Graph Neural Network Reinforcement Learning for Autonomous Mobility-on-Demand Systems

Combinatorial optimization has found its way into a variety of domains, including artificial intelligence and cybernetics. Deep Reinforcement Learning (DRL) has recently demonstrated its promise for developing heuristics for NP-hard routing problems. The current generalization performance of models needs to be improved, especially for large-scale routing problems. In this paper, we propose a hybrid approach for the Capacitated Vehicle Routing Problem (CVRP) based on DRL and adaptive large neighborhood search. The information representation of the neural network for CVRP is also improved by the combination of multi-head attention mechanism, pointer network and graph neural networks. The experimental results demonstrate that the optimization of our model on CVRP outperforms existing DRL techniques and some traditional algorithms. In addition, our method improves the training efficiency of the model and the performance of generalization to large-scale CVRP.

The effective and reliable routing for Low Earth Orbit (LEO) satellite networks is intractable. The existing approaches cannot well handle the time-varying topology, frequent link handover, and imbalanced communication load. To tackle these issues, in this paper, we propose GRouting algorithm combining Graph Neural Networks (GNN) with Deep Reinforcement Learning (DRL) to dynamically find the optimal routing paths for LEO satellite networks. First, GNN is employed to learn the representation of satellite networks with non-Euclidean data structures. GNN is able to generalize over arbitrary satellite networks topologies, which means that it can deal with time-varying states of satellite networks. Then, based on the representation learned by GNN, DRL is applied to select the optimal routing path between two satellites, which can maximize the utilization of network resources while guaranteeing the requirement of transmission delay. Finally, extensive simulation experiments are carried out to illustrate that 1) our method has a better performance than the baseline algorithms, and 2) the GNN-based method can achieve better generalization over time-varying topologies.

This paper surveys the growing interest in utilizing deep learning (DL) as a powerful tool to address challenging problems in earthquake engineering. Despite decades of advancement in domain knowledge, issues such as uncertainty in earthquake occurrence, unpredictable seismic loads, nonlinear structural responses, and community engagement remain difficult to tackle using domain-specific methods. DL offers promising solutions by leveraging its data-driven capacity for nonlinear mapping, sequential data modeling, automatic feature extraction, dimensionality reduction, optimal decision-making, and so on. However, the literature lacks a comprehensive review that systematically covers a consistent scope intersecting DL and earthquake engineering. To bridge this gap, this paper first discusses methodological advances to elucidate various applicable DL techniques, such as multilayer perceptron, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network, autoencoder, transfer learning, reinforcement learning (RL), and graph neural network. A thorough research landscape is then disclosed by exploring various DL applications across different research topics, including vision-based seismic damage assessment and structural characterization, seismic demand and damage state prediction, seismic response history prediction, regional seismic risk assessment and community resilience, ground motion (GM) for engineering use, seismic response control, and the inverse problem of system/damage identification. Suitable DL techniques for each research topic are identified, emphasizing the preeminence of CNN for vision-based tasks, RNN for sequential data, RL for community resilience, and unsupervised learning for GM analysis. The paper also discusses opportunities and challenges for leveraging DL in earthquake engineering research and practice, highlighting the need for open-access multimodal big data and efforts to enhance model interpretability and incorporate physics information into DL. Finally, the paper advocates for DL applications to further advance the research frontier of uncertainty quantification in performance-based earthquake engineering.

To meet the needs of AI design in analog IC design automation and especially in big data applications, the application of sensitive and precise Graph Neural Network (GNN) recognition will become increasingly necessary. This sensitive GNN recognition is needed to accommodate the highly stringent trade-offs on analog IC design requirements, combined with the increasingly large learning data requirements. Furthermore, more precise GNN recognition will be a fundamental requirement for a more sensitive system to accommodate noise in floating point (FP) calculations, namely inaccuracies and imprecision in IEEE 754 FP calculations. In this study, by refining a previously proposed method that uses the output vector representation (OVR) of the untrained Graph Neural Network (GNN), and by exploiting the numerical reproducibility error in FP calculations, a method for measuring the sensitivity and precision of GNNs for use in analog IC design recognition has been proposed. The results of the sensitivity and precision measurements of the proposed method show a complex combination of effects between dataset quality (the presence or absence of data duplication), the sensitivity of the GNN to distinguish each feature in the dataset, the complexity of the calculations that occur in the GNN, and the level of quality of the FP calculations performed by the processing unit related to the non-ideal FP calculations. With certain GNN configurations, the proposed method also succeeded in measuring the difference in FP calculation quality of Central Processing Unit (CPU) and Graphics Processing Unit (GPU), where, for big data applications, from the tests carried out, the maximum amount of data that can be distinguished by the CPU is 25 to 100 times more than with the GPU. Because it only uses untrained GNN OVR and does not involve any training process in obtaining results, the proposed method is still unable to obtain a correlation with the final value of GNN performance after training is complete. The measurement method using GNN OVR involving the learning process is future work.

A networked system consists of a collection of interconnected autonomous agents that communicate and interact through a shared communication infrastructure. These agents collaborate to pursue common objectives or exhibit coordinated behaviors that would be difficult or impossible for a single agent to achieve alone. With widespread applications in domains such as robotics, smart grids, and communication networks, the coordination and control of networked systems have become a vital research focus—driven by the complexity of distributed interactions and decision-making processes. Graph-based reinforcement learning (GRL) has emerged as a powerful paradigm that combines reinforcement learning with graph signal processing and graph neural networks (GNNs) to develop policies that are relationally aware, scalable, and adaptable to diverse network topologies. This survey aims to advance research in this evolving area by providing a comprehensive overview of GRL in the context of networked coordination and control. It covers the fundamental principles of reinforcement learning and graph neural networks, examines state-of-the-art GRL models and algorithms, reviews training methodologies, discusses key challenges, and highlights real-world applications. By synthesizing theoretical foundations, empirical insights, and open research questions, this survey serves as a cohesive and structured resource for the study and advancement of GRL-enabled networked systems.

Recent advances in Graph Neural Networks (GNNs) have changed the landscape of modern graph analytics. The complexity of GNN training and the scalability challenges have also sparked interest from the systems community, with efforts to build systems that provide higher efficiency and schemes to reduce costs. However, we observe that many such systems basically "reinvent the wheel" of much work done in the database world on scalable graph analytics engines. Further, they often tightly couple the scalability treatments of graph data processing with that of GNN training, resulting in entangled complex problems and systems that often do not scale well on one of those axes. In this paper, we ask a fundamental question: How far can we push existing systems for scalable graph analytics and deep learning (DL) instead of building custom GNN systems? Are compromises inevitable on scalability and/or runtimes? We propose Lotan, the first scalable and optimized data system for full-batch GNN training with decoupled scaling that bridges the hitherto siloed worlds of graph analytics systems and DL systems. Lotan offers a series of technical innovations, including re-imagining GNN training as query plan-like dataflows, execution plan rewriting, optimized data movement between systems, a GNN-centric graph partitioning scheme, and the first known GNN model batching scheme. We prototyped Lotan on top of GraphX and PyTorch. An empirical evaluation using several real-world benchmark GNN workloads reveals a promising nuanced picture: Lotan significantly surpasses the scalability of state-of-the-art custom GNN systems, while often matching or being only slightly behind on time-to-accuracy metrics in some cases. We also show the impact of our system optimizations. Overall, our work shows that the GNN world can indeed benefit from building on top of scalable graph analytics engines. Lotan's new level of scalability can also empower new ML-oriented research on ever-larger graphs and GNNs.

The Science of Deep Learning emerged from courses taught by the author that have provided thousands of students with training and experience for their academic studies, and prepared them for careers in deep learning, machine learning, and artificial intelligence in top companies in industry and academia. The book begins by covering the foundations of deep learning, followed by key deep learning architectures. Subsequent parts on generative models and reinforcement learning may be used as part of a deep learning course or as part of a course on each topic. The book includes state-of-the-art topics such as Transformers, graph neural networks, variational autoencoders, and deep reinforcement learning, with a broad range of applications. The appendices provide equations for computing gradients in backpropagation and optimization, and best practices in scientific writing and reviewing. The text presents an up-to-date guide to the field built upon clear visualizations using a unified notation and equations, lowering the barrier to entry for the reader. The accompanying website provides complementary code and hundreds of exercises with solutions.

With the proliferation of Internet of Things (IoT) devices and edge nodes, edge computing has taken on much of the real-time data processing and low-latency response tasks which were previously managed by cloud computing. However, edge computing often encounters challenges such as network instability and dynamic resource variations, which can lead to task interruptions or failures. To address these issues, developing a fault-tolerant scheduling mechanism is crucial to ensure that a system continues to operate efficiently even when some nodes experience failures. In this paper, we propose an innovative fault-tolerant scheduling model based on asynchronous graph reinforcement learning. This model incorporates a deep reinforcement learning framework built upon a graph neural network, allowing it to accurately capture the complex communication relationships between computing nodes. The model generates fault-tolerant scheduling actions as output, ensuring robust performance in dynamic environments. Additionally, we introduce an asynchronous model update strategy, which enhances the model’s capability of real-time dynamic scheduling through multi-threaded parallel interactions with the environment and frequent model updates via running threads. The experimental results demonstrate that the proposed method outperformed the baseline algorithms in terms of quality of service (QoS) assurance and fault-tolerant scheduling capabilities.

In general, graph neural networks (GNNs) adopt the message-passing scheme to capture the information of a node (i.e., nodal attributes, and local graph structure) by iteratively transforming, aggregating the features of its neighbors. Nonetheless, recent studies show that the performance of GNNs can be easily hampered by the existence of abnormal or malicious nodes due to the vulnerability of neighborhood aggregation. Thus it is necessary to learn anomaly-resistant GNNs without the prior knowledge of ground-truth anomalies, given the fact that labeling anomalies is costly and requires intensive domain knowledge. Though removing anomalies through unsupervised anomaly detection methods could be a possible solution, it may render unreasonable GNN model performance on target tasks due to the non-differentiable gap between the two learning procedures. In order to keep the effectiveness of GNNs on anomaly-contaminated graphs, in this paper, we propose a new framework named RARE-GNN (Reinforced Anomaly-REsistant Graph Neural Networks) which can detect anomalies from the input graph and learn anomaly-resistant GNNs simultaneously. Extensive experiments on real-world datasets demonstrate the effectiveness of the proposed framework.

With growing environmental awareness and increasing energy demands, sustainable manufacturing has become a focal point in the industry. Meanwhile, globalization has propelled distributed manufacturing systems as a dominant trend. This paper tackles the energy-efficient distributed heterogeneous hybrid flow-shop scheduling problem (EDHHFSP), aiming to minimize both makespan and total energy consumption. We first formulate a mixed-integer linear programming (MILP) model to provide a benchmark for small instances. More importantly, we propose a novel end-to-end deep reinforcement learning framework based on a heterogeneous graph neural network, which models the scheduling problem as a distributed decision-making process. A key innovation lies in the design of an action space composed of "job–factory" and "operation–machine" pairs, enabling fine-grained, decentralized scheduling decisions. Our approach starts with a novel heterogeneous graph representation of scheduling states, capturing complex interactions among jobs, factories, and machines. A three-stage embedding mechanism is developed to encode real-time scheduling environments. The agent then learns a parameterized policy using the proximal policy optimization (PPO) algorithm, guided by a reward function that balances makespan and energy efficiency. Experimental results demonstrate that our method generalizes well across different problem scales and significantly outperforms traditional heuristics and learning-based baselines in terms of both scheduling quality and energy savings.

A new ensemble deep graph reinforcement learning network for spatio-temporal traffic volume forecasting in a freeway network

Network representation learning is receiving increasing attention from scholars. Among them, methods based on graph neural networks have become particularly popular. However, most existing methods currently only focus on networks with a single type of relations. In the real world, networks contain a wealth of diverse information, with multiple types of relationships between nodes. In this paper, we propose a graph neural network-based multiplex network representation learning model (GNMRL). We model nodes within each layer of the multiplex network by aggregating neighbor information. Additionally, since nodes are influenced by different network layers, we integrate node interaction information across network layers. We conducted systematic experiments on four datasets, and the results show that GNMRL outperforms other comparison methods in both link prediction and node classification tasks.

The Science of Deep Learning emerged from courses taught by the author that have provided thousands of students with training and experience for their academic studies, and prepared them for careers in deep learning, machine learning, and artificial intelligence in top companies in industry and academia. The book begins by covering the foundations of deep learning, followed by key deep learning architectures. Subsequent parts on generative models and reinforcement learning may be used as part of a deep learning course or as part of a course on each topic. The book includes state-of-the-art topics such as Transformers, graph neural networks, variational autoencoders, and deep reinforcement learning, with a broad range of applications. The appendices provide equations for computing gradients in backpropagation and optimization, and best practices in scientific writing and reviewing. The text presents an up-to-date guide to the field built upon clear visualizations using a unified notation and equations, lowering the barrier to entry for the reader. The accompanying website provides complementary code and hundreds of exercises with solutions.

The Science of Deep Learning emerged from courses taught by the author that have provided thousands of students with training and experience for their academic studies, and prepared them for careers in deep learning, machine learning, and artificial intelligence in top companies in industry and academia. The book begins by covering the foundations of deep learning, followed by key deep learning architectures. Subsequent parts on generative models and reinforcement learning may be used as part of a deep learning course or as part of a course on each topic. The book includes state-of-the-art topics such as Transformers, graph neural networks, variational autoencoders, and deep reinforcement learning, with a broad range of applications. The appendices provide equations for computing gradients in backpropagation and optimization, and best practices in scientific writing and reviewing. The text presents an up-to-date guide to the field built upon clear visualizations using a unified notation and equations, lowering the barrier to entry for the reader. The accompanying website provides complementary code and hundreds of exercises with solutions.

The Science of Deep Learning emerged from courses taught by the author that have provided thousands of students with training and experience for their academic studies, and prepared them for careers in deep learning, machine learning, and artificial intelligence in top companies in industry and academia. The book begins by covering the foundations of deep learning, followed by key deep learning architectures. Subsequent parts on generative models and reinforcement learning may be used as part of a deep learning course or as part of a course on each topic. The book includes state-of-the-art topics such as Transformers, graph neural networks, variational autoencoders, and deep reinforcement learning, with a broad range of applications. The appendices provide equations for computing gradients in backpropagation and optimization, and best practices in scientific writing and reviewing. The text presents an up-to-date guide to the field built upon clear visualizations using a unified notation and equations, lowering the barrier to entry for the reader. The accompanying website provides complementary code and hundreds of exercises with solutions.