gradient aggregation

Revealing Procedural Reasoning Structures in Chain-of-Thought Training via Span-Level Gradient Organization ACL 2026 Co-Dream: Collaborative Dream Synthesis over Decentralized Models AAAI 2025 Conflict-Averse Gradient Aggregation for Constrained Multi-Objective Reinforcement Learning ICLR 2025 On the Convergence of Continual Federated Learning Using Incrementally Aggregated Gradients AISTATS 2025 Revisiting Fairness in Multitask Learning: A Performance-Driven Approach for Variance Reduction CVPR 2025 Towards Consistent Multi-Task Learning: Unlocking the Potential of Task-Specific Parameters CVPR 2025 Batch-ICL: Effective, Efficient, and Order-Agnostic In-Context Learning ACL 2024 Bayesian Uncertainty for Gradient Aggregation in Multi-Task Learning ICML 2024 Byzantine-Robust Decentralized Learning via Remove-then-Clip Aggregation AAAI 2024 Fairness-Aware Meta-Learning via Nash Bargaining NeurIPS 2024 Internal Cross-layer Gradients for Extending Homogeneity to Heterogeneity in Federated Learning ICLR 2024 Leveraging partial stragglers within gradient coding NeurIPS 2024 Mitigating Catastrophic Forgetting in Online Continual Learning by Modeling Previous Task Interrelations via Pareto Optimization ICML 2024 Multi-Dimensional Fair Federated Learning AAAI 2024 Robust Distributed Gradient Aggregation Using Projections onto Gradient Manifolds AAAI 2024 Tolerating Outliers: Gradient-Based Penalties for Byzantine Robustness and Inclusion IJCAI 2024 Towards the Robustness of Differentially Private Federated Learning AAAI 2024 A General Theory for Federated Optimization with Asynchronous and Heterogeneous Clients Updates JMLR 2023 Enhancing Generalization of Universal Adversarial Perturbation through Gradient Aggregation ICCV 2023 Global Balanced Experts for Federated Long-Tailed Learning ICCV 2023 Industry-Scale Orchestrated Federated Learning for Drug Discovery AAAI 2023 RECESS Vaccine for Federated Learning: Proactive Defense Against Model Poisoning Attacks NeurIPS 2023 FedProto: Federated Prototype Learning across Heterogeneous Clients AAAI 2022 GBA: A Tuning-free Approach to Switch between Synchronous and Asynchronous Training for Recommendation Models NeurIPS 2022 Model Doctor: A Simple Gradient Aggregation Strategy for Diagnosing and Treating CNN Classifiers AAAI 2022