paper-with-me

홈 › Papers

PRANCE: Joint Token-Optimization and Structural Channel-Pruning for Adaptive ViT Inference

2024-07-06 · Ye Li, Chen Tang, Yuan Meng, Jiajun Fan, Zenghao Chai, Xinzhu Ma, Zhi Wang, Wenwu Zhu

We introduce PRANCE, a Vision Transformer compression framework that jointly optimizes the activated channels and reduces tokens, based on the characteristics of inputs. Specifically, PRANCE~ leverages adaptive token optimization strategies for a certain computational budget, aiming to accelerate ViTs' inference from a unified data and architectural perspective. However, the joint framework poses challenges to both architectural and decision-making aspects. Firstly, while ViTs inherently support variable-token inference, they do not facilitate dynamic computations for variable channels. To overcome this limitation, we propose a meta-network using weight-sharing techniques to support arbitrary channels of the Multi-head Self-Attention and Multi-layer Perceptron layers, serving as a foundational model for architectural decision-making. Second, simultaneously optimizing the structure of the meta-network and input data constitutes a combinatorial optimization problem with an extremely large decision space, reaching up to around $10^{14}$, making supervised learning infeasible. To this end, we design a lightweight selector employing Proximal Policy Optimization for efficient decision-making. Furthermore, we introduce a novel "Result-to-Go" training mechanism that models ViTs' inference process as a Markov decision process, significantly reducing action space and mitigating delayed-reward issues during training. Extensive experiments demonstrate the effectiveness of PRANCE~ in reducing FLOPs by approximately 50\%, retaining only about 10\% of tokens while achieving lossless Top-1 accuracy. Additionally, our framework is shown to be compatible with various token optimization techniques such as pruning, merging, and sequential pruning-merging strategies. The code is available at \href{https://github.com/ChildTang/PRANCE}{https://github.com/ChildTang/PRANCE}.

📄 PDF Abstract BibTeX arXiv:2407.05010

Code (1)

childtang/prance 공식 구현 pytorch

Tasks

Combinatorial OptimizationDecision Making

Methods 이 논문이 사용한 방법론

Attention 설명 없음
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 $x$…
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…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음

Similar Papers 제목 키워드 기반

Rotation-Aligned Key Channel Pruning for Efficient Vision-Language Model Inference

2026-05-19 · Beomseok Kang, Dongwon Jo, Jiwon Song, Donghwee Son 외 arxiv

Vision-Language Models suffer severe KV cache pressure at inference, as a single image often encodes into thousands of tokens. Most existing methods exploit token sparsity through token pruning, but permanently discardin…

DisentangleFormer: Spatial-Channel Decoupling for Multi-Channel Vision

2025-12-03 · Jiashu Liao, Pietro Liò, Marc de Kamps, Duygu Sarikaya arxiv

Vision Transformers face a fundamental limitation: standard self-attention jointly processes spatial and channel dimensions, leading to entangled representations that prevent independent modeling of structural and semant…

Representation Learning

Joint Semantic-Channel Coding and Modulation for Token Communications

2025-11-19 · Jingkai Ying, Zhijin Qin, Yulong Feng, Liejun Wang 외 arxiv

In recent years, the Transformer architecture has achieved outstanding performance across a wide range of tasks and modalities. Token is the unified input and output representation in Transformer-based models, which has …

Adaptive Semantic Token Communication for Transformer-based Edge Inference

2025-05-23 · Alessio Devoto, Jary Pomponi, Mattia Merluzzi, Paolo Di Lorenzo 외

This paper presents an adaptive framework for edge inference based on a dynamically configurable transformer-powered deep joint source channel coding (DJSCC) architecture. Motivated by a practical scenario where a resour…

object-detectionObject DetectionSemantic CommunicationStochastic Optimization

DIANOIA: Diagnostic Decomposition and Joint Optimization for Multi-Agent Reasoning

2026-02-09 · Yiming Yang, Zhuoyuan Li, Fanxiang Zeng, Hao Fu 외 arxiv

Multi-agent LLM systems consistently outperform single-agent baselines, yet practitioners still cannot predict which design works for a new task or diagnose why one fails. We argue this gap persists largely because the f…