Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Beyond Binary: Turning Partial Success into Dense Verifiable Rewards for Reinforcement Learning in Code Generation
Longwen Wang, Yirui Liu, Xuan'er Wu +6
Effective reward design is a central challenge in Reinforcement Learning (RL) for code generation. Mainstream test-suite-level outcome rewards enforce functional correctness but in…
cs.LG2024
Optimizing Federated Graph Learning with Inherent Structural Knowledge and Dual-Densely Connected GNNs
Longwen Wang, Jianchun Liu, Zhi Liu +1
Federated Graph Learning (FGL) is an emerging technology that enables clients to collaboratively train powerful Graph Neural Networks (GNNs) in a distributed manner without exposin…