MixPHM: Redundancy-Aware Parameter-Efficient Tuning for Low-Resource
Visual Question Answering
- URL: http://arxiv.org/abs/2303.01239v2
- Date: Wed, 7 Jun 2023 12:02:51 GMT
- Title: MixPHM: Redundancy-Aware Parameter-Efficient Tuning for Low-Resource
Visual Question Answering
- Authors: Jingjing Jiang, Nanning Zheng
- Abstract summary: Finetuning pretrained Vision-Language Models (VLMs) has been a prevailing paradigm for achieving state-of-the-art performance in Visual Question Answering (VQA)
Current parameter-efficient tuning methods dramatically reduce the number of tunable parameters, but there still exists a significant performance gap with full finetuning.
We propose MixPHM, a redundancy-aware parameter-efficient tuning method that outperforms full finetuning in low-resource VQA.
- Score: 66.05768870785548
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Recently, finetuning pretrained Vision-Language Models (VLMs) has been a
prevailing paradigm for achieving state-of-the-art performance in Visual
Question Answering (VQA). However, as VLMs scale, finetuning full model
parameters for a given task in low-resource settings becomes computationally
expensive, storage inefficient, and prone to overfitting. Current
parameter-efficient tuning methods dramatically reduce the number of tunable
parameters, but there still exists a significant performance gap with full
finetuning. In this paper, we propose MixPHM, a redundancy-aware
parameter-efficient tuning method that outperforms full finetuning in
low-resource VQA. Specifically, MixPHM is a lightweight module implemented by
multiple PHM-experts in a mixture-of-experts manner. To reduce parameter
redundancy, MixPHM reparameterizes expert weights in a low-rank subspace and
shares part of the weights inside and across experts. Moreover, based on a
quantitative redundancy analysis for adapters, we propose Redundancy
Regularization to reduce task-irrelevant redundancy while promoting
task-relevant correlation in MixPHM representations. Experiments conducted on
VQA v2, GQA, and OK-VQA demonstrate that MixPHM outperforms state-of-the-art
parameter-efficient methods and is the only one consistently surpassing full
finetuning.
Related papers
- RoSTE: An Efficient Quantization-Aware Supervised Fine-Tuning Approach for Large Language Models [95.32315448601241]
We propose an algorithm named Rotated Straight-Through-Estimator (RoSTE)
RoSTE combines quantization-aware supervised fine-tuning (QA-SFT) with an adaptive rotation strategy to reduce activation outliers.
Our findings reveal that the prediction error is directly proportional to the quantization error of the converged weights, which can be effectively managed through an optimized rotation configuration.
arXiv Detail & Related papers (2025-02-13T06:44:33Z) - FreqMixFormerV2: Lightweight Frequency-aware Mixed Transformer for Human Skeleton Action Recognition [9.963966059349731]
FreqMixForemrV2 is built upon the Frequency-aware Mixed Transformer (FreqMixFormer) for identifying subtle and discriminative actions.
The proposed model achieves a superior balance between efficiency and accuracy, outperforming state-of-the-art methods with only 60% of the parameters.
arXiv Detail & Related papers (2024-12-29T23:52:40Z) - FineGates: LLMs Finetuning with Compression using Stochastic Gates [7.093692674858257]
Large Language Models (LLMs) present significant challenges for full finetuning due to the high computational demands.
Lightweight finetuning techniques have been proposed, like learning low-rank adapter layers.
We propose an adaptor model based on gates that simultaneously sparsify the frozen base model with task-specific adaptation.
arXiv Detail & Related papers (2024-12-17T14:33:05Z) - ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts [71.91042186338163]
ALoRE is a novel PETL method that reuses the hypercomplex parameterized space constructed by Kronecker product to Aggregate Low Rank Experts.
Thanks to the artful design, ALoRE maintains negligible extra parameters and can be effortlessly merged into the frozen backbone.
arXiv Detail & Related papers (2024-12-11T12:31:30Z) - LoRTA: Low Rank Tensor Adaptation of Large Language Models [70.32218116940393]
Low Rank Adaptation (LoRA) is a popular Efficient Fine Tuning (PEFT) method.
We propose a higher-order Candecomp/Parafac (CP) decomposition, enabling a more compact and flexible representation.
Our method can achieve a reduction in the number of parameters while maintaining comparable performance.
arXiv Detail & Related papers (2024-10-05T06:59:50Z) - QFT: Quantized Full-parameter Tuning of LLMs with Affordable Resources [37.265708531464746]
Large Language Models (LLMs) have showcased remarkable impacts across a wide spectrum of natural language processing tasks.
Fine-tuning these pre-trained models on downstream datasets provides further significant performance gains, but this process has been challenging due to its extraordinary resource requirements.
We propose QFT, a novel Quantized Full- parameter Tuning framework for LLMs that enables memory-efficient fine-tuning without harming performance.
arXiv Detail & Related papers (2023-10-11T02:47:40Z) - Parameter-Efficient Fine-Tuning without Introducing New Latency [7.631596468553607]
We introduce a novel adapter technique that directly applies the adapter to pre-trained parameters instead of the hidden representation.
Our proposed method attains a new state-of-the-art outcome in terms of both performance and storage efficiency, storing only 0.03% parameters of full fine-tuning.
arXiv Detail & Related papers (2023-05-26T08:44:42Z) - AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuning [112.97430455461097]
We propose a general PEFT method that tunes a mixture of adaptation modules introduced in each Transformer layer while keeping most of the PLM weights frozen.
By only tuning 0.1-0.2% of PLM parameters, we show that AdaMix outperforms SOTA parameter-efficient fine-tuning and full model fine-tuning for both NLU and NLG tasks.
arXiv Detail & Related papers (2022-10-31T16:23:36Z) - Amortized Auto-Tuning: Cost-Efficient Transfer Optimization for
Hyperparameter Recommendation [83.85021205445662]
We propose an instantiation--amortized auto-tuning (AT2) to speed up tuning of machine learning models.
We conduct a thorough analysis of the multi-task multi-fidelity Bayesian optimization framework, which leads to the best instantiation--amortized auto-tuning (AT2)
arXiv Detail & Related papers (2021-06-17T00:01:18Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.