# GD-FPS: Growth-Driven Feedforward Parameter Selection for Efficient Fine-Tuning

arXiv: https://arxiv.org/abs/2510.27359 · HTML: https://mlsanity.com/paper/2510.27359/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 47 references that are in the map.
- First posted on arXiv 31 Oct 2025.

## Builds on (most cited first, 30 of 33)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models](https://mlsanity.com/paper/2211.10438/) (2022)
- [Unified Perceptual Parsing for Scene Understanding](https://mlsanity.com/paper/1807.10221/) (2018)
- [BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models](https://mlsanity.com/paper/2106.10199/) (2021)
- [How transferable are features in deep neural networks?](https://mlsanity.com/paper/1411.1792/) (2014)
- [CLIP-Adapter: Better Vision-Language Models with Feature Adapters](https://mlsanity.com/paper/2110.04544/) (2021)
- [Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution](https://mlsanity.com/paper/2202.10054/) (2022)
- [AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition](https://mlsanity.com/paper/2205.13535/) (2022)
- [Do Vision Transformers See Like Convolutional Neural Networks?](https://mlsanity.com/paper/2108.08810/) (2021)
- [Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning](https://mlsanity.com/paper/2012.13255/) (2020)
- [To prune, or not to prune: exploring the efficacy of pruning for model compression](https://mlsanity.com/paper/1710.01878/) (2017)
- [LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model](https://mlsanity.com/paper/2304.15010/) (2023)
- [The State of Sparsity in Deep Neural Networks](https://mlsanity.com/paper/1902.09574/) (2019)
- [A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark](https://mlsanity.com/paper/1910.04867/) (2019)
- [SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression](https://mlsanity.com/paper/2306.03078/) (2023)
- [K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters](https://mlsanity.com/paper/2002.01808/) (2020)
- [Prompting Visual-Language Models for Efficient Video Understanding](https://mlsanity.com/paper/2112.04478/) (2021)
- [Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning](https://mlsanity.com/paper/2210.08823/) (2022)
- [Knowledgeable Prompt-tuning: Incorporating Knowledge into Prompt Verbalizer for Text Classification](https://mlsanity.com/paper/2108.02035/) (2021)
- [PTQ4ViT: Post-training quantization for vision transformers with twin uniform quantization](https://mlsanity.com/paper/2111.12293/) (2021)
- [OpenPrompt: An Open-source Framework for Prompt-learning](https://mlsanity.com/paper/2111.01998/) (2021)
- [RepQ-ViT: Scale Reparameterization for Post-Training Quantization of Vision Transformers](https://mlsanity.com/paper/2212.08254/) (2022)
- [Fine-Grained Car Detection for Visual Census Estimation](https://mlsanity.com/paper/1709.02480/) (2017)

## Built on by (most cited first, 1 of 1)

- [Emoception: Selective Affective Layer Fine-Tuning of Video Vision Transformers for Player Arousal Change Recognition From Gameplay Footage](https://mlsanity.com/paper/2610.07603/) (2026)

## Abstract (arXiv)

Parameter-Efficient Fine-Tuning (PEFT) has emerged as a key strategy for adapting large-scale pre-trained models to downstream tasks, but existing approaches face notable limitations. Addition-based methods, such as Adapters, introduce inference latency and engineering complexity, whereas selection-based methods like Gradient-based Parameter Selection (GPS) require a full backward pass. The reliance on gradients not only incurs massive memory usage and substantial computational latency, but also leaves the selection vulnerable to the randomness of stochastic batch sampling. To resolve this, we propose Growth-Driven Feedforward Parameter Selection (GD-FPS). Operating entirely via forward passes, this strictly gradient-free method identifies the optimal parameter subset by scaling intrinsic weight magnitudes by their relative activation growth against a pre-training anchor. Evaluated on 26 visual tasks spanning image classification and semantic segmentation, GD-FPS achieves competitive or superior performance over state-of-the-art PEFT baselines. Crucially, compared to GPS, it reduces peak memory usage by nearly 18× and accelerates execution by over 2.7× during the parameter selection stage. By guaranteeing deterministic selection, GD-FPS offers a memory-efficient, fast, and robust solution for fine-tuning.