paper-with-me

홈 › Papers

Discovering Influential Neuron Path in Vision Transformers

2025-03-12 · Yifan Wang, Yifei Liu, Yingdong Shi, Changming Li, Anqi Pang, Sibei Yang, Jingyi Yu, Kan Ren

Vision Transformer models exhibit immense power yet remain opaque to human understanding, posing challenges and risks for practical applications. While prior research has attempted to demystify these models through input attribution and neuron role analysis, there's been a notable gap in considering layer-level information and the holistic path of information flow across layers. In this paper, we investigate the significance of influential neuron paths within vision Transformers, which is a path of neurons from the model input to output that impacts the model inference most significantly. We first propose a joint influence measure to assess the contribution of a set of neurons to the model outcome. And we further provide a layer-progressive neuron locating approach that efficiently selects the most influential neuron at each layer trying to discover the crucial neuron path from input to output within the target model. Our experiments demonstrate the superiority of our method finding the most influential neuron path along which the information flows, over the existing baseline solutions. Additionally, the neuron paths have illustrated that vision Transformers exhibit some specific inner working mechanism for processing the visual information within the same image category. We further analyze the key effects of these neurons on the image classification task, showcasing that the found neuron paths have already preserved the model capability on downstream tasks, which may also shed some lights on real-world applications like model pruning. The project website including implementation code is available at https://foundation-model-research.github.io/NeuronPath/.

📄 PDF Abstract BibTeX arXiv:2503.09046

Code (0)

등록된 구현이 없습니다.

Tasks

image-classificationImage Classification

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Similar Papers 제목 키워드 기반

Cross-Modal Unlearning via Influential Neuron Path Editing in Multimodal Large Language Models

2025-11-10 · Kunhao Li, Wenhao Li, Di Wu, Lei Yang 외 arxiv

Multimodal Large Language Models (MLLMs) extend foundation models to real-world applications by integrating inputs such as text and vision. However, their broad knowledge capacity raises growing concerns about privacy le…

General Knowledge

Self-Supervised Vision Transformers Learn Visual Concepts in Histopathology

2022-03-01 · Richard J. Chen, Rahul G. Krishnan

Tissue phenotyping is a fundamental task in learning objective characterizations of histopathologic biomarkers within the tumor-immune microenvironment in cancer pathology. However, whole-slide imaging (WSI) is a complex…

DiversityKnowledge DistillationTransfer Learning

Neuron Level Analysis of Large Language Model in Legal Domain Reasoning

2026-06-14 · Eri Onami, Youmi Ma, Shuhei Kurita, Naoaki Okazaki arxiv

We presented a neuron-level analysis of legal-domain reasoning in LLMs, comparing it with other applied domain tasks across seven open-weight models. Using neuron attribution scores to rank and suppress influential neuro…

Discovering Influential Factors in Variational Autoencoder

2018-09-06 · Shiqi Liu, Jingxin Liu, Qian Zhao, Xiangyong Cao 외

In the field of machine learning, it is still a critical issue to identify and supervise the learned representation without manually intervening or intuition assistance to extract useful knowledge or serve for the downst…

General Classification

DIWIFT: Discovering Instance-wise Influential Features for Tabular Data

2022-07-06 · Dugang Liu, Pengxiang Cheng, Hong Zhu, Xing Tang 외

Tabular data is one of the most common data storage formats behind many real-world web applications such as retail, banking, and e-commerce. The success of these web applications largely depends on the ability of the emp…

feature selection