Ratings? Claims, Solution, and Its Application to Collaborative Filtering”, In Proc. of the 27th Int’l World Wide Web Conference (WWW 2018), pp. 783-792, Lyon, France, Apr. 23-27, 2018 (full paper).
  • Yeon-Chang Lee, Sang-Wook Kim, and Dongwon Lee, “gOCCF: Graph-Theoretic One-Class Collaborative Filtering Based on Uninteresting Items”, In Proc. of Int’l AAAI Conf. on Artificial Intelligence (AAAI 2018), pp. 3448-3456, New Orleans, Louisiana, USA, Feb. 2-7, 2018 (full paper).
  • Jiwon Hong and Sang-Wook Kim, Mina Rho, YoonHee Choi, Yoonsik Tak, “An Accurate, Efficient, and Scalable Approach to Channel Matching in Smart TVs”, In Proc. of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval (ACM SIGIR 2017), pp. 1025-1028, Tokyo, Japan, Aug. 7-11, 2017 (short paper).
  • Sang-Chul Lee, Sang-Wook Kim, Sunju Park and Dong-Kyu Chae, “A Single-Step Approach to Recommendation Diversification,“ In Proc. of the 26th Int’l World Wide Web Conference (WWW 2017), pp. 809-810, Perth, Australia, Apr. 03-07, 2017 (short paper).
  • Won-Seok Hwang, Juan Parc, Sang-Wook Kim, Jongwuk Lee, and Dongwon Lee, ““Told You I Didn’t Like It”: Exploiting Uninteresting Items for Effective Collaborative Filtering”, In Proc. of the 32nd IEEE Int’l Conf. on Data En gineering (IEEE ICDE 2016), pp. 349-360, Helsinki, Finland, May 16-20, 2016 (full paper).(journal 초청됨)
  • Won-Seok Hwang, Ho-Jong Lee, Sang-Wook Kim, Youngjoon Won, and Minsoo Lee, “Efficient Recommendation Methods using Category Experts for a Large Dataset,” Information Fusion, Vol. 28, No., pp. 75-82, Mar. 2016.
  • Jongwuk Lee, Dongwon Lee, Yeon-Chang Lee, Won-Seok Hwang and Sang-Wook Kim, “Improving the Accuracy of Top-N Recommendation using a Preference Model”, Information Sciences, Vol. 348, No. 20, pp. 290-304, June 2016.
  • Sang-Chul Lee, Sang-Wook Kim, and SunJu Park, “A Graph-Based Recommendation Framework for Price Comparison Services”, In Proc. of the 24th Int’l World Wide Web Conference (WWW 2015), pp.59-60, May 18-22, 2015 (short paper).