关于组合优化的机器学习的最新作品表明,基于学习的方法可以优于速度和性能方面的启发式方法。在本文中,我们考虑了在定向的无环图上找到最佳拓扑顺序的问题,重点是编译器中出现的记忆最小化问题。我们提出了一种基于端到端的机器学习方法,用于使用编码器框架,用于拓扑排序。我们的编码器是一种基于注意力的新图形神经网络体系结构,称为\ emph {topoformer},它使用DAG的不同拓扑转换来传递消息。由编码器产生的节点嵌入被转换为节点优先级,解码器使用这些嵌入,以生成概率分布对拓扑顺序。我们在称为分层图的合成生成图的数据集上训练我们的模型。我们表明,我们的模型的表现优于或在PAR上,具有多个拓扑排序基线,同时在最多2K节点的合成图上明显更快。我们还在一组现实世界计算图上训练和测试我们的模型,显示了性能的改进。
translated by 谷歌翻译
组合优化是运营研究和计算机科学领域的一个公认领域。直到最近,它的方法一直集中在孤立地解决问题实例,而忽略了它们通常源于实践中的相关数据分布。但是,近年来,人们对使用机器学习,尤其是图形神经网络(GNN)的兴趣激增,作为组合任务的关键构件,直接作为求解器或通过增强确切的求解器。GNN的电感偏差有效地编码了组合和关系输入,因为它们对排列和对输入稀疏性的意识的不变性。本文介绍了对这个新兴领域的最新主要进步的概念回顾,旨在优化和机器学习研究人员。
translated by 谷歌翻译
用于图形组合优化问题的神经网络溶剂的端到端培训,例如旅行销售人员问题(TSP)最近看到了感兴趣的激增,但在几百节节点的图表中保持棘手和效率低下。虽然最先进的学习驱动的方法对于TSP在培训的古典索引时与古典求解器密切相关,但它们无法通过实际尺度的实际情况概括到更大的情况。这项工作提出了一个端到端的神经组合优化流水线,统一几个卷纸,以确定促进比在训练中看到的实例的概括的归纳偏差,模型架构和学习算法。我们的受控实验提供了第一个原则上调查这种零拍摄的概括,揭示了超越训练数据的推断需要重新思考从网络层和学习范例到评估协议的神经组合优化流水线。此外,我们分析了深入学习的最近进步,通过管道的镜头路由问题,并提供新的方向,以刺激未来的研究。
translated by 谷歌翻译
我们提出了一个通用图形神经网络体系结构,可以作为任何约束满意度问题(CSP)作为末端2端搜索启发式训练。我们的体系结构可以通过政策梯度下降进行无监督的培训,以纯粹的数据驱动方式为任何CSP生成问题的特定启发式方法。该方法基于CSP的新型图表,既是通用又紧凑的,并且使我们能够使用一个GNN处理所有可能的CSP实例,而不管有限的Arity,关系或域大小。与以前的基于RL的方法不同,我们在全局搜索动作空间上运行,并允许我们的GNN在随机搜索的每个步骤中修改任何数量的变量。这使我们的方法能够正确利用GNN的固有并行性。我们进行了彻底的经验评估,从随机数据(包括图形着色,Maxcut,3-SAT和Max-K-Sat)中学习启发式和重要的CSP。我们的方法表现优于先验的神经组合优化的方法。它可以在测试实例上与常规搜索启发式竞争,甚至可以改善几个数量级,结构上比训练中看到的数量级更为复杂。
translated by 谷歌翻译
最近的反向散射通信技术使超低功耗无线设备使得在没有电池的情况下操作,同时直接与未修饰的商品无线设备互操作。商品设备在提供未调制的载体时,可以在从其环境中收集能量以执行感测,计算和通信任务的同时需要进行通信的未调制载波。未经调制载波的最佳提供限制了网络的大小,因为它是NP硬组合优化问题。因此,以前的作品要么完全忽略载体优化,要么避免次优启发式,浪费宝贵的能量和光谱资源。我们展示了Deepgantt,这是一种与无线商品互通设备的无电池设备的深度学习调度程序。 Deepgantt利用图形神经网络来克服这个问题固有的变量输入和输出大小挑战。我们培养我们的深度学习调度程序,具有从约束优化求解器获得的相对较小的尺寸的最佳时间表。 Deepgantt不仅优于精心制作的启发式解决方案,而且还在训练有素的问题大小的最佳调度器的3%内执行。最后,DeepGantt推广了超过用于训练的最大值的问题超过四倍,因此打破了最佳调度器的可扩展性限制,并为更有效的反向散射网络铺平道路。
translated by 谷歌翻译
广泛研究和使用旅行推销员问题等图形问题,如旅行推销员问题,或发现最小的施泰纳树在数据工程和计算机科学中使用。通常,在现实世界应用中,图表的特征往往会随着时间的推移而变化,因此,找到问题的解决方案变得具有挑战性。许多图表问题的动态版本是运输,电信和社交网络中普遍世界问题的关键。近年来,利用深度学习技术来寻找NP-Hard图组合问题的启发式解决方案,因为这些学习的启发式可以有效地找到近最佳解决方案。但是,大多数现有的学习启发式方法都关注静态图问题。动态性质使NP-Hard图表问题更具挑战性,并且现有方法无法找到合理的解决方案。在本文中,我们提出了一种名为Cabl时间关注的新型建筑,并利用加固学习(GTA-RL)来学习基于图形的动态组合优化问题的启发式解决方案。 GTA-RL架构包括能够嵌入组合问题实例的时间特征的编码器和能够动态地关注嵌入功能的解码器,以找到给定组合问题实例的解决方案。然后,我们将架构扩展到学习HeuRistics的组合优化问题的实时版本,其中问题的所有输入特征是未知的,而是实时学习。我们针对几种最先进的基于学习的算法和最佳求解器的实验结果表明,我们的方法在动态和效率方面,在有效性和最佳求解器方面优于基于最先进的学习方法。实时图组合优化。
translated by 谷歌翻译
This paper surveys the recent attempts, both from the machine learning and operations research communities, at leveraging machine learning to solve combinatorial optimization problems. Given the hard nature of these problems, state-of-the-art algorithms rely on handcrafted heuristics for making decisions that are otherwise too expensive to compute or mathematically not well defined. Thus, machine learning looks like a natural candidate to make such decisions in a more principled and optimized way. We advocate for pushing further the integration of machine learning and combinatorial optimization and detail a methodology to do so. A main point of the paper is seeing generic optimization problems as data points and inquiring what is the relevant distribution of problems to use for learning on a given task.
translated by 谷歌翻译
路由问题是许多实际应用的一类组合问题。最近,已经提出了端到端的深度学习方法,以了解这些问题的近似解决方案启发式。相比之下,经典动态编程(DP)算法保证最佳解决方案,但与问题大小严重规模。我们提出了深入的政策动态规划(DPDP),旨在将学习神经启发式的优势与DP算法结合起来。 DPDP优先确定并限制DP状态空间,使用来自深度神经网络的策略进行培训,以预测示例解决方案的边缘。我们在旅行推销员问题(TSP)上评估我们的框架,车辆路由问题(VRP)和TSP与时间窗口(TSPTW),并表明神经政策提高了(限制性)DP算法的性能,使其对强有力的替代品具有竞争力如LKH,同时也优于求解TSP,VRP和TSPTWS的大多数其他“神经方法”,其中包含100个节点。
translated by 谷歌翻译
Steiner树问题(STP)在图中旨在在连接给定的顶点集的图表中找到一个最小权重的树。它是一种经典的NP - 硬组合优化问题,具有许多现实世界应用(例如,VLSI芯片设计,运输网络规划和无线传感器网络)。为STP开发了许多精确和近似算法,但它们分别遭受高计算复杂性和弱案例解决方案保证。还开发了启发式算法。但是,它们中的每一个都需要应用域知识来设计,并且仅适用于特定方案。最近报道的观察结果,同一NP-COLLECLIAL问题的情况可能保持相同或相似的组合结构,但主要在其数据中不同,我们调查将机器学习技术应用于STP的可行性和益处。为此,我们基于新型图形神经网络和深增强学习设计了一种新型模型瓦坎。 Vulcan的核心是一种新颖的紧凑型图形嵌入,将高瞻度图形结构数据(即路径改变信息)转换为低维矢量表示。鉴于STP实例,Vulcan使用此嵌入来对其路径相关的信息进行编码,并基于双层Q网络(DDQN)将编码的图形发送到深度加强学习组件,以找到解决方案。除了STP之外,Vulcan还可以通过将解决方案(例如,SAT,MVC和X3C)来减少到STP来找到解决方案。我们使用现实世界和合成数据集进行广泛的实验,展示了vulcan的原型,并展示了它的功效和效率。
translated by 谷歌翻译
高吞吐量数据处理应用的高效硬件加速器设计,例如深度神经网络,是计算机架构设计中有挑战性的任务。在这方面,高级合成(HLS)作为快速原型设计的解决方案,从应用程序计算流程的行为描述开始。这种设计空间探索(DSE)旨在识别帕累托最佳的合成配置,其穷举搜索由于设计空间维度和合成过程的禁止计算成本而往往不可行。在该框架内,我们通过提出在文献中,有效和有效地解决了设计问题图形神经网络,该神经网络共同预测了合成的行为规范的加速性能和硬件成本给出了优化指令。考虑到性能和成本估计,学习模型可用于通过引导DSE来快速接近帕累托曲线。所提出的方法优于传统的HLS驱动DSE方法,通过考虑任意长度的计算机程序和输入的不变特性。我们提出了一种新颖的混合控制和数据流图表示,可以在不同硬件加速器的规格上培训图形神经网络;该方法自然地转移到解除数据处理应用程序。此外,我们表明我们的方法实现了与常用模拟器的预测准确性相当,而无需访问HLS编译器和目标FPGA的分析模型,同时是更快的数量级。最后,通过微调来自新目标域的少量样本,可以在未开发的配置空间中解放所学习的表示。
translated by 谷歌翻译
在过去的几年中,已经开发了图形绘图技术,目的是生成美学上令人愉悦的节点链接布局。最近,利用可区分损失功能的使用已为大量使用梯度下降和相关优化算法铺平了道路。在本文中,我们提出了一个用于开发图神经抽屉(GND)的新框架,即依靠神经计算来构建有效且复杂的图的机器。 GND是图形神经网络(GNN),其学习过程可以由任何提供的损失函数(例如图形图中通常使用的损失函数)驱动。此外,我们证明,该机制可以由通过前馈神经网络计算的损失函数来指导,并根据表达美容特性的监督提示,例如交叉边缘的最小化。在这种情况下,我们表明GNN可以通过位置功能很好地丰富与未标记的顶点处理。我们通过为边缘交叉构建损失函数来提供概念验证,并在提议的框架下工作的不同GNN模型之间提供定量和定性的比较。
translated by 谷歌翻译
最近的进步表明,使用强化学习和搜索来解决NP-HARD相关的任务的成功,例如旅行推销员优化,图表编辑距离计算等。但是,尚不清楚如何有效,准确地检测到如何有效地检测大型目标图中的一个小查询图,它是图数据库搜索,生物医学分析,社交组发现等中的核心操作。此任务称为子图匹配,本质上是在查询图和大型目标图之间执行子图同构检查。解决这个经典问题的一种有前途的方法是“学习进行搜索”范式,其中强化学习(RL)代理人的设计具有学习的政策,以指导搜索算法以快速找到解决方案而无需任何解决方案实例进行监督。但是,对于子图匹配的特定任务,尽管查询图通常由用户作为输入给出,但目标图通常更大。它为神经网络设计带来了挑战,并可能导致解决方案和奖励稀疏性。在本文中,我们提出了两项​​创新的N-BLS来应对挑战:(1)一种新颖的编码器折线神经网络体系结构,以动态计算每个搜索状态下查询和目标图之间的匹配信息; (2)蒙特卡洛树搜索增强了双层搜索框架,用于培训政策和价值网络。在五个大型现实世界目标图上进行的实验表明,N-BLS可以显着改善子图匹配性能。
translated by 谷歌翻译
Pre-publication draft of a book to be published byMorgan & Claypool publishers. Unedited version released with permission. All relevant copyrights held by the author and publisher extend to this pre-publication draft.
translated by 谷歌翻译
The design of good heuristics or approximation algorithms for NP-hard combinatorial optimization problems often requires significant specialized knowledge and trial-and-error. Can we automate this challenging, tedious process, and learn the algorithms instead? In many real-world applications, it is typically the case that the same optimization problem is solved again and again on a regular basis, maintaining the same problem structure but differing in the data. This provides an opportunity for learning heuristic algorithms that exploit the structure of such recurring problems. In this paper, we propose a unique combination of reinforcement learning and graph embedding to address this challenge. The learned greedy policy behaves like a meta-algorithm that incrementally constructs a solution, and the action is determined by the output of a graph embedding network capturing the current state of the solution. We show that our framework can be applied to a diverse range of optimization problems over graphs, and learns effective algorithms for the Minimum Vertex Cover, Maximum Cut and Traveling Salesman problems.
translated by 谷歌翻译
钢筋学习最近在许多组合优化问题中显示了学习质量解决方案的承诺。特别地,基于注意的编码器 - 解码器模型在各种路由问题上显示出高效率,包括旅行推销员问题(TSP)。不幸的是,它们对具有无人机(TSP-D)的TSP表现不佳,需要在协调中路由车辆的异构队列 - 卡车和无人机。在TSP-D中,这两个车辆正在串联移动,并且可能需要在用于其他车辆的节点上等待加入。不那么关注的基于关注的解码器无法在车辆之间进行这种协调。我们提出了一种注意力编码器-LSTM解码器混合模型,其中解码器的隐藏状态可以代表所做的动作序列。我们经验证明,这种混合模型可提高基于纯粹的关注的模型,用于解决方案质量和计算效率。我们对MIN-MAX电容车辆路由问题(MMCVRP)的实验还确认混合模型更适合于多车辆的协调路由而不是基于注意的模型。
translated by 谷歌翻译
Optimization of directed acyclic graph (DAG) structures has many applications, such as neural architecture search (NAS) and probabilistic graphical model learning. Encoding DAGs into real vectors is a dominant component in most neural-network-based DAG optimization frameworks. Currently, most DAG encoders use an asynchronous message passing scheme which sequentially processes nodes according to the dependency between nodes in a DAG. That is, a node must not be processed until all its predecessors are processed. As a result, they are inherently not parallelizable. In this work, we propose a Parallelizable Attention-based Computation structure Encoder (PACE) that processes nodes simultaneously and encodes DAGs in parallel. We demonstrate the superiority of PACE through encoder-dependent optimization subroutines that search the optimal DAG structure based on the learned DAG embeddings. Experiments show that PACE not only improves the effectiveness over previous sequential DAG encoders with a significantly boosted training and inference speed, but also generates smooth latent (DAG encoding) spaces that are beneficial to downstream optimization subroutines. Our source code is available at \url{https://github.com/zehao-dong/PACE}
translated by 谷歌翻译
快速扩大的神经网络模型在单个设备上运行越来越具有挑战性。因此,在多个设备上的模型并行性对于确保训练大型模型的效率至关重要。最近的建议在长时间处理时间或性能差。因此,我们提出了Celeritas,这是一个快速的框架,用于优化大型型号的设备放置。Celeritas在标准评估中采用简单但有效的模型并行化策略,并通过一系列调度算法生成位置策略。我们进行实验以在许多大型模型上部署和评估Celeritas。结果表明,与大多数高级方法相比,Celeritas不仅将放置策略生成时间减少26.4 \%,而且还将模型运行时间提高了34.2 \%。
translated by 谷歌翻译
Outstanding achievements of graph neural networks for spatiotemporal time series analysis show that relational constraints introduce an effective inductive bias into neural forecasting architectures. Often, however, the relational information characterizing the underlying data-generating process is unavailable and the practitioner is left with the problem of inferring from data which relational graph to use in the subsequent processing stages. We propose novel, principled - yet practical - probabilistic score-based methods that learn the relational dependencies as distributions over graphs while maximizing end-to-end the performance at task. The proposed graph learning framework is based on consolidated variance reduction techniques for Monte Carlo score-based gradient estimation, is theoretically grounded, and, as we show, effective in practice. In this paper, we focus on the time series forecasting problem and show that, by tailoring the gradient estimators to the graph learning problem, we are able to achieve state-of-the-art performance while controlling the sparsity of the learned graph and the computational scalability. We empirically assess the effectiveness of the proposed method on synthetic and real-world benchmarks, showing that the proposed solution can be used as a stand-alone graph identification procedure as well as a graph learning component of an end-to-end forecasting architecture.
translated by 谷歌翻译
Graph classification is an important area in both modern research and industry. Multiple applications, especially in chemistry and novel drug discovery, encourage rapid development of machine learning models in this area. To keep up with the pace of new research, proper experimental design, fair evaluation, and independent benchmarks are essential. Design of strong baselines is an indispensable element of such works. In this thesis, we explore multiple approaches to graph classification. We focus on Graph Neural Networks (GNNs), which emerged as a de facto standard deep learning technique for graph representation learning. Classical approaches, such as graph descriptors and molecular fingerprints, are also addressed. We design fair evaluation experimental protocol and choose proper datasets collection. This allows us to perform numerous experiments and rigorously analyze modern approaches. We arrive to many conclusions, which shed new light on performance and quality of novel algorithms. We investigate application of Jumping Knowledge GNN architecture to graph classification, which proves to be an efficient tool for improving base graph neural network architectures. Multiple improvements to baseline models are also proposed and experimentally verified, which constitutes an important contribution to the field of fair model comparison.
translated by 谷歌翻译
In recent years, methods based on deep neural networks, and especially Neural Improvement (NI) models, have led to a revolution in the field of combinatorial optimization. Given an instance of a graph-based problem and a candidate solution, they are able to propose a modification rule that improves its quality. However, existing NI approaches only consider node features and node-wise positional encodings to extract the instance and solution information, respectively. Thus, they are not suitable for problems where the essential information is encoded in the edges. In this paper, we present a NI model to solve graph-based problems where the information is stored either in the nodes, in the edges, or in both of them. We incorporate the NI model as a building block of hill-climbing-based algorithms to efficiently guide the election of neighborhood operations considering the solution at that iteration. Conducted experiments show that the model is able to recommend neighborhood operations that are in the $99^{th}$ percentile for the Preference Ranking Problem. Moreover, when incorporated to hill-climbing algorithms, such as Iterated or Multi-start Local Search, the NI model systematically outperforms the conventional versions. Finally, we demonstrate the flexibility of the model by extending the application to two well-known problems: the Traveling Salesman Problem and the Graph Partitioning Problem.
translated by 谷歌翻译