Domain Expansion: Parameter-Efficient Modules as Building Blocks for Composite Domains
Parameter-Efficient Fine-Tuning (PEFT) is an efficient alternative to full scale fine-tuning, gaining popularity recently. With pre-trained model sizes growing exponentially, PEFT can be effectively utilized to fine-tune compact modules, Parameter-Efficient Modules (PEMs), trained to be domain experts over diverse domains. In this project, we explore composing such individually fine-tuned PEMs for distribution generalization over the composite domain. To compose PEMs, simple composing functions are used that operate purely on the weight space of the individually fine-tuned PEMs, without requiring any additional fine-tuning. The proposed method is applied to the task of representing the 16 Myers-Briggs Type Indicator (MBTI) composite personalities via 4 building block dichotomies, comprising of 8 individual traits which can be merged (composed) to yield a unique personality. We evaluate the individual trait PEMs and the composed personality PEMs via an online MBTI personality quiz questionnaire, validating the efficacy of PEFT to fine-tune PEMs and merging PEMs without further fine-tuning for domain composition.
Code (1)
Tasks
parameter-efficient fine-tuningSimilar Papers 제목 키워드 기반
NeMo: a toolkit for building AI applications using Neural Modules
NeMo (Neural Modules) is a Python framework-agnostic toolkit for creating AI applications through re-usability, abstraction, and composition. NeMo is built around neural modules, conceptual blocks of neural networks that…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech RecognitionBiO-Net: Learning Recurrent Bi-directional Connections for Encoder-Decoder Architecture
U-Net has become one of the state-of-the-art deep learning-based approaches for modern computer vision tasks such as semantic segmentation, super resolution, image denoising, and inpainting. Previous extensions of U-Net …
DecoderDenoisingImage DenoisingMedical Image Analysis+2SynLlama: Generating Synthesizable Molecules and Their Analogs with Large Language Models
Generative machine learning models for small molecule drug discovery have shown immense promise, but many molecules they generate are too difficult to synthesize, making them impractical for further investigation or deve…
Drug DiscoveryCompositional Models: Multi-Task Learning and Knowledge Transfer with Modular Networks
Conditional computation and modular networks have been recently proposed for multitask learning and other problems as a way to decompose problem solving into multiple reusable computational blocks. We propose a new appro…
Domain Adaptationimage-classificationImage ClassificationMulti-Task Learning+1Speeding Up EfficientNet: Selecting Update Blocks of Convolutional Neural Networks using Genetic Algorithm in Transfer Learning
The performance of convolutional neural networks (CNN) depends heavily on their architectures. Transfer learning performance of a CNN relies quite strongly on selection of its trainable layers. Selecting the most effecti…
Transfer Learning