Assignment Mechanism Research Articles

Experimental evaluation of a latency-aware routing and spectrum assignment mechanism based on deep reinforcement learning

The introduction of futuristic and challenging use cases of 5G and 6G communications will demand strict requirements in terms of high bandwidth and low latency. Optical backbone networks need to tackle these new network scenarios by offering highly efficient, flexible, and scalable technologies and solutions. In this context, elastic optical networks (EONs) have been recognized as a promising technological transport infrastructure for the future Internet since they can manage the optical spectrum with enhanced flexibility and efficiency. The service provisioning in EONs is a challenging issue to tackle since the routing and spectrum assignment (RSA) is characterized by a high degree of complexity. This work presents an approach for RSA in EONs leveraging the advantages of deep reinforcement learning (DRL) solutions. The devised approach jointly considers the constraints imposed by the optical technologies and the demanded connectivity service requirements (i.e., guaranteed bandwidth and maximum end-to-end latency) when computing and selecting the optical path and spectral resources. We first evaluate our approach through simulation experiments considering two reference network topologies, demonstrating its effectiveness in reducing the bandwidth blocking ratio, the path computation time, and the number of rejected connectivity services requiring lower latencies when compared to a baseline k-shortest path routing and first-fit spectrum allocation algorithm. Then, the trained DRL agent is integrated within a real proof of concept to attain an ML-assisted SDN control plane in the CTTC ADRENALINE testbed. The attained performance improvements highlight the potential benefits brought by using DRL mechanisms and its feasible integration within production EON transport infrastructures.

The Genetic Code Assembles via Division and Fusion, Basic Cellular Events.

Standard Genetic Code (SGC) evolution is quantitatively modeled in up to 2000 independent coding 'environments'. Environments host multiple codes that may fuse or divide, with division yielding identical descendants. Code division may be selected-sophisticated gene products could be required for an orderly separation that preserves the coding. Several unforeseen results emerge: more rapid evolution requires unselective code division rather than its selective form. Combining selective and unselective code division, with/without code fusion, with/without independent environmental coding tables, and with/without wobble defines 25 = 32 possible pathways for SGC evolution. These 32 possible histories are compared, specifically, for evolutionary speed and code accuracy. Pathways differ greatly, for example, by ≈300-fold in time to evolve SGC-like codes. Eight of thirty-two pathways employing code division evolve quickly. Four of these eight that combine fusion and division also unite speed and accuracy. The two most precise, swiftest paths; thus the most likely routes to the SGC are similar, differing only in fusion with independent environmental codes. Code division instead of fusion with unrelated codes implies that exterior codes can be dispensable. Instead, a single ancestral code that divides and fuses can initiate fully encoded peptide biosynthesis. Division and fusion create a 'crescendo of competent coding', facilitating the search for the SGC and also assisting the advent of otherwise uniformly disfavored wobble coding. Code fusion can unite multiple codon assignment mechanisms. However, via code division and fusion, an SGC can emerge from a single primary origin via familiar cellular events.

Relation Between Objective Space Normalization and Weight Vector Scaling in Decomposition-Based Multiobjective Evolutionary Algorithms

Real-world multiobjective optimization problems (MOPs) usually have conflicting and differently-scaled objectives. To deal with such problems, objective space normalization is widely used in multiobjective evolutionary algorithm (MOEA) design, especially, in the design of decomposition-based MOEAs. It has been demonstrated that uniformly-distributed solutions can be obtained for badly-scaled MOPs by decomposition-based MOEAs with objective space normalization. Recently, weight vector scaling has also been used for badly-scaled MOPs. In some studies, it was argued that weight vector scaling and objective space normalization are essentially the same when applied to decomposition-based MOEAs. In this paper, we theoretically and empirically show the relation between objective space normalization and weight vector scaling. Our results demonstrate that similarities and differences between the two methods depend on the choice of a scalarizing function. How the choice between normalization and weight vector scaling affects decomposition-based MOEAs with solution assignment mechanisms is also analyzed.

A Multiplatform-Cooperation-Based Task Assignment Mechanism for Mobile Crowdsensing

Mobile crowdsensing (MCS) has been an effective sensing paradigm by utilizing the smart devices carried by mobile users to complete sensing tasks at different locations. An important problem in MCS is how to achieve effective task assignment in the context of opportunistic sensing, where mobile users are selectively recruited to perform tasks in an opportunistic way. However, most existing work in this aspect suppose there are only one service platform and further the sensing qualities of users are known apriori. In this paper, we study the task assignment when there are multiple service platforms and further the sensing qualities of users are unknown apriori. The design objective is to maximize the overall sensing qualities of finished tasks at all platforms. For this purpose, we build a multi-platform cooperation framework and formulate the task quality maximization problem in this case as a 0-1 integer linear programming (ILP) problem. We propose a Multi-platform Cooperation based Task Assignment mechanism (MCTA). MCTA includes two phases. The first phase establishes stable cooperation relationship among platforms while respecting their respective cooperation willingness, and for this phase, we propose a cross-platform cooperation relationship construction algorithm. The second phase performs effective online task assignment, and for this phase, we propose two online Multi-Armed Bandit (MAB) with sleeping arms based user selection algorithms using local and global learning, respectively, based on whether cross-platform user-sensing-quality learning is allowed. We derive the regrets of the proposed algorithms and prove that MCTA has the properties of cooperation stability and computation efficiency. Extensive simulation results show the high performance of our proposed MCTA mechanism as compared with existing work.

Probabilistic Coverage Constraint Task Assignment with Privacy Protection in Vehicular Crowdsensing.

The increasing popularity of portable smart devices has led to the emergence of vehicular crowdsensing as a novel approach for real-time sensing and environmental data collection, garnering significant attention across various domains. Within vehicular crowdsensing, task assignment stands as a fundamental research challenge. As the number of vehicle users and perceived tasks grows, the design of efficient task assignment schemes becomes crucial. However, existing research solely focuses on task deadlines, neglecting the importance of task duration. Additionally, the majority of privacy protection mechanisms in the current task assignment process emphasize safeguarding user location information but overlook the protection of user-perceived duration. This lack of protection exposes users to potential time-aware inference attacks, enabling attackers to deduce user schedules and device information. To address these issues in opportunistic task assignment for vehicular crowdsensing, this paper presents the minimum number of participants required under the constraint of probability coverage and proposes the User-Based Task Assignment (UBTA) mechanism, which selects the smallest set of participants to minimize the payment cost while measuring the probability of accomplishing perceived tasks by user combinations. To ensure privacy protection during opportunistic task assignment, a privacy protection method based on differential privacy is introduced. This method fuzzifies the sensing duration of vehicle users and calculates the probability of vehicle users completing sensing tasks, thus avoiding the exposure of users' sensitive data while effectively assigning tasks. The efficacy of the proposed algorithm is demonstrated through theoretical analysis and a comprehensive set of simulation experiments.

Strategy-proof and envy-free mechanisms for house allocation

We consider the problem of allocating indivisible objects to agents when agents have strict preferences over objects. There are inherent trade-offs between competing notions of efficiency, fairness and incentives in such assignment mechanisms. It is, therefore, natural to consider mechanisms that satisfy two of these three properties in their strongest notions, while trying to improve on the third dimension. In this paper, we are motivated by the following question: Is there a strategy-proof and envy-free random assignment mechanism more efficient than equal division?Our contributions in this paper are twofold. First, we further explore the incompatibility between efficiency, fairness, and strategy-proofness within random assignment mechanisms. We define a new notion of efficiency that is weaker than ex-post efficiency and prove that any strategy-proof and envy-free mechanism must sacrifice efficiency even in this very weak sense. Next, we introduce a new family of mechanisms called Rank Exchange mechanisms that are strategy-proof and envy-free and stochastically dominate equal division. Further, we show that Rank Exchange mechanisms characterize the set of neutral, strategy-proof, and envy-free mechanisms that also satisfy a natural separability axiom that may be of independent interest.

Federated causal inference in heterogeneous observational data.

We are interested in estimating the effect of a treatment applied to individuals at multiple sites, where data is stored locally for each site. Due to privacy constraints, individual-level data cannot be shared across sites; the sites may also have heterogeneous populations and treatment assignment mechanisms. Motivated by these considerations, we develop federated methods to draw inferences on the average treatment effects of combined data across sites. Our methods first compute summary statistics locally using propensity scores and then aggregate these statistics across sites to obtain point and variance estimators of average treatment effects. We show that these estimators are consistent and asymptotically normal. To achieve these asymptotic properties, we find that the aggregation schemes need to account for the heterogeneity in treatment assignments and in outcomes across sites. We demonstrate the validity of our federated methods through a comparative study of two large medical claims databases.

Simulation-based joint user assignment and edge resource allocation optimization for hybrid tasks in vehicular edge computing

With the swift advancement of 5G communication technology and the widespread prevalence of intelligent connected vehicles, a multitude of applications for the Internet of Vehicles (IoV) have been steadily burgeoning. Nevertheless, owing to vehicular mobility and the variety of tasks generated by IoV applications competing for restricted edge resources, the task of assigning users to edge nodes, in addition to appropriating edge node resources to hybrid tasks within edge environments, persists as a formidable challenge. In addressing this predicament, we establish a model delineating the execution duration of hybrid tasks engendered by IoV applications, and introduce a joint mechanism for user assignment and edge resource allocation. Within this mechanism, we architect an optimal strategy for edge resource allocation, predicated upon given user assignment outcomes. In order to ascertain the user assignment strategy, we employ an enhanced genetic algorithm in scenarios of a large user base, and utilize the branch-and-bound algorithm when dealing with a small user base. Finally, we design and implement an experimental setup for joint user assignment and edge resource allocation. The comprehensive simulation results provide robust verification of the effectiveness of our proposed mechanism.

Edge Trusted Sharing: Task-Driven Decentralized Resources Collaborate in IoT

6G is committed to providing a fully connected world. The deployment and application of 6G technology in the Internet of Things (IoT) can efficiently collaborate IoT resources and realize resource sharing, which mainly encourages IoT development. However, due to the lack of trust between IoT resources, security and privacy become the main challenges. As an emerging technology, blockchain can solve the trust-absence issues and provide more benefits, but the introduction of blockchain also brings problems for IoT resource collaboration and sharing. This article first proposes a blockchain-enabled edge resource sharing (BEERS) architecture by combining blockchain and edge computing technology. Then, based on a typical resource sharing and collaboration scenario, the joint optimization problem of resource scheduling and task assignment (JRSTA) is constructed. We decompose JRSTA into a primal problem and a master problem and design a greedy-based task assignment (GBTA) algorithm to solve the primal problem. Based on the GBTA algorithm, the resource scheduling and task assignment (RSTA) algorithm is developed. Next, we design a layered parallel edge resource scheduling and task assignment (LPRSTA) mechanism to improve practicability. Finally, we analyze the security and the performance of our proposed architecture and algorithms. The results show that the proposed architecture can support the secure collaboration of IoT resources, and the proposed algorithm can achieve effective resource scheduling and task assignment.

Planning-based mobile crowdsourcing bidirectional multi-stage online task assignment

With the development of mobile Internet networks, Mobile CrowdSourcing (MCS) is becoming increasingly popular in online scenarios. This poses a new challenge to the task assignment mechanism in the mobile crowdsourcing system. Existing task assignment schemes are mainly platform-centric and worker-centric. The previous focuses are on the total utility, while the latter focuses on the interests of workers. In actual online scenarios, current researches are difficult to take both platform and worker wishes into consideration. In this paper, a Bidirectional Multi-Stage Online task assignment algorithm (BMSO) is proposed. It divides the task assignment process into three stages. The first stage selects tasks not only satisfy the basic Spatio-temporal constraints but also have a high acceptance value for workers by using two rounds of screening. The second stage combines price forecasting with reverse auctions, considering both of the platform’s benefits and workers’ wish. In the third stage, the workers and tasks which have not completed their assignments are assigned twice to improve the total utility. Furthermore, we solve the problem that traditional task-planning methods are unsuitable for mobile crowdsourcing scenarios. This paper proposes a Dynamic Voronoi diagram-based Task Planning algorithm (DVTP) that generates a Voronoi diagram using the real-time positions of the workers to find the most efficient task execution sequence for the workers. Finally, we conduct comprehensive experiments on real datasets. The results demonstrate our proposed BMSO algorithm achieves superior performances on total utility, running time, number of assigned tasks, and task assignment rate compared to other baseline algorithms.

Bayesian Optimization-Based Combinatorial Assignment

We study the combinatorial assignment domain, which includes combinatorial auctions and course allocation. The main challenge in this domain is that the bundle space grows exponentially in the number of items. To address this, several papers have recently proposed machine learning-based preference elicitation algorithms that aim to elicit only the most important information from agents. However, the main shortcoming of this prior work is that it does not model a mechanism's uncertainty over values for not yet elicited bundles. In this paper, we address this shortcoming by presenting a Bayesian optimization-based combinatorial assignment (BOCA) mechanism. Our key technical contribution is to integrate a method for capturing model uncertainty into an iterative combinatorial auction mechanism. Concretely, we design a new method for estimating an upper uncertainty bound that can be used to define an acquisition function to determine the next query to the agents. This enables the mechanism to properly explore (and not just exploit) the bundle space during its preference elicitation phase. We run computational experiments in several spectrum auction domains to evaluate BOCA's performance. Our results show that BOCA achieves higher allocative efficiency than state-of-the-art approaches.

Learning Instrumental Variable from Data Fusion for Treatment Effect Estimation

The advent of the big data era brought new opportunities and challenges to draw treatment effect in data fusion, that is, a mixed dataset collected from multiple sources (each source with an independent treatment assignment mechanism). Due to possibly omitted source labels and unmeasured confounders, traditional methods cannot estimate individual treatment assignment probability and infer treatment effect effectively. Therefore, we propose to reconstruct the source label and model it as a Group Instrumental Variable (GIV) to implement IV-based Regression for treatment effect estimation. In this paper, we conceptualize this line of thought and develop a unified framework (Meta-EM) to (1) map the raw data into a representation space to construct Linear Mixed Models for the assigned treatment variable; (2) estimate the distribution differences and model the GIV for the different treatment assignment mechanisms; and (3) adopt an alternating training strategy to iteratively optimize the representations and the joint distribution to model GIV for IV regression. Empirical results demonstrate the advantages of our Meta-EM compared with state-of-the-art methods. The project page with the code and the Supplementary materials is available at https://github.com/causal-machine-learning-lab/meta-em.

Assigning Property Rights to Scarce Resources when Individual Wealth Levels are Observable

Abstract In this note, we consider how to allocate property rights to scarce resources when agents have budget constraints. Each individual’s wealth level is often observable to the state, although the individual subjective valuation for the resource is hardly known to the state. Under this situation, we mainly compare the efficiency of allocations under two assignment mechanisms; (i) the random assignment with resale and (ii) priority assignment to the poorest with resale. We show that the latter is more efficient than the former. If the mass of goods to be allocated is large enough, the latter can achieve social optimum.

If You Love Your Agents, Set Them Free: Task Discretion in Online Workplaces

In manufacturing and service operations, flexibility is beneficial for matching supply with demand, but it comes at a cost. In modern digital workplaces, agents have different skills associated with corresponding and variable task preferences. Some are inclined to give up part of their payment to avoid unfavorable matches, and the platform manager, in turn, gains extra freedom in allocating tasks by possibly charging servers for favorable assignments. Innovative marketplaces facilitate task discretion and seek novel and beneficial implementations in the platform design. This naturally leads to the problem of exploring and optimizing the task allocation process. We introduce an innovative mechanism for task assignment in the workplace and compare it to the traditional mechanism in which task routing is solely the platform’s decision. To improve the welfare of all users, agents are allowed some task discretion in exchange for a fee. In a multiserver system, a server may request flexibility and, considering the other agents’ behavior, choose the costly to the platform option, which may or may not be beneficial for the platform when the agents’ and the platform’s preferences are misaligned. We model different working environments and server preferences via different distributions and study how the agents’ preferences, task costs, and flexibility fee affect the equilibrium assignment. In every case, through pricing and offering flexibility, the platform can do at least as well as a scheme with no flexibility. An important conclusion is that pricing task discretion can often improve the agents’ welfare and the labor platform’s profit. This paper was accepted by Victor Martínez-de-Albéniz, operations management.

A two-stage federated optimization algorithm for privacy computing in Internet of Things

With the advent of the Internet of things (IoT) era, federated learning plays an important role in breaking through traditional data barriers and effectively realizing data privacy and security in the process of sharing. However, the demand of the practical problems makes the algorithm still have great challenges in effectively balancing various factors, such as privacy security, accuracy, computing efficiency and so on. To challenge this problem, a two-stage federated optimization algorithm based on robust and multitasking learning is designed. In optimization client local model stage, an adaptive weight assignment mechanism is adopted to guide robust learning based on multiple untrusted sources data, which aims to ensure the credibility and robustness of the client model and obtain a reliable client model. To address the information leakage problem during the server–client global model optimization stage, a privacy patch layer is added to the client local model in multitask learning and maintain its privacy parameters stored on the client model during the global model parameter aggregation process, which aims to meet the personalized requirements and performance requirements of protecting the model privacy. To effectively measure the performance of our algorithm, two extensive experiments are carried out to verify the robustness and accuracy of model under different datasets, respectively. In addition, simulation results show that our algorithm successfully suppresses the impact of corrupted or irrelevant sources on performance, and its performance is better than the other two robust distributed learning baseline methods in the client local model optimization stage. At the same time, our algorithm achieves better accuracy performance than other advanced personalized optimization algorithms in the server–client global model optimization stage. Finally, it achieves a good balance between robustness, computational efficiency and model privacy protection.

Bayesian causal inference: a critical review.

This paper provides a critical review of the Bayesian perspective of causal inference based on the potential outcomes framework. We review the causal estimands, assignment mechanism, the general structure of Bayesian inference of causal effects and sensitivity analysis. We highlight issues that are unique to Bayesian causal inference, including the role of the propensity score, the definition of identifiability, the choice of priors in both low- and high-dimensional regimes. We point out the central role of covariate overlap and more generally the design stage in Bayesian causal inference. We extend the discussion to two complex assignment mechanisms: instrumental variable and time-varying treatments. We identify the strengths and weaknesses of the Bayesian approach to causal inference. Throughout, we illustrate the key concepts via examples. This article is part of the theme issue 'Bayesian inference: challenges, perspectives, and prospects'.

Learning end-to-end patient representations through self-supervised covariate balancing for causal treatment effect estimation

A causal effect can be defined as a comparison of outcomes that result from two or more alternative actions, with only one of the action-outcome pairs actually being observed. In healthcare, the gold standard for causal effect measurements is randomized controlled trials (RCTs), in which a target population is explicitly defined and each study sample is randomly assigned to either the treatment or control cohorts. The great potential to derive actionable insights from causal relationships has led to a growing body of machine-learning research applying causal effect estimators to observational data in the fields of healthcare, education, and economics. The primary difference between causal effect studies utilizing observational data and RCTs is that for observational data, the study occurs after the treatment, and therefore we do not have control over the treatment assignment mechanism. This can lead to massive differences in covariate distributions between control and treatment samples, making a comparison of causal effects confounded and unreliable. Classical approaches have sought to solve this problem piecemeal, first by predicting treatment assignment and then treatment effect separately. Recent work extended part of these approaches to a new family of representation-learning algorithms, showing that the upper bound of the expected treatment effect estimation error is determined by two factors: the outcome generalization-error of the representation and the distance between the treated and control distributions induced by the representation. To achieve minimal dissimilarity in learning such distributions, in this work we propose a specific auto-balancing, self-supervised objective. Experiments on real and benchmark datasets revealed that our approach consistently produced less biased estimates than previously published state-of-the-art methods. We demonstrate that the reduction in error can be directly attributed to the ability to learn representations that explicitly reduce such dissimilarity; further, in case of violations of the positivity assumption (frequent in observational data), we show our approach performs significantly better than the previous state of the art. Thus, by learning representations that induce similar distributions of the treated and control cohorts, we present evidence to support the error bound dissimilarity hypothesis as well as providing a new state-of-the-art model for causal effect estimation.

A Simple Characterization of Assignment Mechanisms on Set Constraints

We consider the problem of allocating divisible/indivisible goods to agents according to agents’ ordinal preferences. Hashimoto et al. [15] provided a nonalgorithmic and axiomatic characterization of well-studied probabilistic serial (PS) mechanism. Recently, Fujishige et al. [12] generalized the PS mechanism where goods are enlarged from a fixed set to a family of sets which is a polytope defined by a system of linear inequalities associated with submodular functions. The above extended PS (EPS) greatly improved the flexibility of allocations. Based on these two results, in this paper, we investigate the nonalgorithmic and axiomatic characterization of EPS. We show that the EPS rule is the only mechanism satisfying the ordinal fairness and a newly defined non-wastefulness. The submodularity plays a crucial role in our arguments.

College-major choice to college-then-major choice: Experimental evidence from Chinese college admissions reforms

One of the most important mechanism design policies in college admissions is to let students choose a college major sequentially (college-then-major choice) or jointly (college-major choice). In the context of the Chinese meta-major reforms that transition from college-major choice to college-then-major choice, we provide the first experimental evidence on the information frictions and heterogeneous preferences that students have in their response to the meta-major option. In a randomized experiment with a nationwide sample of 11,424 high school graduates, we find that providing information on the benefits of a meta-major significantly increased students’ willingness to choose the meta-major; however, information about specific majors and assignment mechanisms did not affect students major choice preferences. We also find that information provision mostly affected the preferences of students who were from disadvantaged backgrounds, lacked accurate information, did not have clear major preferences, or were risk loving.

Towards energy-efficient and time-sensitive task assignment in cross-silo federated learning

Federated learning (FL) is a novel distributed learning framework in which clients with models can collaboratively train a high-quality global model while maintaining the privacy of their local data. The heterogeneity of datasets makes the global aggregation and local training requirements of each client in the cross-silo scenario inconsistent. Although many efforts are dedicated to improving the efficiency of cross-silo FL, the task assignment design of cross-silo FL remains an open question. To optimize the efficiency of energy consumption and training time of cross-silo FL, we develop a novel Energy-efficient and Time-sensitive Task Assignment (ETTA) mechanism. Specifically, we model clients’ requirements for energy efficiency and training time in cross-silo FL as an optimization problem, and design a utility transfer function to maintain the honesty of clients and the stability of ETTA. In terms of energy efficiency maximization, we analyze the conditions of optimal solutions based on the equilibrium of marginal cost and income, and design an approximate algorithm for cross-silo FL scenarios that require lightweight mechanisms. In terms of training time minimization, we model this objective as a min–max problem and give its analytical solution with Pareto optimality. To ensure that the task assignment achieves incentive compatibility, we further design a utility transfer selection function to incentivize honest collaboration among selfish clients. Finally, we conduct extensive experiments on the performance of ETTA to demonstrate that it outperforms the state-of-the-art and can maintain stability in a dishonest environment.