Embedded Files
"AI For Good"
OUR Mission: Make AI More ACcessible, Scalable & Reliable
OUR Mission: Make AI More ACcessible, Scalable & Reliable
Our group is dedicated to advancing machine learning (ML) technologies using Big Data. Our research spans key areas such as machine learning, data mining, databases, and computational theory.
Our primary focus is on enhancing the accessibility, scalability, and reliability of learned knowledge in large-scale AI models, including deep neural networks (DNNs). Specifically, we aim to address the following academic challenges:
(Accessibility) How can we extract, reuse, and explain the knowledge learned by trained DNNs?
(Scalability) How can we continually, incrementally, and efficiently update a trained DNN?
(Reliability) How can we repair or reorganize erroneously learned knowledge within DNNs?
In the academic perspective, we always pursue research of the highest quality in theory as well as in practice, and attempt to publish solid papers in top-tier venues in the fields of machine learning and big data, including ICML, NeurIPS, ICLR, AAAI, KDD, ICDM, SIGMOD, VLDB, ICDE, etc. For a comprehensive list of top-tier conferences and journals, please refer to the following Google Scholar pages: Artificial Intelligence, Data Mining & Analysis, and Databases & Information Systems.
Big Data Lab @ Inha University (한국어)
Big Data Lab @ Inha University (English Version)
LATEST NEWS
LATEST NEWS
[Jan 2025] A paper has been accepted in Neural Networks, a prestigious journal in the field of deep learning.
[Jan 2025] A paper has been accepted in Neural Networks, a prestigious journal in the field of deep learning.
Our paper, "Out-of-Distribution Detection via Outlier Exposure in Federated Learning," (1st author: Gu-Bon Jeong, MS alumnus) has been accepted for publication in Neural Networks, which is a prestigious SCIE journal (IF 6.0) in deep learning. Well deserved, Gu-Bon!
[Dec 2024] Seongsoo won the Best Paper Award at KSC 2024.
[Dec 2024] Seongsoo won the Best Paper Award at KSC 2024.
Seongsoo Heo (MS Student) won the Best Paper Award (최우수논문상) at the KSC 2024 conference in the field of AI and Theory for our paper, "Enhancing Robustness of Sparse Model Inversion in Data-Free Applications through Attention Entropy Minimization (어텐션 엔트로피 최소화를 통한 데이터 없는 적용에서 희소 모델 인버전의 강건성 향상 방법론)." Congratulations to Seongsoo!
[Apr 2024] A paper has been accepted in CoLLAs 2024, a rising conference in continual learning.
[Apr 2024] A paper has been accepted in CoLLAs 2024, a rising conference in continual learning.
Our paper, "Replaying with Realistic Latent Vectors in Generative Continual Learning," (1st author: Hyemin Jeong, MS alumnus) has been accepted for the CoLLAs 2024 conference, which is a rapidly evolving conference in the specific field of Continual Learning. Congratulations to Hyemin!
[Dec 2023] Yunseok won an Outstanding Papers Award at KSC 2023.
[Dec 2023] Yunseok won an Outstanding Papers Award at KSC 2023.
Yunseok Oh (MS Student) won an Outstanding Papers Award (우수논문상) at the KSC 2023 conference in the field of AI for our paper, "Efficient Prompt Learning Method in Blurry Class Incremental Learning Environment (Blurry 클래스 증분 학습 환경에서의 효율적인 프롬프트 학습 방법)." Congratulations to Yunseok!
[Dec 2023] Two papers have been accepted in AAAI 2024, a top-tier conference in the field of AI.
[Dec 2023] Two papers have been accepted in AAAI 2024, a top-tier conference in the field of AI.
For AAAI 2024, the following two papers are accepted within our lab.
"Recall-Oriented Continual Learning with Generative Adversarial Meta-Model" (1st author: Haneol Kang, MS alumnus)
"Teacher as a Lenient Expert: Teacher-Agnostic Data-Free Knowledge Distillation" (1st author: Hyunjune Shin, MS candidate)
Congratulations to Haneol and Hyunjune!
Vacancies
Vacancies
We are consistently seeking highly talented and motivated individuals to join our research group as BS, MS or PhD students. If you are interested in working with us on cutting-edge research in the field of Big Data & Machine Learning, please email Prof. Choi your CV, transcript, and hopefully a short statement of your research interests.
빅데이터 연구실에서는 학부연구생, 석사과정, 박사과정 학생을 모집하고 있습니다. 대학원 진학 및 연구실에 대해서 관심이 있는 학생들은 dchoi@inha.ac.kr로 CV와 간단한 연구(학업)계획서를 첨부해서 이메일을 보내기 바랍니다.
Google Sites
Report abuse