Prof. Ha-Myung Park - Kookmin University AI·SW Graduate School

Research Overview연구 개요

Research focuses on efficient data mining, AI model compression, and vector databases. The lab develops scalable algorithms for large-scale data processing, including distributed graph algorithms and high-dimensional proximity search.

대규모 데이터의 효율적 마이닝, AI 모델 압축, 벡터 데이터베이스를 연구합니다. 분산 그래프 알고리즘과 고차원 근접 탐색 등 대규모 데이터 처리를 위한 확장 가능한 알고리즘을 개발합니다.

Research Areas연구 분야

Efficient Data Mining
AI Model Compression
Vector Database
Distributed Graph Algorithms

효율적 데이터 마이닝
AI 모델 압축
벡터 데이터베이스
분산 그래프 알고리즘

Major Achievements주요 연구 성과

SkySearch: Satellite Video Search at Scale (KDD 2025)
BTS: Load-Balanced Distributed Union-Find (ICDE 2024)
Distributed Approximate k-NN Graph Construction (KDD 2023)

Honors & Awards수상

Naver PhD Fellowship Award, 2016
HumanTech Award - Silver, Samsung, 2016
IEEE ICDM 2016 Student Travel Award

Recent Publications주요 논문

Ha-Myung Park, Jungeun Park, Chaewon Jeong, Woncheol Son, Yunjun Kim, Junseo Youn, Ki Yeon Park, "EPTQ: Fast and Accurate 2-bit Post-Training Quantization via Factored E8 Lattice," ACM International Conference on Information and Knowledge Management (CIKM), 2026
Wooseong Cho, Ha-Myung Park, "S3-Prompt: Resolving Activity Cliffs via Structure-Disentangled Molecular Graph-Text Alignment," ACM International Conference on Information and Knowledge Management (CIKM), 2026
Min-Hyoung Kim, Ha-Myung Park, "COSMO: Contrastive Satellite Image Embedding Techniques Reflecting Expert Weather Bulletins," IEEE Access, Vol. 14, pp. 92385-92398, 2026 원문 ↗Paper ↗
YoungJun Lee, Ha-Myung Park, "Efficient Reconstruction of Masked Image Embeddings for Region-Specific Satellite Image Retrieval," IEEE Access, 2026
Jisoo Kang, Changhun Han, Suji Kim, Ha-Myung Park, "Efficient Time-Restricted k NN Search in High-Dimensional Data Using Multi-Level Block Indexing, with Extensions to Multi-Attribute Filtering," ACM Transactions on Knowledge Discovery from Data, Vol. 20, No. 3, pp. 1-30, 2026 원문 ↗Paper ↗
M. Choe, G. Lee, C. Han, S. Kim, W. Hu, H. Hwang, G. Park, B. Kim, H. Lee, H.-M. Park, and K. Shin, "SkySearch: Satellite Video Search at Scale," KDD, 2025
C. Kim, C. Han, and H.-M. Park, "BTS: Load-Balanced Distributed Union-Find for Finding Connected Components with Balanced Tree Structures," IEEE ICDE, 2024
C. Han, S. Kim, and H.-M. Park, "Efficient Proximity Search in Time-evolving High-dimensional Data using Multi-level Block Indexing," EDBT, 2024
I. Abdulhakin, and H.-M. Park, "Latent Representation Generation for Efficient Content-Based Image Retrieval in Weather Satellite Images Using Self-Supervised Segmentation", BigComp, 2024
H. Park, and H.-M. Park, "Enhancing Heterophilic Graph Neural Network Performance through Label Propagation in K-Nearest Neighbor Graphs", BigComp, 2024
S. Kim and H.-M. Park, "Efficient Distributed Approximate k-Nearest Neighbor Graph Construction by Multiway Random Division Forest," KDD, 2023
C. Kim, C. Han, and H.-M. Park, "UniCon: A Unified Star-Operation to Efficiently Find Connected Components on a Cluster of Commodity Hardware," PLOS ONE, 2022
J. Jung, H.-M. Park, and U Kang, "BalanSiNG: Fast and Scalable Generation of Realistic Signed Networks," EDBT, 2020
H.-M. Park, N. Park, S.-H. Myaeng, and U Kang, "PACC: Large Scale Connected Component Computation on Hadoop and Spark," PLOS ONE, 2020
J. Jung, W. Jin, H.-M. Park, and U Kang, "Accurate Relational Reasoning in Edge-labeled Graphs by Multi-Labeled Random Walk with Restart," World Wide Web Journal, 2020