paper-with-me

홈 › Papers

Derivative Free Weight-space Ensembling

2023-07-07 · Dean Ninalga

Recent work suggests that interpolating between the weights of two specialized language models can transfer knowledge between tasks in a way that multi-task learning cannot. However, very few have explored interpolation between more than two models, where each has a distinct knowledge base. In this paper, we introduce Derivative Free Weight-space Ensembling (DFWE), a new few-sample task transfer approach for open-domain dialogue. Our framework creates a set of diverse expert language models trained using a predefined set of source tasks. Next, we finetune each of the expert models on the target task, approaching the target task from several distinct knowledge bases. Finally, we linearly interpolate between the model weights using a gradient-free-optimization algorithm, to efficiently find a good interpolation weighting. We demonstrate the effectiveness of the method on FETA-Friends outperforming the standard pretrain-finetune approach.

📄 PDF Abstract BibTeX arXiv:2307.03506

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-Task Learning

Similar Papers 제목 키워드 기반

MASS: MoErging through Adaptive Subspace Selection

2025-04-06 · Donato Crisostomi, Alessandro Zirilli, Antonio Andrea Gargiulo, Maria Sofia Bucarelli 외

Model merging has recently emerged as a lightweight alternative to ensembling, combining multiple fine-tuned models into a single set of parameters with no additional training overhead. Yet, existing merging methods fall…

image-classificationImage Classification

On Defining Neural Averaging

2025-08-20 · Su Hyeong Lee, Richard Ngo arxiv

What does it even mean to average neural networks? We investigate the problem of synthesizing a single neural network from a collection of pretrained models, each trained on disjoint data shards, using only their final w…

Clip-Tuning: Towards Derivative-free Prompt Learning with a Mixture of Rewards

2022-10-21 · Yekun Chai, Shuohuan Wang, Yu Sun, Hao Tian 외

Derivative-free prompt learning has emerged as a lightweight alternative to prompt tuning, which only requires model inference to optimize the prompts. However, existing work did not take full advantage of the over-param…

Prompt Learning

Derivative-Informed Projected Neural Networks for High-Dimensional Parametric Maps Governed by PDEs

2020-11-30 · Thomas O'Leary-Roseberry, Umberto Villa, Peng Chen, Omar Ghattas

Many-query problems, arising from uncertainty quantification, Bayesian inversion, Bayesian optimal experimental design, and optimization under uncertainty-require numerous evaluations of a parameter-to-output map. These …

Experimental DesignUncertainty Quantification

Weighted universal approximation of differentiable maps on infinite-dimensional manifolds

2026-06-08 · Philipp Schmocker, Josef Teichmann arxiv

We generalize the universal approximation theorem for functional input neural networks (FNN) to differentiable maps by including the approximation of the derivatives. A FNN maps the input from a possibly infinite-dimensi…