3 papers
cs.LG2025
Balancing Graph Embedding Smoothness in Self-Supervised Learning via Information-Theoretic Decomposition
Heesoo Jung, Hogun Park
Self-supervised learning (SSL) in graphs has garnered significant attention, particularly in employing Graph Neural Networks (GNNs) with pretext tasks initially designed for other…
cs.LG2025
CIMAGE: Exploiting the Conditional Independence in Masked Graph Auto-encoders
Jongwon Park, Heesoo Jung, Hogun Park
Recent Self-Supervised Learning (SSL) methods encapsulating relational information via masking in Graph Neural Networks (GNNs) have shown promising performance. However, most exist…
cs.AI2024
Improving Multi-hop Logical Reasoning in Knowledge Graphs with Context-Aware Query Representation Learning
Jeonghoon Kim, Heesoo Jung, Hyeju Jang +1
Multi-hop logical reasoning on knowledge graphs is a pivotal task in natural language processing, with numerous approaches aiming to answer First-Order Logic (FOL) queries. Recent…