paper-with-me

Papers

Delayed Propagation Transformer: A Universal Computation Engine towards Practical Control in Cyber-Physical Systems

2021-10-29 · NeurIPS 2021 12 · Wenqing Zheng, Qiangqiang Guo, Hao Yang, Peihao Wang, Zhangyang Wang

Multi-agent control is a central theme in the Cyber-Physical Systems (CPS). However, current control methods either receive non-Markovian states due to insufficient sensing and decentralized design, or suffer from poor convergence. This paper presents the Delayed Propagation Transformer (DePT), a new transformer-based model that specializes in the global modeling of CPS while taking into account the immutable constraints from the physical world. DePT induces a cone-shaped spatial-temporal attention prior, which injects the information propagation and aggregation principles and enables a global view. With physical constraint inductive bias baked into its design, our DePT is ready to plug and play for a broad class of multi-agent systems. The experimental results on one of the most challenging CPS -- network-scale traffic signal control system in the open world -- show that our model outperformed the state-of-the-art expert methods on synthetic and real-world datasets. Our codes are released at: https://github.com/VITA-Group/DePT.

📄 PDF Abstract BibTeX arXiv:2110.15926

Code (1)

vita-group/dept 공식 구현 tf

Tasks

Inductive BiasTraffic Signal Control

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
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…
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…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
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…
Residual Connection 설명 없음
Adam 설명 없음

Similar Papers 제목 키워드 기반

Differentiable Causal Computations via Delayed Trace

2019-03-04 · David Sprunger, Shin-ya Katsumata

We investigate causal computations taking sequences of inputs to sequences of outputs where the $n$th output depends on the first $n$ inputs only. We model these in category theory via a construction taking a Cartesian c…

Rolling Shutter Correction

Feed-Forward Optimization With Delayed Feedback for Neural Networks

2023-04-26 · Katharina Flügel, Daniel Coquelin, Marie Weiel, Charlotte Debus 외

Backpropagation has long been criticized for being biologically implausible, relying on concepts that are not viable in natural learning processes. This paper proposes an alternative approach to solve two core issues, i.…

Biologically-plausible TrainingComputational Efficiency

DeepAoANet: Learning Angle of Arrival from Software Defined Radios with Deep Neural Networks

2021-12-01 · Zhuangzhuang Dai, Yuhang He, Tran Vu, Niki Trigoni 외

Direction finding and positioning systems based on RF signals are significantly impacted by multipath propagation, particularly in indoor environments. Existing algorithms (e.g MUSIC) perform poorly in resolving Angle of…

Universal Approximation Theorem for a Single-Layer Transformer

2025-07-11 · Esmail Gumaan arxiv

Deep learning employs multi-layer neural networks trained via the backpropagation algorithm. This approach has achieved success across many domains and relies on adaptive gradient methods such as the Adam optimizer. Sequ…

Universal Quantum Transformer

2026-04-29 · Sungyong Chung, Alireza Talebpour arxiv

Classical continuous-space neural networks fundamentally struggle to lock into exact mathematical symmetries, such as modular arithmetic and non-commutative algebra. To approximate these discrete logical rules, they ofte…