cs.LG（2024-08-13）

📊 共 7 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

#	题目	一句话要点	标签	🔗
1	Prioritizing Modalities: Flexible Importance Scheduling in Federated Multimodal Learning	提出FlexMod以解决多模态联邦学习中的资源分配问题	reinforcement learning deep reinforcement learning multimodal
2	DyG-Mamba: Continuous State Space Modeling on Dynamic Graphs	提出DyG-Mamba，将动态图建模转化为序列建模，有效捕捉长期依赖关系。	Mamba state space model	✅
3	Solving Truly Massive Budgeted Monotonic POMDPs with Oracle-Guided Meta-Reinforcement Learning	提出基于Oracle引导的元强化学习方法，解决大规模预算约束单调POMDP问题	reinforcement learning PPO
4	Class-aware and Augmentation-free Contrastive Learning from Label Proportion	提出TabLLP-BDC框架，解决表格数据标签比例学习中无数据增强和类别区分难题。	representation learning contrastive learning

#	题目	一句话要点	标签	🔗
5	A Self-Supervised Paradigm for Data-Efficient Medical Foundation Model Pre-training: V-information Optimization Framework	提出OptiDEL框架，通过V-信息优化实现医学Foundation Model高效自监督预训练。	foundation model
6	Proficient Graph Neural Network Design by Accumulating Knowledge on Large Language Models	提出DesiGNN框架以解决GNN设计中的知识积累问题	large language model
7	Towards Robust and Parameter-Efficient Knowledge Unlearning for LLMs	提出LoKU框架，实现LLM的鲁棒、高效且参数高效的知识遗忘	large language model	✅