CoGraM: Context-sensitive granular optimization method with rollback for robust model fusion
Not on the map. Why?
Abstract (arXiv)
Merging neural networks without retraining is central to federated and distributed learning. Common methods such as weight averaging or Fisher merging often lose accuracy and are unstable across seeds. CoGraM (Contextual Granular Merging) is a multi-stage, context-sensitive, loss-based, and iterative optimization method across layers, neurons, and weight levels that aligns decisions with loss differences and thresholds and prevents harmful updates through rollback. CoGraM is an optimization method that addresses the weaknesses of methods such as Fisher and can significantly improve the merged network.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 14 of its 31 references that are in the map. First posted on arXiv 3 Dec 2025.
Builds on
14 of 31 references.
References · 14
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
- 2019Advances and Open Problems in Federated Learningcited by 3,046
- 2022Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference timecited by 1,396
- 2015Unsupervised Deep Embedding for Clustering Analysiscited by 767
- 2021Merging Models with Fisher-Weighted Averagingcited by 621
- 2025Modeling Multi-Task Model Merging as Adaptive Projective Gradient Descentcited by 39
- 2020Heterogeneous Federated Learningcited by 19
- 2024Understanding the Effect of Noise in LLM Training Data with Algorithmic Chains of Thoughtcited by 19
- 2024Exploring the Frontiers of Softmax: Provable Optimization, Applications in Diffusion Model, and Beyondcited by 15
- 2021On the Hyperparameters in Stochastic Gradient Descent with Momentumcited by 9
- 2024On the Impact of Data Heterogeneity in Federated Learning Environments with Application to Healthcare Networkscited by 3
Built on by
Not cited yet.