AFLoRA: Adaptive Freezing of Low Rank Adaptation in Parameter Efficient Fine-Tuning of Large Models
- URL: http://arxiv.org/abs/2403.13269v3
- Date: Tue, 16 Apr 2024 17:37:12 GMT
- Title: AFLoRA: Adaptive Freezing of Low Rank Adaptation in Parameter Efficient Fine-Tuning of Large Models
- Authors: Zeyu Liu, Souvik Kundu, Anni Li, Junrui Wan, Lianghao Jiang, Peter Anthony Beerel,
- Abstract summary: We present a novel.
-Efficient Fine-Tuning (PEFT) method, dubbed as Adaptive Freezing of Low Rank Adaptation (AFLoRA)
Specifically, we add a parallel path of trainable low-rank matrices, namely a down-projection and an up-projection matrix, each of which is followed by a feature transformation vector.
Our experimental results demonstrate that we can achieve state-of-the-art performance with an average improvement of up to $0.85%$ as evaluated on GLUE benchmark.
- Score: 5.981614673186146
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We present a novel Parameter-Efficient Fine-Tuning (PEFT) method, dubbed as Adaptive Freezing of Low Rank Adaptation (AFLoRA). Specifically, for each pre-trained frozen weight tensor, we add a parallel path of trainable low-rank matrices, namely a down-projection and an up-projection matrix, each of which is followed by a feature transformation vector. Based on a novel freezing score, we the incrementally freeze these projection matrices during fine-tuning to reduce the computation and alleviate over-fitting. Our experimental results demonstrate that we can achieve state-of-the-art performance with an average improvement of up to $0.85\%$ as evaluated on GLUE benchmark while yeilding up to $9.5\times$ fewer average trainable parameters. While compared in terms of runtime, AFLoRA can yield up to $1.86\times$ improvement as opposed to similar PEFT alternatives. Besides the practical utility of our approach, we provide insights on the trainability requirements of LoRA paths at different modules and the freezing schedule for the different projection matrices. Code will be released.
Related papers
- LaMDA: Large Model Fine-Tuning via Spectrally Decomposed Low-Dimensional Adaptation [7.788139145984213]
Low-rank adaptation (LoRA) has become the default approach to fine-tune large language models (LLMs)
We introduce large model fine-tuning via spectrally decomposed low-dimensional adaptation (LaMDA)
LaMDA achieves significant reductions in trainable parameters and peak GPU memory footprint.
arXiv Detail & Related papers (2024-06-18T17:52:59Z) - Optimization-based Structural Pruning for Large Language Models without Back-Propagation [57.9629676017527]
We propose an optimization-based structural pruning on Large-Language Models (LLMs)
Our method learns the pruning masks in a probabilistic space directly by optimizing the loss of the pruned model.
Our method operates for 2.7 hours with around 35GB memory for the 13B models on a single A100 GPU, and our pruned models outperform the state-of-the-arts w.r.t. perplexity.
arXiv Detail & Related papers (2024-06-15T09:31:03Z) - Spectrum-Aware Parameter Efficient Fine-Tuning for Diffusion Models [73.88009808326387]
We propose a novel spectrum-aware adaptation framework for generative models.
Our method adjusts both singular values and their basis vectors of pretrained weights.
We introduce Spectral Ortho Decomposition Adaptation (SODA), which balances computational efficiency and representation capacity.
arXiv Detail & Related papers (2024-05-31T17:43:35Z) - SVFT: Parameter-Efficient Fine-Tuning with Singular Vectors [80.6043267994434]
We propose SVFT, a simple approach that fundamentally differs from existing methods.
SVFT updates (W) as a sparse combination of outer products of its singular vectors, training only the coefficients (scales) of these sparse combinations.
Experiments on language and vision benchmarks show that SVFT recovers up to 96% of full fine-tuning performance while training only 0.006 to 0.25% of parameters.
arXiv Detail & Related papers (2024-05-30T01:27:43Z) - Parameter Efficient Quasi-Orthogonal Fine-Tuning via Givens Rotation [20.47507483613317]
One representative line of fine-tuning methods is Orthogonal Fine-tuning (OFT)
OFT rigorously preserves the angular distances within the parameter space to preserve the pretrained knowledge.
We propose quasi-Givens Orthogonal Fine-Tuning (qGOFT) to address the problems.
arXiv Detail & Related papers (2024-04-05T15:28:44Z) - AffineQuant: Affine Transformation Quantization for Large Language Models [58.45460102764]
Post-Training Quantization (PTQ) has emerged as a subject of considerable interest due to its compression efficiency and cost-effectiveness in the context of training.
Existing PTQ methods for Large-scale Language Models (LLMs) limit the optimization scope to scaling transformations between pre- and post-quantization weights.
In this paper, we advocate for the direct optimization using equivalent Affine transformations in PTQ (AffineQuant)
arXiv Detail & Related papers (2024-03-19T08:40:21Z) - Flora: Low-Rank Adapters Are Secretly Gradient Compressors [30.224822087562163]
Low-rank adaptation (LoRA) is proposed to reduce the optimization states by training fewer parameters.
LoRA restricts overall weight update matrices to be low-rank, limiting the model performance.
We propose Flora, which is able to achieve high-rank updates by resampling the projection matrices.
arXiv Detail & Related papers (2024-02-05T18:50:39Z) - Time-, Memory- and Parameter-Efficient Visual Adaptation [75.28557015773217]
We propose an adaptation method which does not backpropagate gradients through the backbone.
We achieve this by designing a lightweight network in parallel that operates on features from the frozen, pretrained backbone.
arXiv Detail & Related papers (2024-02-05T10:55:47Z) - Federated Learning Using Variance Reduced Stochastic Gradient for
Probabilistically Activated Agents [0.0]
This paper proposes an algorithm for Federated Learning (FL) with a two-layer structure that achieves both variance reduction and a faster convergence rate to an optimal solution in the setting where each agent has an arbitrary probability of selection in each iteration.
arXiv Detail & Related papers (2022-10-25T22:04:49Z) - AdaGDA: Faster Adaptive Gradient Descent Ascent Methods for Minimax
Optimization [104.96004056928474]
We propose a class of faster adaptive gradient descent methods for non-strongly-concave minimax problems.
We show that our method reaches a lower sample complexity of $O(kappa2.5epsilon-3)$ with the mini-batch size $O(kappa)$.
arXiv Detail & Related papers (2021-06-30T14:47:09Z) - Bayesian Sparse learning with preconditioned stochastic gradient MCMC
and its applications [5.660384137948734]
The proposed algorithm converges to the correct distribution with a controllable bias under mild conditions.
We show that the proposed algorithm canally converge to the correct distribution with a controllable bias under mild conditions.
arXiv Detail & Related papers (2020-06-29T20:57:20Z)
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.