Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Weisfeiler and Lehman Go Categorical
Seongjin Choi, Gahee Kim, Se-Young Yun
While lifting map has significantly enhanced the expressivity of graph neural networks, extending this paradigm to hypergraphs remains fragmented. To address this, we introduce the…
cs.LG2024
Diffusion-based Episodes Augmentation for Offline Multi-Agent Reinforcement Learning
Jihwan Oh, Sungnyun Kim, Gahee Kim +2
Offline multi-agent reinforcement learning (MARL) is increasingly recognized as crucial for effectively deploying RL algorithms in environments where real-time interaction is impra…
cs.LG2023
Non-backtracking Graph Neural Networks
Seonghyun Park, Narae Ryu, Gahee Kim +3
The celebrated message-passing updates for graph neural networks allow representing large-scale graphs with local and computationally tractable updates. However, the updates suffer…