据官方微博，ICML 2021官方今日发布接收论文，共有5513篇论文投稿，共有1184篇接受（包括1018篇短论文和166篇长论文），接受率21.48%。
成为VIP会员查看完整内容
EMaQ: Expected-Max Q-Learning Operator for Simple Yet Effective Offline and Online RL
Policy Information Capacity: Information-Theoretic Measure for Task Complexity in Deep Reinforcement Learning，
Supervised Tree-Wasserstein Distance
Lipschitz Normalization for Self-Attention Layers with Application to Graph Neural Networks
等变图神经网络，E(n) Equivariant Graph Neural Networks
图神经网络优化，Optimization of Graph Neural Networks: Implicit Acceleration by Skip Connections and More Depth
图神经网络加速训练，GraphNorm: A Principled Approach to Accelerating Graph Neural Network Training
图对抗网络，Information Obfuscation of Graph Neural Networks
因果表示学习，Causal Curiosity: RL Agents Discovering Self-supervised Experiments for Causal Representation Learning
元强化学习，Exploration in Approximate Hyper-State Space for Meta Reinforcement Learning
联邦持续学习，Federated Continual Learning with Weighted Inter-client Transfer
带不确定性的领域不变学习，A Bit More Bayesian: Domain-Invariant Learning with Uncertainty
领域自适应标签传播理论Theory of Label Propagation for Domain Adaptation
MC-LSTM: Mass-Conserving LSTM
特征属性形式化，Towards Rigorous Interpretations: a Formalisation of Feature Attribution
消息传递简单网络，Weisfeiler and Lehman Go Topological: Message Passing Simplicial Networks
剖监督对比学习，Dissecting Supervised Constrastive Learning
不平衡小批量最优传输;域自适应的应用，Unbalanced minibatch Optimal Transport; applications to Domain Adaptation
复杂行动空间中的学习与规划，Learning and Planning in Complex Action Spaces
神经A*搜索的路径规划，Path Planning using Neural A* Search
有向偏差放大，Directional Bias Amplification
现代强化学习，Revisiting Peng’s Q(λ) for Modern Reinforcement Learning
池化注意力的长文档建模，Poolingformer: Long Document Modeling with Pooling Attention
分子图神经网络可解释性，Improving Molecular Graph Neural Network Explainability with Orthonormalization and Induced Sparsity
相关内容
Arxiv
0+阅读 · 2021年6月22日
Arxiv
14+阅读 · 2018年10月11日
相关VIP内容
相关资讯
相关论文
Arxiv
0+阅读 · 2021年6月22日
Arxiv
14+阅读 · 2018年10月11日
微信扫码咨询专知VIP会员