Benchmark Algorithms Research Articles

A Review of Safe Reinforcement Learning: Methods, Theories, and Applications.

Reinforcement Learning (RL) has achieved tremendous success in many complex decision-making tasks. However, safety concerns are raised during deploying RL in real-world applications, leading to a growing demand for safe RL algorithms, such as in autonomous driving and robotics scenarios. While safe control has a long history, the study of safe RL algorithms is still in the early stages. To establish a good foundation for future safe RL research, in this paper, we provide a review of safe RL from the perspectives of methods, theories, and applications. First, we review the progress of safe RL from five dimensions and come up with five crucial problems for safe RL being deployed in real-world applications, coined as "2H3W". Second, we analyze the algorithm and theory progress from the perspectives of answering the "2H3W" problems. Particularly, the sample complexity of safe RL algorithms is reviewed and discussed, followed by an introduction to the applications and benchmarks of safe RL algorithms. Finally, we open the discussion of the challenging problems in safe RL, hoping to inspire future research on this thread. To advance the study of safe RL algorithms, we release an open-sourced repository containing major safe RL algorithms at the link.

A Research Approach to Port Information Security Link Prediction Based on HWA Algorithm

For the protection of information security, link prediction, as a basic problem of network science, has important application significance. However, most of the existing link prediction algorithms rely on the node information of the graph structure, which is not applicable in some graph structure data involving privacy. At the same time, most of the algorithms only consider the general graph structure and do not fully consider the high-order information in the graph. Because of this, this paper proposes an algorithm called hypergraph-based link prediction with self-attention (HWA) to solve the above problems. The algorithm can obtain hypergraphs without knowing the attribute information of hypergraph nodes and combines the graph convolutional network (GCN) framework to capture node feature information for link prediction. Experiments show that the HWA algorithm proposed in this paper, combined with the GCN framework, shows better link prediction performance than other graph-based neural network benchmark algorithms on eight real networks. This further verifies the validity and reliability of the model in this paper and provides new protection ideas and technical means for information security.

Predicting Feynman periods in ϕ4-theory

We present efficient data-driven approaches to predict the value of subdivergence-free Feynman integrals (Feynman periods) in ϕ4-theory from properties of the underlying Feynman graphs, based on a statistical examination of almost 2 million graphs. We find that the numbers of cuts and cycles determines the period to better than 2% relative accuracy. Hepp bound and Martin invariant allow for even more accurate predictions. In most cases, the period is a multi-linear function of the properties in question. Furthermore, we investigate the usefulness of machine-learning algorithms to predict the period. When sufficiently many properties of the graph are used, the period can be predicted with better than 0.05% relative accuracy.We use one of the constructed prediction models for weighted Monte-Carlo sampling of Feynman graphs, and compute the primitive contribution to the beta function of ϕ4-theory at L ∈ {13, … , 17} loops. Our results confirm the previously known numerical estimates of the primitive beta function and improve their accuracy. Compared to uniform random sampling of graphs, our new algorithm is 1000-times faster to reach a desired accuracy, or reaches 32-fold higher accuracy in fixed runtime.The dataset of all periods computed for this work, combined with a previous dataset, is made publicly available. Besides the physical application, it could serve as a benchmark for graph-based machine learning algorithms.

Grover-QAOA for 3-SAT: quadratic speedup, fair-sampling, and parameter clustering

Abstract The SAT problem is a prototypical NP-complete problem of fundamental importance in computational complexity theory with many applications in science and engineering; as such, it has long served as an essential benchmark for classical and quantum algorithms. This study shows numerical evidence for a quadratic speedup of the Grover Quantum Approximate Optimization Algorithm (G-QAOA) over random sampling for finding all solutions to 3-SAT (All-SAT) and Max-SAT problems. G-QAOA is less resource-intensive and more adaptable for these problems than Grover’s algorithm, and it surpasses conventional QAOA in its ability to sample all solutions. We show these benefits by classical simulations of many-round G-QAOA on thousands of random 3-SAT instances. We also observe G-QAOA advantages on the IonQ Aria quantum computer for small instances, finding that current hardware suffices to determine and sample all solutions. Interestingly, a single-angle-pair constraint that uses the same pair of angles at each G-QAOA round greatly reduces the classical computational overhead of optimizing the G-QAOA angles while preserving its quadratic speedup. We also find parameter clustering of the angles. The single-angle-pair protocol and parameter clustering significantly reduce obstacles to classical optimization of the G-QAOA angles.

Learning-based cooperative content caching and sharing for multi-layer vehicular networks

Caching and sharing the content files is critical and fundamental for various future vehicular applications. However, how to satisfy the content demands in a timely manner with limited storage is an open issue owing to the high mobility of vehicles and the unpredictable distribution of dynamic requests. To better serve the requests from the vehicles, a cache-enabled multi-layer architecture, consisting of a Micro Base Station (MBS) and several Small Base Stations (SBSs), is proposed in this paper. Considering that vehicles usually travel through the coverage of multiple SBSs in a short time period, the cooperative caching and sharing strategy is introduced, which can provide comprehensive and stable cache services to vehicles. In addition, since the content popularity profile is unknown, we model the content caching problems in a Multi-Armed Bandit (MAB) perspective to minimize the total delay while gradually estimating the popularity of content files. The reinforcement learning-based algorithms with a novel Q-value updating module are employed to update the caching files in different timescales for MBS and SBSs, respectively. Simulation results show the proposed algorithm outperforms benchmark algorithms with static or varying content popularity. In the high-speed environment, the cooperation between SBSs effectively improves the cache hit rate and further improves service performance.

Attribute-Aware Graph Convolutional Network Recommendation Method

In recent years, recommendation systems have made significant strides through the application of graph neural networks (GNNs). However, most of the existing methods primarily focus on modeling user–item interactions, often failing to account for the distinct roles of different types of neighboring nodes during the graph convolution process. Moreover, the intricate relationships between user and item attributes are frequently underexplored, which constrains further improvement in the performance of recommendation models. To overcome these challenges, this paper proposes an attribute-aware graph convolutional network recommendation model (AAGCNR). This model accounts for the complex interrelationships between user and item attributes while distinguishing between different types of neighboring nodes during graph convolution. First, a multi-head self-attention mechanism is applied to capture the semantic relationships among attributes across various semantic spaces. Additionally, a bilinear interaction module is employed to facilitate interactions between attributes. Since different neighboring nodes exert different influences on target nodes, the model performs convolutional aggregation by leveraging the interrelationships of these attributes throughout the graph convolution process. Experiments conducted on real-world datasets reveal that AAGCNR outperforms other benchmark algorithms, particularly in terms of RECALL and NDCG metrics.

Technical note: A guide to using three open-source quality control algorithms for rainfall data from personal weather stations

Abstract. The number of rainfall observations from personal weather stations (PWSs) has increased significantly over the past years; however, there are persistent questions about data quality. In this paper, we reflect on three quality control algorithms (PWSQC, PWS-pyQC, and GSDR-QC) designed for the quality control (QC) of rainfall data. Technical and operational guidelines are provided to help interested users in finding the most appropriate QC to apply for their use case. All three algorithms can be accessed within the OpenSense sandbox where users can run the code. The results show that all three algorithms improve PWS data quality when cross-referenced against a rain radar data product. The considered algorithms have different strengths and weaknesses depending on the PWS and official data availability, making it inadvisable to recommend one over another without carefully considering the specific setting. The authors highlight a need for further objective quantitative benchmarking of QC algorithms. This requires freely available test datasets representing a range of environments, gauge densities, and weather patterns.

A comprehensive comparison of deep learning-based compound-target interaction prediction models to unveil guiding design principles

The evaluation of compound-target interactions (CTIs) is at the heart of drug discovery efforts. Given the substantial time and monetary costs of classical experimental screening, significant efforts have been dedicated to develop deep learning-based models that can accurately predict CTIs. A comprehensive comparison of these models on a large, curated CTI dataset is, however, still lacking. Here, we perform an in-depth comparison of 12 state-of-the-art deep learning architectures that use different protein and compound representations. The models were selected for their reported performance and architectures. To reliably compare model performance, we curated over 300 thousand binding and non-binding CTIs and established several gold-standard datasets of varying size and information. Based on our findings, DeepConv-DTI consistently outperforms other models in CTI prediction performance across the majority of datasets. It achieves an MCC of 0.6 or higher for most of the datasets and is one of the fastest models in training and inference. These results indicate that utilizing convolutional-based windows as in DeepConv-DTI to traverse trainable embeddings is a highly effective approach for capturing informative protein features. We also observed that physicochemical embeddings of targets increased model performance. We therefore modified DeepConv-DTI to include normalized physicochemical properties, which resulted in the overall best performing model Phys-DeepConv-DTI. This work highlights how the systematic evaluation of input features of compounds and targets, as well as their corresponding neural network architectures, can serve as a roadmap for the future development of improved CTI models.Scientific contributionThis work features comprehensive CTI datasets to allow for the objective comparison and benchmarking of CTI prediction algorithms. Based on this dataset, we gained insights into which embeddings of compounds and targets and which deep learning-based algorithms perform best, providing a blueprint for the future development of CTI algorithms. Using the insights gained from this screen, we provide a novel CTI algorithm with state-of-the-art performance.

Time-Efficient RSA over Large-Scale Multi-Domain EON.

The poor timeliness of routing has always been an urgent problem in practical operator networks, especially in situations with large-scale networks and multiple network domains. In this article, a pruning idea of routing integrated with Dijkstra's shortest path searching is utilized to accelerate the process of routing in large-scale multi-domain elastic optical networks (EONs). The layered-graph approach is adopted in the spectrum allocation stage. To this end, an efficient heuristic algorithm is proposed, called "Branch-and-Bound based Routing and Layered Graph based Spectrum Allocation algorithm (BBR-LGSA)", which is an integrated RSA algorithm. Notably, the significant reduction in algorithm time complexity is not only reflected in the pruning method used in the routing stage but also in the construction of auxiliary graphs during the spectrum allocation stage utilizing the Branch-and-Bound method. Simulation results show that the proposed BBR-LGSA significantly reduces the average running time by nearly 78% with higher spectrum utilization in large-scale multi-domain EONs, compared with benchmark algorithms. In addition, the impact of key parameters on performance comparisons of different algorithms is evaluated.

Multi-objective optimization algorithms for building performance assessment – A benchmark

The increasing development in the computational field that allowed software and hardware advances enables more refined building performance analysis. Simulation-based optimization (SBO) methods allow high standards to be achieved by combining parametric modeling, simulation, and optimization methods. However, SBO methods still need development, especially regarding the correct choice of the optimization algorithm based on the specific characteristics of each problem. This study proposes a multi-objective optimization algorithms benchmark by comparing seven multi-objective optimization algorithms: RBFMOpt, NSGA2, MHACO, NSPSO, MOEA/D, HypE, and SPEA2, across nine building-related problems, including thermal, energy, and daylight simulation. The problems varied from 5 to 18 discrete, continuous, and mixed parameters. The objective functions varied between two and three. We used the hypervolume indicator, IGD+, GD+, and EPS + to compare algorithms’ performance and assess the tendency to reduce computational costs. We also performed the Kruskal-Wallis non-parametric test to analyze the impact of multiple runs on the hypervolume indicator. The results showed that RBFMOpt and HypE perform best across all problems. However, RBFMOpt tends to reduce computational costs since the algorithm requires fewer simulations to obtain the best results.

Android Malware Detection Using Support Vector Regression for Dynamic Feature Analysis

Mobile devices face significant security challenges due to the increasing proliferation of Android malware. This study introduces an innovative approach to Android malware detection, combining Support Vector Regression (SVR) and dynamic feature analysis to address escalating mobile security challenges. Our research aimed to develop a more accurate and reliable malware detection system capable of identifying both known and novel malware variants. We implemented a comprehensive methodology encompassing dynamic feature extraction from Android applications, feature preprocessing and normalization, and the application of SVR with a Radial Basis Function (RBF) kernel for malware classification. Our results demonstrate the SVR-based model’s superior performance, achieving 95.74% accuracy, 94.76% precision, 98.06% recall, and a 96.38% F1-score, outperforming benchmark algorithms including SVM, Random Forest, and CNN. The model exhibited excellent discriminative ability with an Area Under the Curve (AUC) of 0.98 in ROC analysis. The proposed model’s capacity to capture complex, non-linear relationships in the feature space significantly enhanced its effectiveness in distinguishing between benign and malicious applications. This research provides a robust foundation for advancing Android malware detection systems, offering valuable insights for researchers and security practitioners in addressing evolving malware challenges.

Avoid backtracking and burn your inputs: CONUS-scale watershed delineation using OpenMP

The Memory-Efficient Watershed Delineation (MESHED) parallel algorithm is introduced for Contiguous United States (CONUS)-scale hydrologic modeling. Delineating tens of thousands of watersheds for a continental-scale study can not only be computationally intensive, but also be memory-consuming. Existing algorithms require separate input and output data stores. However, as the number of watersheds to delineate and the resolution of input data grow significantly, the amount of memory required for an algorithm also quickly increases. MESHED uses one data store for both input and output by destructing input data as processed and a node-skipping depth-first search to further reduce required memory. For 1000 watersheds in Texas, MESHED performed 95% faster than the Central Processing Unit (CPU) benchmark algorithm using 33% less memory. In a scaling experiment, it delineated 100,000 watersheds across the CONUS in 13.64s. Given the same amount of memory, MESHED can solve 50% larger problems than the CPU benchmark algorithm can.

Dynamic collaborative truck-drone delivery with en-route synchronization and random requests

Coordinated truck and drone delivery is gaining popularity in logistics as it can greatly reduce operation costs. However, existing studies on related operations management problems typically ignore the following important features: (i) the random appearance of requests, which require operators to dynamically respond to the requests; and (ii) the decisions of optimal launch and retrieval locations for trucks and drones instead of fixed to customer locations, which can significantly impact the overall time costs. To tackle these challenges, this study investigates the dynamic collaborative truck-drone routing problem with randomly arriving requests and synchronization on routes. We model the problem as a Markov Decision Process (MDP) and solve the MDP via a reinforcement learning (RL) approach. The proposed RL approach determines: (i) whether each request should be serviced upon arrival, (ii) which truck or drone should be assigned for the request, and (iii) the optimal en-route take-off and landing positions for paired trucks and drones. We further employ a framework of decentralized learning and centralized dispatching in RL to increase performance. Numerical experiments are conducted to assess the proposed solution approach on instances generated based on both the Solomon dataset and real-world operational data of a logistics operator in Singapore over several benchmark algorithms under various battery endurance levels of drones and distinct transportation scenarios including node-based dynamic collaborative truck-drone routing problem, dynamic non-collaborative truck and drone routing problem, and dynamic vehicle routing problem. The results show that our RL solution outperforms the benchmark algorithm in total profit by an average of 28.03 %, and our en-route takeoff and landing scenario outperforms the benchmark scenarios in total profit by an average of 8.43 % in multi-day instances. Additionally, compared to the traditional node-based landing scenario, employing our en-route takeoff and landing strategy can save 0.9 h/(drone*day) of waiting time on average.

Cuckoo Search Optimization-Based Influence Maximization in Dynamic Social Networks

Online social networks are crucial in propagating information and exerting influence through word-of-mouth transmission. Influence maximization (IM) is the fundamental task in social network analysis to find the group of nodes that maximizes the influence in the social network. IM has different applications like viral marketing, campaigning, advertising, and so on. Literature has presented various algorithms based on different approaches to address the IM problem, including nature-inspired algorithms. Most of the work focuses on the static social network. The proposed work first employs nature-inspired Cuckoo Search Optimization to solve the IM problem in dynamic networks. The proposed algorithm applies the fuzzy-logic-based technique to optimize the nests. We also perform statistical tests to show the effectiveness of the proposed algorithm with the benchmark algorithms. The experimental results are performed on five datasets and compare the results with the state-of-the-art algorithms. The results show that the proposed algorithm gives better results than the nature-inspired state-of-the-art algorithms.

DCDIMB: Dynamic Community-based Diversified Influence Maximization using Bridge Nodes

Influence maximization (IM) is the fundamental study of social network analysis. The IM problem finds the top k nodes that have maximum influence in the network. Most of the studies in IM focus on maximizing the number of activated nodes in the static social network. But in real life, social networks are dynamic in nature. This work addresses the diversification of activated nodes in the dynamic social network. This work proposes an objective function that maximizes the number of communities by utilizing bridge nodes. We also propose a diffusion model that considers the role of inactive nodes in influencing a node. We prove the submodularity, and monotonicity of the objective function under the proposed diffusion model. This work analyzes the impact of different ratios of bridge nodes in the seed set on real-world and synthetic datasets. Furthermore, we prove the NP-Hardness of the objective function under the proposed diffusion model. The experiments are conducted on various real-world and synthetic datasets with known and unknown community information. The proposed work experimentally shows that the objective function gives the maximum number of communities considering bridge nodes compared with the benchmark algorithms.

Multi-temperature capable enhanced bidirectional long short term memory-multilayer perceptron hybrid model for lithium-ion battery SOC estimation

In this study, we propose a novel hybrid modeling framework for State of Charge (SOC) estimation across a broad temperature spectrum. First, we build a hybrid model to optimize stacked layers of stacked bidirectional long short term memory networks by introducing dropout mechanisms. At the same time, we also optimize the traditional multi-layer perceptron model to ResMLP, which is improved by introducing residual linkage, and then integrate the two optimization models. Finally, the synergistic effect and attention mechanism of genetic algorithm and particle swarm optimization are used to optimize its parameters. We then rigorously tested the model on nine datasets, including HPPC, DST and BBDST, at different temperatures of 5 °C, 15 °C and 35 °C. Using MAE, RMSE and MAXE benchmarks, our research results show that the proposed hybrid model outperforms the benchmark algorithm, achieving significantly enhanced performance and higher accuracy, and the maximum SOC estimation error is kept below 4.53 %. In addition, experimental evaluation at different temperatures shows the robustness and adaptability of the proposed algorithm.

FedADMM-InSa: An inexact and self-adaptive ADMM for federated learning

Federated learning (FL) is a promising framework for learning from distributed data while maintaining privacy. The development of efficient FL algorithms encounters various challenges, including heterogeneous data and systems, limited communication capacities, and constrained local computational resources. Recently developed FedADMM methods show great resilience to both data and system heterogeneity. However, they still suffer from performance deterioration if the hyperparameters are not carefully tuned. To address this issue, we propose an inexact and self-adaptive FedADMM algorithm, termed FedADMM-InSa. First, we design an inexactness criterion for the clients’ local updates to eliminate the need for empirically setting the local training accuracy. This inexactness criterion can be assessed by each client independently based on its unique condition, thereby reducing the local computational cost and mitigating the undesirable straggle effect. The convergence of the resulting inexact ADMM is proved under the assumption of strongly convex loss functions. Additionally, we present a self-adaptive scheme that dynamically adjusts each client’s penalty parameter, enhancing algorithm robustness by mitigating the need for empirical penalty parameter choices for each client. Extensive numerical experiments on both synthetic and real-world datasets have been conducted. As validated by some tests, our FedADMM-InSa algorithm improves model accuracy by 7.8% while reducing clients’ local workloads by 55.7% compared to benchmark algorithms.

Control parameter optimisation using the evidence framework for the ant colony optimisation algorithm

The ant colony optimization (ACO) algorithm is a metaheuristic initially designed to solve the travelling salesman problem (TSP). The design of experiments, finding the suitable ACO algorithm configuration, and calibrating the adaptive control parameters are exhaustive and time-consuming exercises, especially for TSPs where the number of cities can exceed 1000. This paper presents an evidence framework driven control parameter optimisation (EFCPO) algorithm for an ACO algorithm solving TSPs. EFCPO performs auto-tuning of the adaptive control parameters and makes recommendations about the ACO algorithms that are best suited for the TSPs in question using the log evidence. In addition, with this ability, the algorithm can take a solution provided by an ACO algorithm and improve the results. The EFCPO accomplishes this over a number of cycles through auto-tuning of the control parameters and re-running the ACO until the process is completed. The capabilities of EFCPO are compared to another configuration tool, irace, using benchmark ACO algorithms to test the efficiency of the framework. The benchmark algorithms make use of a local search strategy to solve TSPs. The results show that ACO algorithms are able to find new and improved solution tours within reasonable times. The improvements are also significant. In addition, ACO algorithms that are best suited for the TSP in question are preferred, making the EFCPO an effective tool for real-time configuration of ACO algorithms for solving TSPs .

UAV Jamming Localization Against Random Eavesdropper Positions Using Cuckoo Search Algorithm

ABSTRACTUnmanned Aerial Vehicle (UAV) jammer localization refers to the process of determining the optimal location for a UAV jammer to be placed to interfere with an eavesdropper's communication with a target. In fact, the main goal is to maximize the jamming signal power at the eavesdropper's position while minimizing the jamming signal power at the target's position. This paper leverages Cuckoo Search algorithm for the secrecy rate optimization which refers to the amount of secure information transmitted from the target to the intended receiver. The model is composed with an UAV jammer, two ground nodes and an illegitimate user with unknown position. True uniform random deployment processes is used to model the randomness of the eavesdropper location. Further, a novel summed secrecy approach is proposed to determine the overall optimal UAV position. Simulations demonstrate the superiority of the novel approach versus other benchmark algorithms across various numbers of eavesdroppers.

A cooperative perception based adaptive signal control under early deployment of connected and automated vehicles

Connected vehicle-based adaptive traffic signal control requires certain market penetration rates (MPRs) to be effective, usually exceeding 10%. Cooperative perception based on connected and automated vehicles (CAVs) can effectively improve overall data collection efficiency and reduce required MPR. However, the distribution of observed vehicles under cooperative perception is highly skewed and imbalanced, especially under very low CAV MPRs (e.g., 1%). To address this challenge, this paper proposes a novel deep reinforcement learning-based adaptive traffic signal control (RL-TSC) method that integrates a traffic flow model, known as the cell transmission model (CTM), denoted as CAVLight. Traffic states estimated from the CTM are integrated with the data collected from the cooperative perception environment to update the states in the CAVLight model. The design of reward function aims for reducing total vehicle delays and stabilizing agent behaviors. Extensive numerical experiments under a real-world intersection with varying traffic demand levels and CAV MPRs are conducted to compare the performance of CAVLight and other benchmark algorithms, including a fixed-time controller, an actuated controller, the max pressure model, and an optimization-based adaptive TSC. Results demonstrate the superiority of CAVLight in performance and generalizability over benchmarks, especially under 1% CAV MPR scenario with high traffic demands. The influence of CTM integration on CAVLight is further explored through RL agent policy visualization and sensitivity analysis in CTM parameters and CAV perception capabilities (i.e., detection range and detection accuracy).