Papers › Fisher Mask Nodes for Language Model Merging

Fisher Mask Nodes for Language Model Merging

14 Mar 2024arXiv:2403.09891archive 2025-07-28

Thennal D K, Ganesh Nathan, Suchithra M S

Fine-tuning pre-trained models provides significant advantages in downstream performance. The ubiquitous nature of pre-trained models such as BERT and its derivatives in natural language processing has also led to a proliferation of task-specific fine-tuned models. As these models typically only perform one task well, additional training or ensembling is required in multi-task scenarios. The growing field of model merging provides a solution, dealing with the challenge of combining multiple task-specific models into a single multi-task model. In this study, we introduce a novel model merging method for Transformers, combining insights from previous work in Fisher-weighted averaging and the use of Fisher information in model pruning. Utilizing the Fisher information of mask nodes within the Transformer architecture, we devise a computationally efficient weighted-averaging scheme. Our method exhibits a regular and significant performance increase across various models in the BERT family, outperforming full-scale Fisher-weighted averaging in a fraction of the computational cost, with baseline performance improvements of up to +6.5 and a speedup between 57.4x and 321.7x across models. Our results prove the potential of our method in current multi-task learning environments and suggest its scalability and adaptability to new model architectures and learning scenarios.

Paper PDF Code

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

thennal10/fisher-nodes-merging officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Language Modeling Language Modelling Multi-Task Learning model

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position Encodings Adam Attention Attention Dropout BERT BPE Dense Connections Dropout Label Smoothing Layer Normalization Linear Layer Linear Warmup With Linear Decay Multi-Head Attention Position-Wise Feed-Forward Layer Residual Connection Softmax Transformer Weight Decay WordPiece

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections