Discovering Long-Term Effects on Parameter Efficient Fine-tuning

• URL: http://arxiv.org/abs/2409.06706v1
• Date: Sat, 24 Aug 2024 03:27:29 GMT
• Title: Discovering Long-Term Effects on Parameter Efficient Fine-tuning
• Authors: Gaole Dai, Yiming Tang, Chunkai Fan, Qizhe Zhang, Zhi Zhang, Yulu Gan, Chengqing Zeng, Shanghang Zhang, Tiejun Huang,
• Abstract summary: Pre-trained Artificial Neural Networks (Annns) exhibit robust pattern recognition capabilities. Annns and BNNs share extensive similarities with the human brain, specifically Biological Neural Networks (BNNs) Annns can acquire new knowledge through fine-tuning.
• Score: 36.83255498301937
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Pre-trained Artificial Neural Networks (ANNs) exhibit robust pattern recognition capabilities and share extensive similarities with the human brain, specifically Biological Neural Networks (BNNs). We are particularly intrigued by these models' ability to acquire new knowledge through fine-tuning. In this regard, Parameter-efficient Fine-tuning (PEFT) has gained widespread adoption as a substitute for full fine-tuning due to its cost reduction in training and mitigation of over-fitting risks by limiting the number of trainable parameters during adaptation. Since both ANNs and BNNs propagate information layer-by-layer, a common analogy can be drawn: weights in ANNs represent synapses in BNNs, while features (also known as latent variables or logits) in ANNs represent neurotransmitters released by neurons in BNNs. Mainstream PEFT methods aim to adjust feature or parameter values using only a limited number of trainable parameters (usually less than 1% of the total parameters), yet achieve surprisingly good results. Building upon this clue, we delve deeper into exploring the connections between feature adjustment and parameter adjustment, resulting in our proposed method Synapses & Neurons (SAN) that learns scaling matrices for features and propagates their effects towards posterior weight matrices. Our approach draws strong inspiration from well-known neuroscience phenomena - Long-term Potentiation (LTP) and Long-term Depression (LTD), which also reveal the relationship between synapse development and neurotransmitter release levels. We conducted extensive comparisons of PEFT on 26 datasets using attention-based networks as well as convolution-based networks, leading to significant improvements compared to other tuning methods (+8.5% over fully-finetune, +7% over Visual Prompt Tuning, and +3.2% over LoRA). The codes would be released.

Related papers

• rule4ml: An Open-Source Tool for Resource Utilization and Latency Estimation for ML Models on FPGA [0.0]
  This paper introduces a novel method to predict the resource utilization and inference latency of Neural Networks (NNs) before their synthesis and implementation on FPGA. We leverage HLS4ML, a tool-flow that helps translate NNs into high-level synthesis (HLS) code. Our method uses trained regression models for immediate pre-synthesis predictions.
  arXiv  Detail & Related papers  (2024-08-09T19:35:10Z)
• Unlock the Correlation between Supervised Fine-Tuning and Reinforcement Learning in Training Code Large Language Models [12.656574142412484]
  We make an attempt to understand the correlation between supervised fine-tuning and reinforcement learning. We find that both atomic and synthetic functions are indispensable for SFT's generalization.
  arXiv  Detail & Related papers  (2024-06-14T03:39:01Z)
• Let's Focus on Neuron: Neuron-Level Supervised Fine-tuning for Large Language Model [43.107778640669544]
  Large Language Models (LLMs) are composed of neurons that exhibit various behaviors and roles. Recent studies have revealed that not all neurons are active across different datasets. We introduce Neuron-Level Fine-Tuning (NeFT), a novel approach that refines the granularity of parameter training down to the individual neuron.
  arXiv  Detail & Related papers  (2024-03-18T09:55:01Z)
• Fine-Tuning Surrogate Gradient Learning for Optimal Hardware Performance in Spiking Neural Networks [1.52292571922932]
  Spiking Neural Networks (SNNs) can provide tremendous energy efficiency benefits when carefully exploited in hardware. This work reveals novel insights into the impacts of training on hardware performance.
  arXiv  Detail & Related papers  (2024-02-09T06:38:12Z)
• The Expressive Leaky Memory Neuron: an Efficient and Expressive Phenomenological Neuron Model Can Solve Long-Horizon Tasks [64.08042492426992]
  We introduce the Expressive Memory (ELM) neuron model, a biologically inspired model of a cortical neuron. Our ELM neuron can accurately match the aforementioned input-output relationship with under ten thousand trainable parameters. We evaluate it on various tasks with demanding temporal structures, including the Long Range Arena (LRA) datasets.
  arXiv  Detail & Related papers  (2023-06-14T13:34:13Z)
• Bayesian Neural Network Language Modeling for Speech Recognition [59.681758762712754]
  State-of-the-art neural network language models (NNLMs) represented by long short term memory recurrent neural networks (LSTM-RNNs) and Transformers are becoming highly complex. In this paper, an overarching full Bayesian learning framework is proposed to account for the underlying uncertainty in LSTM-RNN and Transformer LMs.
  arXiv  Detail & Related papers  (2022-08-28T17:50:19Z)
• Vision Transformers are Robust Learners [65.91359312429147]
  We study the robustness of the Vision Transformer (ViT) against common corruptions and perturbations, distribution shifts, and natural adversarial examples. We present analyses that provide both quantitative and qualitative indications to explain why ViTs are indeed more robust learners.
  arXiv  Detail & Related papers  (2021-05-17T02:39:22Z)
• Towards a Competitive End-to-End Speech Recognition for CHiME-6 Dinner Party Transcription [73.66530509749305]
  In this paper, we argue that, even in difficult cases, some end-to-end approaches show performance close to the hybrid baseline. We experimentally compare and analyze CTC-Attention versus RNN-Transducer approaches along with RNN versus Transformer architectures. Our best end-to-end model based on RNN-Transducer, together with improved beam search, reaches quality by only 3.8% WER abs. worse than the LF-MMI TDNN-F CHiME-6 Challenge baseline.
  arXiv  Detail & Related papers  (2020-04-22T19:08:33Z)
• Flexible Transmitter Network [84.90891046882213]
  Current neural networks are mostly built upon the MP model, which usually formulates the neuron as executing an activation function on the real-valued weighted aggregation of signals received from other neurons. We propose the Flexible Transmitter (FT) model, a novel bio-plausible neuron model with flexible synaptic plasticity. We present the Flexible Transmitter Network (FTNet), which is built on the most common fully-connected feed-forward architecture.
  arXiv  Detail & Related papers  (2020-04-08T06:55:12Z)

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.