연구실 정보를 불러오고 있습니다
Ho-Gun Park
성균관대학교 소프트웨어학과
Machine Learning, Explainable AI(XAI), Knowledge Discovery, Relational learning, Graph Mining, Trustworthy AI
LearnData laboratory
hogunpark@skku.edu
Develop novel graph neural network/transformer architectures, self-supervised graph representation methods, and federated graph learning frameworks addressing knowledge graph reasoning, recommendation systems, and node/graph-level representation learning.
Build AI systems that are transparent, robust, and grounded in structured knowledge through explainability methods for graph neural networks, knowledge-based LLM steering, adversarial robustness techniques, and watermarking methods.
Low-pass Personalized Subgraph Federated Recommendation
Balancing Graph Embedding Smoothness in Self-Supervised Learning via Information-Theoretic Decomposition
CIMAGE: Exploiting the Conditional Independence in Masked Graph Auto-encoders
Exploiting Relation-aware Attribute Representation Learning in Knowledge Graph Embedding for Numerical Reasoning
M³KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation
Judo: A Juxtaposed Domain-oriented Multimodal Reasoner for Industrial Anomaly QA
Self-supervised Adversarial Purification for Graph Neural Networks
Harnessing Influence Function in Explaining Graph Neural Networks
Complex Reasoning in Knowledge Graph Question Answering Through Query Graph Approximation
MAMS: Model-Agnostic Module Selection Framework for Video Captioning
UNR-Explainer: Counterfactual Explanations for Unsupervised Node Representation Learning Models
Generating Post-hoc Explanations for Skip-gram-based Node Embeddings by Identifying Important Nodes with Bridgeness
출처: 연구실 홈페이지
현재 재학생
16명
최근 5년 졸업
0명
학위 과정 분포: 석사 7명, 석박통합 1명, 박사 8명 (대학원 16명)
대학원 16명 · 포닥·학부연구생 2명 별도
본 페이지는 연구실 규모 파악을 위한 집계 통계(구성원 수, 진로 카테고리, 학위 과정 분포)만 제공하며, 개별 학생의 이름·전적·취업처 등은 표시하지 않습니다. 학위 과정 분포는 모든 재학생의 과정이 명확히 분류된 경우에만 표시되며 (분류 미상 학생이 1명이라도 있으면 미표시), k≥5 익명성 조건을 충족할 때만 공개됩니다 (PIPA §58-2·§28-2 + 대법원 2014다235080).
수집 중
수집 중
논문 데이터가 수집되면 연구 키워드가 자동 추출됩니다