Search

Rank aggregation combines the preference rankings of multiple alternatives from different voters into a single consensus ranking, providing a useful model for a variety of practical applications but posing a computationally challenging problem. In this paper, we provide an effective hybrid evolutionary ranking algorithm to solve the rank aggregation problem with both complete and partial rankings. The algorithm features a semantic crossover based on concordant pairs and an enhanced late acceptance local search method reinforced by a relaxed acceptance and replacement strategy and a fast incremental evaluation mechanism. Experiments are conducted to assess the algorithm, indicating a highly competitive performance on both synthetic and real-world benchmark instances compared with state-of-the-art algorithms. To demonstrate its practical usefulness, the algorithm is applied to label ranking, a well-established machine learning task. We additionally analyze several key algorithmic components to gain insight into their operation. History: Accepted by Erwin Pesch, Area Editor for Heuristic Search & Approximation Algorithms. Funding: This work was supported by the National Natural Science Foundation of China [Grant 72371157] and Shanghai Pujiang Programme [Grant 23PJC069]. Supplemental Material: The software that supports the findings of this study is available within the paper and its Supplemental Information (https://pubsonline.informs.org/doi/suppl/10.1287/ijoc.2022.0019) as well as from the IJOC GitHub software repository (https://github.com/INFORMSJoC/2022.0019). The complete IJOC Software and Data Repository is available at https://informsjoc.github.io/. [ABSTRACT FROM AUTHOR]

Imbalanced classification is widely referred in many real-world applications and has been extensively studied. Most existing algorithms consider alleviating the imbalance by sampling or guiding ensemble learners with punishments. The combination of ensemble learning and sampling strategy at class level has achieved great progress. Actually, specific hard examples have little benefit for model learning and even degrade the performance. From the view of identifying classification difficulty of samples, one important motivation is to design algorithms to finely equip different samples with progressive learning. Unfortunately, how to perfectly configure the sampling and learning strategies under ensemble principles at the sample level remains a research gap. In this paper, we propose a new view from the sample level rather than class level in existing studies. We design an ensemble approach in pipe with sample-level gradient resampling, that is, balanced cascade with filters (BCWF). Before that, as a preliminary exploration, we first design a hard examples mining algorithm to explore the gradient distribution of classification difficulty of samples and identify the hard examples. Specifically, BCWF uses an under-sampling strategy and a boosting manner to train T predictive classifiers and reidentify hard examples. In BCWF, moreover, we design two types of filters: the first is assembled with a hard filter (BCWF_h), whereas the second is assembled with a soft filter (BCWF_s). In each round of boosting, BCWF_h strictly removes a gradient/set of the hardest examples from both classes, whereas BCWF_s removes a larger number of harder and easy examples simultaneously for final balanced-class retention. Consequently, the well-trained T predictive classifiers can be used with two ensemble voting strategies: average probability and majority vote. To evaluate the proposed approach, we conduct intensive experiments on 10 benchmark data sets and apply our algorithms to perform default user detection on a real-world peer to peer lending data set. The experimental results fully demonstrate the effectiveness and the managerial implications of our approach when compared with 11 competitive algorithms. History: Accepted by Ram Ramesh, Area Editor for Data Science & Machine Learning. Funding: This work was supported by the National Natural Science Foundation of China [Grants 72101176, 71722005, and 72241432], the National Key R&D program of China [Grant 2020YFA0908600] and the Natural Science Foundation of Tianjin City [Grant 18JCJQJC45900]. Supplemental Material: The software that supports the findings of this study is available within the paper and its Supplemental Information (https://pubsonline.informs.org/doi/suppl/10.1287/ijoc.2023.1274) as well as from the IJOC GitHub software repository (https://github.com/INFORMSJoC/2021.0104) at (http://dx.doi.org/10.5281/zenodo.6360996). [ABSTRACT FROM AUTHOR]

Federated learning is a new distributed machine learning framework, where numerous heterogeneous clients collaboratively train a model without sharing training data. In this work, we consider a practical and ubiquitous issue when deploying federated learning in mobile environments: intermittent client availability, where the set of eligible clients may change during the training process. Such intermittent client availability would seriously deteriorate the performance of the classical federated averaging algorithm (FedAvg). Thus, we propose a simple distributed nonconvex optimization algorithm, called federated latest averaging (FedLaAvg), which leverages the latest gradients of all clients, even when the clients are not available, to jointly update the global model in each iteration. Our theoretical analysis shows that FedLaAvg achieves guaranteed convergence and a sublinear speedup with respect to the total number of clients. We implement FedLaAvg along with several baselines and evaluate them over the benchmarking MNIST and Sentiment140 data sets. The evaluation results demonstrate that FedLaAvg achieves more stable training than FedAvg in both convex and nonconvex settings and reaches a sublinear speedup. Source code and online supplement are available at the IJOC GitHub site (http://dx.doi.org/10.1287/ijoc.2022.0057.cd, https://github.com/INFORMSJoC/2022.0057). History: Accepted by Ram Ramesh, Area Editor for Data Science & Machine Leaning. Funding: This work was supported by the National Key R&D Program of China [Grant 2022ZD0119100], the National Natural Science Foundation of China (NSFC) [Grants 61972252, 61972254, 62072303, 62025204, 62132018, 62202296, and 62202297], the Alibaba Innovation Research (AIR) Program, and the Tencent Rhino Bird Key Research Project. Supplemental Material: The software that supports the findings of this study is available within the paper and its Supplemental Information (https://pubsonline.informs.org/doi/suppl/10.1287/ijoc.2022.0057) as well as from the IJOC GitHub software repository (https://github.com/INFORMSJoC/2022.0057). The complete IJOC Software and Data Repository is available at https://informsjoc.github.io/. [ABSTRACT FROM AUTHOR]

We propose a preference-learning algorithm for uncovering Decision Makers' (DMs') contingent evaluation strategies in the context of multiple criteria sorting. We assume the preference information in the form of holistic assignment examples derived from the analysis of alternatives' performance vectors and textual descriptions. We characterize the decision policies using a mixture of threshold-based, value-driven preference models and associated latent topics. The latter serve as the stimuli underlying the contingency in decision behavior. Such a probabilistic model is constructed by using a flexible and nonparametric Bayesian framework. The proposed method adopts a hierarchical Dirichlet process as the prior so that a group of DMs can share a countably infinite number of contingent models and topics. For all DMs, it automatically identifies the components representing their evaluation strategies adequately. The posterior is summarized by using the Hamiltonian Monte Carlo sampling method. We demonstrate the method's practical usefulness in a real-world recruitment problem considered by a Chinese IT company. We also compare the approach with counterparts that use a single preference model, implement the parametric framework, or consider each DM's preferences individually. The results indicate that our approach performs favorably in both interpreting DMs' contingent decision behavior and recommending decisions on new alternatives. Furthermore, the approach's performance and robustness are investigated through a computational experiment involving real-world data sets. History: Accepted by Ram Ramesh, Area Editor for Data Science and Machine Learning. Funding: J. Liu received financial support from the National Natural Science Foundation of China [Grants 72071155 and 71701160]. M. Kadziński received financial support from the Polish National Science Center under the SONATA BIS project [Grant DEC-2019/34/E/HS4/00045]. X. Liao received financial support from the National Natural Science Foundation of China [Grant 71872144]. Supplemental Material: The software that supports the findings of this study is available within the paper and its Supplemental Information (https://pubsonline.informs.org/doi/suppl/10.1287/ijoc.2023.1292) as well as from the IJOC GitHub software repository (https://github.com/INFORMSJoC/2021.0328) at (http://dx.doi.org/10.5281/zenodo.7608750). [ABSTRACT FROM AUTHOR]

Personalized points-of-interest (POI) recommendation is very important for improving the service quality of location-based social network applications. It has become one of the most popular research directions in the industry and academia. However, the realization of high-quality personalized POI recommendation faces three major challenges: (i) the interest drift issue caused by the spatiotemporal dynamics of user check-in behavior, (ii) how to integrate as much heterogeneous information as possible to alleviate data sparseness and cold start issues, and (iii) how to use implicit feedback to model complex high-order nonlinear user-POI interactions. To jointly address all these challenges, we propose the TGVx recommendation framework and establish a dynamic personalized POI deep recommendation model, where T and G respectively represent time and geographic factors, V represents out-of-town visitors, and x represents time slot number. TGVx is composed of x parallel TGV models where the TG module mines high-order nonlinear user-POI interaction relationships and integrates multisource heterogeneous information, and the V module transfers the check-in records of out-of-town visitors in hometowns and generates pseudo check-in records in the target city. Technically, we design a new unsupervised deep learning network T-SemiDAE for the TG module. We built a POI-word heterogeneous network for the V module and used graph embedding technology to match the most similar POIs across cities and transfer check-in records. The experimental results on the actual datasets show that the TGVx model is always better than other advanced models in terms of accuracy and diversity for local and out-of-town recommendation scenarios. Compared with the best baseline model semi-deep auto-encoder with a conditional layer the average improvement rates of accuracy and diversity of TGVx are 17.1% to 58.6% and 2.25% to 28.86%, respectively. In theory, our research effectively uses data science and analysis methods to design a recommender system. In practice, our research is motivated by practical problems, and the research results have high practical promotion value. History: Accepted by Ram Ramesh, Area Editor for Data Science & Machine Learning. Funding: This work was supported by the National Natural Science Foundation of China [Grants 71831003, 72293563, and 72172025], the Dalian Science and Technology Talent Innovation Support Policy Project [The High-level Talent Innovation Team Project 2022RG17], and the Liaoning Provincial Department of Education [Basic Scientific Research Project LJKMZ20221582]. Supplemental Material: The software that supports the findings of this study is available within the paper and its Supplemental Information (https://pubsonline.informs.org/doi/suppl/10.1287/ijoc.2023.1286) as well as from the IJOC GitHub software repository (https://github.com/INFORMSJoC/2021.0010) at (http://dx.doi.org/10.5281/zenodo.7407123). [ABSTRACT FROM AUTHOR]