Seungcheol Park

Huiwen Xu

Hyunsik Jeon

Jun-gi Jang

Jaemin Yoo

Jinhong Jung

Ha-Myung Park

Yongsub Lim

Hyunwoo Lee

Sojin Lee

Chanhee Park

Jin-gee Kim

Doyeon Kim

Jiyun Kim

Sooyeon Shim

Hyojin Jeon

Jaemin Park

Vladimir Egay

Minyong Cho

Tairen Piao

Junghoon Kim

Chaeheum Park

Jay Lee

Shuyu Wang

Bonhun Koo

Chun Quan

Yang Bai

Minsoo Jung

Chiwan Park

Inah Jeon

Ho Lee

The Data Mining Laboratory, part of the Department of Computer Science and Engineering at Seoul National University, focuses on artificial intelligence (AI), data mining, and machine learning. The laboratory aims to discover models, algorithms, and systems for data analysis, with specific research interests in deep learning, machine learning, recommender systems, QA systems, graphs/tensors, and financial AI.

서울대학교 컴퓨터공학과 데이터 마이닝 연구실은 인공지능, 데이터 마이닝, 머신러닝을 주요 연구 분야로 한다. 데이터 분석을 위한 모델, 알고리즘, 시스템 개발을 목표로 하며, 특히 딥러닝, 머신러닝, 추천 시스템, QA 시스템, 그래프/텐서, 금융 AI에 대한 연구를 수행한다.

Fast and Accurate Temporal Super-Resolution via Residual-Aware Coupled Tensor Factorization

Shift-Tolerant Allocation via Black-Litterman Using Conditional Diffusion Estimates

Prune-then-Quantize or Quantize-then-Prune? Understanding the Impact of Compression Order in Joint Model Compression

Dual-level Reweighting for Positive-Unlabeled Graph Classification

Fast and Accurate Online Coupled Matrix-Tensor Factorization via Frequency Regularization

LampQ: Towards Accurate Layer-wise Mixed Precision Quantization for Vision Transformers

Diffusion Models for Risk-Aware Portfolio Optimization

PiGLeT: Probabilistic Message Passing for Semi-supervised Link Sign Prediction

SwaGNER: Leveraging Span-aware Grid Transformers for Accurate Nested Named Entity Recognition

Entity-Aware Generative Retrieval for Personalized Contexts

Mitigating Distribution Shift in Stock Price Data via Return-Volatility Normalization for Accurate Prediction

Context-aware Sequential Bundle Recommendation via User-specific Representations

Unifying Uniform and Binary-coding Quantization for Accurate Compression of Large Language Models

PuzzleTensor: A Method-Agnostic Data Transformation for Compact Tensor Factorization

Accurate Graph-based Multi-Positive Unlabeled Learning via Disentangled Multi-view Feature Propagation

Zero-shot Quantization: A Comprehensive Survey

Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information

AugWard: Augmentation-Aware Representation Learning for Accurate Graph Classification

DART: Diversified and Accurate Long-Tail Recommendation

SynQ: Accurate Zero-shot Quantization by Synthesis-aware Fine-tuning

Accurate Link Prediction for Edge-Incomplete Graphs via PU Learning

Sequentially Diversified and Accurate Recommendations in Chronological Order for a Series of Users

Offline and Online Coupled Tensor Factorization with Knowledge Graph

Accurate Semi-supervised Automatic Speech Recognition for Ordinary and Characterized Speeches via Multi-hypotheses-based Curriculum Learning

Threshold-Based Exploitation of Noisy Label in Black-box Unsupervised Domain Adaptation

Accurate multi-behavior sequence-aware recommendation via graph convolution networks

GATSBY: Graph Attention with Seasonality and Behavioral Yield

Multi-hop Graph Convolutional Networks for Accurate Node Classification

Representing Bundles with Co-Occurrence Entropy of Items for Bundle Recommendation

Exploring Graph Rewiring for Node Classification under Relational Tendency Shift

A Survey on KV Cache Compression Techniques in Large Language Models

StaRes: Stable Residual Forecasting Network for Alleviating Distribution Shift in Time Series

Relation-aware Temporal Knowledge Graph Sampling Method

Analysis of Sequential Recommendation Performance by Large Language Models Without Collaborative Filtering

Item-Level Masking Technique for Addressing Data Sparsity in Sequential Bundle Recommendation

Cold-start Bundle Recommendation via Popularity-based Coalescence and Curriculum Heating

Towards True Multi-interest Recommendation: Enhanced Scheme for Balanced Interest Training

Accurate Stock Movement Prediction via Multi-Scale and Multi-Domain Modeling

Accurate Coupled Tensor Factorization with Knowledge Graph

Fast and Accurate PARAFAC2 Decomposition for Time Range Queries on Irregular Tensors

Domain-Aware Data Selection for Speech Classification via Meta-Reweighting

FreQuant: A Reinforcement-Learning based Adaptive Portfolio Optimization with Multi-frequency Decomposition

Fast Multidimensional Partial Fourier Transform with Automatic Hyperparameter Selection

Fast and Accurate Domain Adaptation for Irregular Tensor Decomposition

Accurate Semi-supervised Automatic Speech Recognition via Multi-hypotheses-based Curriculum Learning

Accurate Retraining-free Pruning for Pretrained Encoder-based Language Models

Representative and Back-In-Time Sampling from Real-world Hypergraphs

DDC3N: Doppler-Driven Convolutional 3D Network for Human Action Recognition

Dependency-Aware Action Planning for Smart Home

Accurate graph classification via two-staged contrastive curriculum learning

Fast and Accurate Transferability Measurement by Evaluating Intra-class Feature Variance

Fast and Accurate Dual-Way Streaming PARAFAC2 for Irregular Tensors - Algorithm and Application

Aggregately Diversified Bundle Recommendation via Popularity Debiasing and Configuration-aware Reranking

Diversely Regularized Matrix Factorization for Accurate and Aggregately Diversified Recommendation

PET: Parameter-efficient Knowledge Distillation on Transformer

Accurate Open-set Recognition for MemoryWorkload

Fast and Accurate Interpretation of Workload Classification Model

Accurate Bundle Matching and Generation via Multitask Learning with Partially Shared Parameters

Falcon: Lightweight and Accurate Convolution Based on Depthwise Separable Convolution

Accurate Stock Movement Prediction with Self-supervised Learning from Sparse Noisy Tweets

Accurate PARAFAC2 Decomposition for Temporal Irregular Tensors with Missing Values

Accurate Action Recommendation for Smart Home via Two-Level Encoders and Commonsense Knowledge

Data Mining Lab

교수님 소개

강우

연구실 소개

연구실 키워드

알럼나이가 간 회사

연구실 지원 방법

대우 조건

연도별 논문 인용수

저널 & 학회 논문 출판 수

연구실 논문 목록

Fast and Accurate Temporal Super-Resolution via Residual-Aware Coupled Tensor Factorization

Shift-Tolerant Allocation via Black-Litterman Using Conditional Diffusion Estimates

Prune-then-Quantize or Quantize-then-Prune? Understanding the Impact of Compression Order in Joint Model Compression

연구실 보유 특허

대학별 입시끈

우리 연구실 모집

교수님 소개

강우

연구실 키워드

알럼나이가 간 회사

연구실 지원 방법

대우 조건

연도별 논문 인용수

저널 & 학회 논문 출판 수

연구실 논문 목록

Fast and Accurate Temporal Super-Resolution via Residual-Aware Coupled Tensor Factorization

Shift-Tolerant Allocation via Black-Litterman Using Conditional Diffusion Estimates

Prune-then-Quantize or Quantize-then-Prune? Understanding the Impact of Compression Order in Joint Model Compression

연구실 보유 특허

최근 3년간 연구실적 높은 연구실

대학별 입시끈

우리 연구실 모집