gradient similarity

Revisiting LocalSGD and SCAFFOLD: Improved Rates and Missing Analysis AISTATS 2025 TreeLoRA: Efficient Continual Learning via Layer-Wise LoRAs Guided by a Hierarchical Gradient-Similarity Tree ICML 2025 Why Does New Knowledge Create Messy Ripple Effects in LLMs? EMNLP 2024 Adversarial Robustness through Random Weight Sampling NeurIPS 2023 GradSim: Gradient-Based Language Grouping for Effective Multilingual Training EMNLP 2023 Adaptive Meta-learner via Gradient Similarity for Few-shot Text Classification COLING 2022 Analyzing and Mitigating Interference in Neural Architecture Search ICML 2022 Investigating Parameter Sharing in Multilingual Speech Translation Interspeech 2022 Parameter Differentiation Based Multilingual Neural Machine Translation AAAI 2022 Evaluation of Similarity-based Explanations ICLR 2021 Gradient Vaccine: Investigating and Improving Multi-task Optimization in Massively Multilingual Models ICLR 2021 SimiGrad: Fine-Grained Adaptive Batching for Large Scale Training using Gradient Similarity Measurement NeurIPS 2021 Student Customized Knowledge Distillation: Bridging the Gap Between Student and Teacher ICCV 2021 Optimizing Data Usage via Differentiable Rewards ICML 2020 Using Priming to Uncover the Organization of Syntactic Representations in Neural Language Models CoNLL 2019