pith. machine review for the scientific record. sign in

arxiv: 2604.07572 · v1 · submitted 2026-04-08 · 💻 cs.IR

Recognition: unknown

HiMARS: Hybrid multi-objective algorithms for recommender systems

Elaheh Lotfian , Alireza Kabgani
Authors on Pith no claims yet

Pith reviewed 2026-05-10 17:08 UTC · model grok-4.3

classification 💻 cs.IR
keywords recommender systemsmulti-objective optimizationaccuracydiversityhybrid algorithmsPareto frontcollaborative filteringtop-k recommendations
0
0 comments X

The pith

Hybrid multi-objective algorithms can simultaneously raise both accuracy and diversity in recommender systems.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper proposes four hybrid multi-objective algorithms that blend elements from immune, annealing, and genetic algorithms to balance accuracy and diversity. It first builds a broad top-k list with item-based collaborative filtering, then solves a bi-objective problem to locate Pareto-optimal top-s subsets where s is much smaller than k, and finally selects one personalized list from the front. A reader would care because most recommenders optimize accuracy alone and produce repetitive suggestions that reduce long-term usefulness. The experiments on real datasets indicate that some of the hybrids improve both metrics at once compared with prior methods.

Core claim

The central claim is that four novel hybrid multi-objective algorithms, derived from NNIA, AMOSA, and NSGA-II, can solve a bi-objective optimization problem on top-s subsets drawn from an initial top-k list produced by item-based collaborative filtering, yielding Pareto fronts from which an optimal personalized top-s list can be chosen, with some hybrids significantly improving both accuracy and diversity over existing approaches.

What carries the argument

The three-stage pipeline that applies hybrid evolutionary algorithms to a bi-objective accuracy-diversity optimization problem on subsets of a top-k list to produce Pareto-optimal top-s recommendations.

If this is right

  • Some of the hybrid algorithms produce recommendation lists that score higher on both accuracy and diversity than baselines.
  • The Pareto fronts supply multiple non-dominated options so a system can pick the list best suited to a user.
  • Standard Pareto-quality metrics such as spacing and spread confirm that the fronts contain well-distributed solutions.
  • The method supplies a concrete new technique for handling conflicting objectives inside recommender systems.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The same hybrid structure could be applied to other pairs of conflicting goals such as novelty versus coverage.
  • The three-stage process could be inserted into existing pipelines that already compute an initial top-k list.
  • Computational cost of the hybrids may limit deployment to large-scale real-time systems unless further tuned.
  • Results could change if the initial top-k list is generated by a different base recommender instead of item-based collaborative filtering.

Load-bearing premise

The bi-objective optimization on top-s subsets of the initial top-k list accurately captures the accuracy-diversity trade-off that matters to users.

What would settle it

If independent tests on multiple benchmark datasets show that none of the four hybrids consistently outperform strong single-objective baselines or prior multi-objective recommenders on both accuracy and diversity, the central claim would be refuted.

read the original abstract

In recommender systems, it is well-established that both accuracy and diversity are crucial for generating high-quality recommendation lists. However, achieving a balance between these two typically conflicting objectives remains a significant challenge. In this work, we address this challenge by proposing four novel hybrid multi-objective algorithms inspired by the Non-dominated Neighbor Immune Algorithm (NNIA), Archived Multi-Objective Simulated Annealing (AMOSA), and Non-dominated Sorting Genetic Algorithm-II (NSGA-II), aimed at simultaneously enhancing both accuracy and diversity through multi-objective optimization. Our approach follows a three-stage process: First, we generate an initial top-$k$ list using item-based collaborative filtering for a given user. Second, we solve a bi-objective optimization problem to identify Pareto-optimal top-$s$ recommendation lists, where $s \ll k$, using the proposed hybrid algorithms. Finally, we select an optimal personalized top-$s$ list from the Pareto-optimal solutions. We evaluate the performance of the proposed algorithms on real-world datasets and compare them with existing methods using conventional metrics in recommender systems such as accuracy, diversity, and novelty. Additionally, we assess the quality of the Pareto frontiers using metrics including the spacing metric, mean ideal distance, diversification metric, and spread of non-dominated solutions. Results demonstrate that some of our proposed algorithms significantly improve both accuracy and diversity, offering a novel contribution to multi-objective optimization in recommender systems.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 2 minor

Summary. The paper proposes four novel hybrid multi-objective algorithms (inspired by NNIA, AMOSA, and NSGA-II) for recommender systems to balance accuracy and diversity. It follows a three-stage process: (1) generate an initial top-k list via item-based collaborative filtering, (2) solve a bi-objective optimization problem over subsets to identify Pareto-optimal top-s lists (s ≪ k) using the hybrids, and (3) select a personalized top-s recommendation from the Pareto front. The approach is evaluated on real-world datasets against conventional accuracy, diversity, and novelty metrics, plus Pareto-front quality measures (spacing, mean ideal distance, diversification, spread), with results indicating that some hybrids significantly improve both accuracy and diversity.

Significance. If the empirical gains hold under scrutiny, the work offers a concrete demonstration of hybrid MOEAs applied to a constrained bi-objective RS problem, extending prior single-objective or non-hybrid multi-objective methods. The explicit three-stage pipeline and use of multiple Pareto-quality metrics provide a reproducible template for similar trade-off problems.

major comments (1)
  1. [Abstract and §3 (Method)] The bi-objective search is performed exclusively over subsets of the accuracy-focused top-k list produced by item-based CF (three-stage process in Abstract and §3). Because the candidate pool is fixed, the optimizer cannot surface items ranked lower by the initial CF that might yield superior accuracy-diversity trade-offs; any reported gains could therefore be driven by the restriction itself rather than by the hybrid algorithms. This directly affects the central claim that the hybrids “significantly improve both accuracy and diversity” and requires either an explicit justification that the top-k pool is sufficient or an ablation comparing against an unconstrained search over the full catalog.
minor comments (2)
  1. [Abstract and Results] The abstract states that “some of our proposed algorithms” outperform baselines but does not name which of the four hybrids achieve the gains; this should be stated explicitly in the results section and abstract.
  2. [Experimental Setup] Baseline methods and exact parameter settings for the hybrid algorithms (population size, mutation rates, etc.) are referenced but not tabulated; a clear comparison table would improve reproducibility.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for the constructive feedback on our manuscript. The major comment raises a valid point about the candidate pool restriction in our three-stage pipeline. We address it directly below and will incorporate revisions to strengthen the presentation.

read point-by-point responses

  1. Referee: [Abstract and §3 (Method)] The bi-objective search is performed exclusively over subsets of the accuracy-focused top-k list produced by item-based CF (three-stage process in Abstract and §3). Because the candidate pool is fixed, the optimizer cannot surface items ranked lower by the initial CF that might yield superior accuracy-diversity trade-offs; any reported gains could therefore be driven by the restriction itself rather than by the hybrid algorithms. This directly affects the central claim that the hybrids “significantly improve both accuracy and diversity” and requires either an explicit justification that the top-k pool is sufficient or an ablation comparing against an unconstrained search over the full catalog.

    Authors: We appreciate the referee's observation on the search space restriction. Our three-stage design deliberately limits the bi-objective optimization to subsets of the initial top-k list generated by item-based collaborative filtering. This choice is driven by practical scalability: real-world catalogs often contain hundreds of thousands to millions of items, rendering exhaustive enumeration or optimization over the full item set computationally intractable for multi-objective evolutionary algorithms. The top-k pool (with k typically set to 100–200) acts as a high-recall candidate generator that already encodes accuracy signals, allowing the hybrid MOEAs to focus computational effort on identifying diverse Pareto-optimal subsets of size s ≪ k. This pipeline aligns with established practices in recommender systems literature for balancing quality and efficiency. The reported improvements are therefore attributable to the hybrid algorithms' ability to better navigate the accuracy-diversity trade-off within this focused space, as evidenced by comparisons against both single-objective baselines and other multi-objective methods using comparable setups. To directly address the concern, we will revise §3 to include an explicit justification of the top-k restriction, supported by references to scalability analyses in prior MOEA-based RS work, and will add a brief discussion of this as a methodological limitation with suggestions for future extensions. revision: partial

Circularity Check

0 steps flagged

No circularity; derivation relies on external benchmarks and standard algorithms

full rationale

The paper generates an initial top-k list via item-based collaborative filtering (a standard external method), then applies hybrid variants of established multi-objective algorithms (NNIA, AMOSA, NSGA-II) to search for Pareto-optimal top-s subsets. Performance is assessed via conventional external metrics (accuracy, diversity, novelty, spacing, etc.) on real-world datasets with comparisons to prior methods. No equations, fitted parameters, or self-citations are shown that reduce any claimed improvement to a tautology or input by construction. The approach is self-contained against external benchmarks.

Axiom & Free-Parameter Ledger

0 free parameters · 2 axioms · 0 invented entities

The central claim rests on standard assumptions of collaborative filtering and multi-objective optimization without introducing new fitted parameters or invented entities in the abstract.

axioms (2)
  • domain assumption Accuracy and diversity are conflicting objectives that can be meaningfully traded off via Pareto optimality.
    Invoked in the bi-objective optimization stage described in the abstract.
  • domain assumption Item-based collaborative filtering produces a useful initial top-k candidate set.
    First stage of the three-stage process.

pith-pipeline@v0.9.0 · 5548 in / 1222 out tokens · 37807 ms · 2026-05-10T17:08:39.153475+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

52 extracted references · 52 canonical work pages

  1. [1]

    doi:10.1007/978-1-4899-7637-6_6

    Adomavicius G, Tuzhilin A (2015) Context-Aware Recommender Systems, Springer US, Boston, MA, pp 191--226. doi:10.1007/978-1-4899-7637-6_6

    work page doi:10.1007/978-1-4899-7637-6_6 2015

  2. [2]

    Applied Soft Computing 85:105830

    Almarimi N, Ouni A, Bouktif S, et al (2019) Web service api recommendation for automated mashup creation using multi-objective evolutionary search. Applied Soft Computing 85:105830. doi:https://doi.org/10.1016/j.asoc.2019.105830

    work page doi:10.1016/j.asoc.2019.105830 2019

  3. [3]

    doi:10.1007/978-3-642-45135-5_10

    Avazpour I, Pitakrat T, Grunske L, et al (2014) Dimensions and Metrics for Evaluating Recommendation Systems, Springer Berlin Heidelberg, Berlin, Heidelberg, pp 245--273. doi:10.1007/978-3-642-45135-5_10

    work page doi:10.1007/978-3-642-45135-5_10 2014

  4. [4]

    IEEE Transactions on Evolutionary Computation 12(3):269--283

    Bandyopadhyay S, Saha S, Maulik U, et al (2008) A simulated annealing-based multiobjective optimization algorithm: Amosa. IEEE Transactions on Evolutionary Computation 12(3):269--283. doi:10.1109/TEVC.2007.900837

    work page doi:10.1109/tevc.2007.900837 2008

  5. [5]

    Knowledge-Based Systems 46:109--132

    Bobadilla J, Ortega F, Hernando A, et al (2013) Recommender systems survey. Knowledge-Based Systems 46:109--132. doi:https://doi.org/10.1016/j.knosys.2013.03.012

    work page doi:10.1016/j.knosys.2013.03.012 2013

  6. [6]

    Management Science 31(6):647--656

    Brans JP, Vincke P (1985) Note—a preference ranking organisation method. Management Science 31(6):647--656. doi:10.1287/mnsc.31.6.647

    work page doi:10.1287/mnsc.31.6.647 1985

  7. [7]

    A hybrid recommendation system with many-objective evolutionary algorithm , journal =

    Cai X, Hu Z, Zhao P, et al (2020) A hybrid recommendation system with many-objective evolutionary algorithm. Expert Systems with Applications 159:113648. doi:https://doi.org/10.1016/j.eswa.2020.113648

    work page doi:10.1016/j.eswa.2020.113648 2020

  8. [8]

    Journal of Ambient Intelligence and Humanized Computing 12:443--454

    Chai Z, Li Y, Zhu S (2021) P-moia-rs: a multi-objective optimization and decision-making algorithm for recommendation systems. Journal of Ambient Intelligence and Humanized Computing 12:443--454. doi:10.1007/s12652-020-01997-x

    work page doi:10.1007/s12652-020-01997-x 2021

  9. [9]

    IEEE Access 7:6060--6071

    Chai ZY, Li YL, Han YM, et al (2019) Recommendation system based on singular value decomposition and multi-objective immune optimization. IEEE Access 7:6060--6071. doi:10.1109/ACCESS.2018.2842257

    work page doi:10.1109/access.2018.2842257 2019

  10. [10]

    Journal of Parallel and Distributed Computing 103:53--63

    Cui L, Ou P, Fu X, et al (2017) A novel multi-objective evolutionary algorithm for recommendation systems. Journal of Parallel and Distributed Computing 103:53--63. doi:https://doi.org/10.1016/j.jpdc.2016.10.014, special Issue on Scalable Cyber-Physical Systems

    work page doi:10.1016/j.jpdc.2016.10.014 2017

  11. [11]

    2002 A fast and elitist multiobjective genetic algorithm: NSGA-II.IEEE Transactions on Evolutionary Computation6, 182–197

    Deb K, Pratap A, Agarwal S, et al (2002) A fast and elitist multiobjective genetic algorithm: Nsga-ii. IEEE Transactions on Evolutionary Computation 6(2):182--197. doi:10.1109/4235.996017

    work page doi:10.1109/4235.996017 2002

  12. [12]

    In: The 2013 International Joint Conference on Neural Networks (IJCNN), pp 1--8, doi:10.1109/IJCNN.2013.6707036

    Drugan MM, Nowe A (2013) Designing multi-objective multi-armed bandits algorithms: A study. In: The 2013 International Joint Conference on Neural Networks (IJCNN), pp 1--8, doi:10.1109/IJCNN.2013.6707036

    work page doi:10.1109/ijcnn.2013.6707036 2013

  13. [13]

    Springer Science & Business Media, Berlin

    Ehrgott M (2005) Multicriteria Optimization. Springer Science & Business Media, Berlin

    work page 2005

  14. [14]

    Physica A: Statistical Mechanics and its Applications 424:383--397

    Geng B, Li L, Jiao L, et al (2015) Nnia-rs: A multi-objective optimization based recommender system. Physica A: Statistical Mechanics and its Applications 424:383--397. doi:https://doi.org/10.1016/j.physa.2015.01.007

    work page doi:10.1016/j.physa.2015.01.007 2015

  15. [15]

    Evolutionary Computation 16(2):225--255

    Gong M, Jiao L, Du H, et al (2008) Multiobjective immune algorithm with nondominated neighbor-based selection. Evolutionary Computation 16(2):225--255. doi:10.1162/evco.2008.16.2.225

    work page doi:10.1162/evco.2008.16.2.225 2008

  16. [16]

    In: 2020 3rd International Conference on Advanced Electronic Materials, Computers and Software Engineering (AEMCSE), pp 129--132, doi:10.1109/AEMCSE50948.2020.00034

    Huang S, Liu J, Zhu D, et al (2020) Application of multi-objective evolutionary algorithm in e-commerce recommendation system. In: 2020 3rd International Conference on Advanced Electronic Materials, Computers and Software Engineering (AEMCSE), pp 129--132, doi:10.1109/AEMCSE50948.2020.00034

    work page doi:10.1109/aemcse50948.2020.00034 2020

  17. [17]

    Springer, Berlin

    Hwang CL, Yoon K (1981) Multiple Attributes Decision Making Methods and Applications. Springer, Berlin

    work page 1981

  18. [18]

    Journal of Ambient Intelligence and Humanized Computing 10:3023--3034

    Jiang L, Cheng Y, Yang L, et al (2019) A trust-based collaborative filtering algorithm for e-commerce recommendation system. Journal of Ambient Intelligence and Humanized Computing 10:3023--3034. doi:10.1007/s12652-018-0928-7

    work page doi:10.1007/s12652-018-0928-7 2019

  19. [19]

    Electronics 11(1)

    Ko H, Lee S, Park Y, et al (2022) A survey of recommendation systems: Recommendation models, techniques, and application fields. Electronics 11(1). doi:10.3390/electronics11010141

    work page doi:10.3390/electronics11010141 2022

  20. [20]

    Computer 42(8):30--37

    Koren Y, Bell R, Volinsky C (2009) Matrix factorization techniques for recommender systems. Computer 42(8):30--37. doi:10.1109/MC.2009.263

    work page doi:10.1109/mc.2009.263 2009

  21. [21]

    Knowledge-Based Systems 123:154--162

    Kunaver M, Požrl T (2017) Diversity in recommender systems – a survey. Knowledge-Based Systems 123:154--162. doi:https://doi.org/10.1016/j.knosys.2017.02.009

    work page doi:10.1016/j.knosys.2017.02.009 2017

  22. [22]

    Neurocomputing 246:12--24

    Lacerda A (2017) Multi-objective ranked bandits for recommender systems. Neurocomputing 246:12--24. doi:https://doi.org/10.1016/j.neucom.2016.12.076, brazilian Conference on Intelligent Systems 2015

    work page doi:10.1016/j.neucom.2016.12.076 2017

  23. [23]

    Computational and Applied Mathematics 42:24

    Lotfian E, Mohammadzadeh M (2023) Multi-objective optimization of spatial sampling using a new hybrid amosa\_nsga-ii algorithm. Computational and Applied Mathematics 42:24. doi:10.1007/s40314-022-02161-1

    work page doi:10.1007/s40314-022-02161-1 2023

  24. [24]

    Physics Reports 519(1):1--49

    Lü L, Medo M, Yeung CH, et al (2012) Recommender systems. Physics Reports 519(1):1--49. doi:https://doi.org/10.1016/j.physrep.2012.02.006

    work page doi:10.1016/j.physrep.2012.02.006 2012

  25. [25]

    Neural Computing and Applications 35:5155--5163

    Ma T, Wang X, Zhou F, et al (2023) Research on diversity and accuracy of the recommendation system based on multi-objective optimization. Neural Computing and Applications 35:5155--5163. doi:10.1007/s00521-020-05438-w

    work page doi:10.1007/s00521-020-05438-w 2023

  26. [26]

    Computers & Chemical Engineering 88:157--169

    Maghsoudlou H, Afshar-Nadjafi B, Niaki STA (2016) A multi-objective invasive weeds optimization algorithm for solving multi-skill multi-mode resource constrained project scheduling problem. Computers & Chemical Engineering 88:157--169. doi:https://doi.org/10.1016/j.compchemeng.2016.02.018

    work page doi:10.1016/j.compchemeng.2016.02.018 2016

  27. [27]

    Knowledge-Based Systems 164:348--357

    Malekzadeh Hamedani E, Kaedi M (2019) Recommending the long tail items through personalized diversification. Knowledge-Based Systems 164:348--357. doi:https://doi.org/10.1016/j.knosys.2018.11.004

    work page doi:10.1016/j.knosys.2018.11.004 2019

  28. [28]

    Association for Computing Machinery, New York, NY, USA, p 640–651, doi:10.1145/3604915.3608805

    Michiels L, Vannieuwenhuyze J, Leysen J, et al (2023) How should we measure filter bubbles? a regression model and evidence for online news. Association for Computing Machinery, New York, NY, USA, p 640–651, doi:10.1145/3604915.3608805

    work page doi:10.1145/3604915.3608805 2023

  29. [29]

    In: 2013 IEEE/WIC/ACM International Joint Conferences on Web Intelligence (WI) and Intelligent Agent Technologies (IAT), pp 9--12, doi:10.1109/WI-IAT.2013.141

    Mikeli A, Apostolou D, Despotis D (2013) A multi-criteria recommendation method for interval scaled ratings. In: 2013 IEEE/WIC/ACM International Joint Conferences on Web Intelligence (WI) and Intelligent Agent Technologies (IAT), pp 9--12, doi:10.1109/WI-IAT.2013.141

    work page doi:10.1109/wi-iat.2013.141 2013

  30. [30]

    Association for Computing Machinery, New York, NY, USA, p 11–18, doi:10.1145/1454008.1454012

    Park YJ, Tuzhilin A (2008) The long tail of recommender systems and how to leverage it. Association for Computing Machinery, New York, NY, USA, p 11–18, doi:10.1145/1454008.1454012

    work page doi:10.1145/1454008.1454012 2008

  31. [31]

    doi:10.1007/978-3-540-72079-9_10

    Pazzani MJ, Billsus D (2007) Content-Based Recommendation Systems, Springer Berlin Heidelberg, Berlin, Heidelberg, pp 325--341. doi:10.1007/978-3-540-72079-9_10

    work page doi:10.1007/978-3-540-72079-9_10 2007

  32. [32]

    Artificial Intelligence Review 55:749--800

    Raza S, Ding C (2022) News recommender system: a review of recent progress, challenges, and opportunities. Artificial Intelligence Review 55:749--800. doi:10.1007/s10462-021-10043-x

    work page doi:10.1007/s10462-021-10043-x 2022

  33. [33]

    In: Proceedings of the Sixth ACM Conference on Recommender Systems

    Ribeiro MT, Lacerda A, Veloso A, et al (2012) Pareto-efficient hybridization for multi-objective recommender systems. In: Proceedings of the Sixth ACM Conference on Recommender Systems. Association for Computing Machinery, New York, NY, USA, p 19–26, doi:10.1145/2365952.2365962

    work page doi:10.1145/2365952.2365962 2012

  34. [34]

    ACM Trans Intell Syst Technol 5(4)

    Ribeiro MT, Ziviani N, Moura ESD, et al (2015) Multiobjective pareto-efficient approaches for recommender systems. ACM Trans Intell Syst Technol 5(4). doi:10.1145/2629350

    work page doi:10.1145/2629350 2015

  35. [35]

    Water Resources Management 34:1437--1451

    Saadatpour M (2020) An adaptive surrogate assisted ce-qual-w2 model embedded in hybrid nsga-ii\_amosa algorithm for reservoir water quality and quantity management. Water Resources Management 34:1437--1451. doi:10.1007/s11269-020-02510-x

    work page doi:10.1007/s11269-020-02510-x 2020

  36. [36]

    International Journal of Services Sciences 1(1):83--98

    Saaty TL (2008) Decision making with the analytic hierarchy process. International Journal of Services Sciences 1(1):83--98. doi:10.1504/IJSSCI.2008.017590

    work page doi:10.1504/ijssci.2008.017590 2008

  37. [37]

    In: Proceedings of the 10th International Conference on World Wide Web

    Sarwar B, Karypis G, Konstan J, et al (2001) Item-based collaborative filtering recommendation algorithms. In: Proceedings of the 10th International Conference on World Wide Web. Association for Computing Machinery, New York, NY, USA, p 285–295, doi:10.1145/371920.372071

    work page doi:10.1145/371920.372071 2001

  38. [38]

    In: 2014 IEEE Congress on Evolutionary Computation (CEC), pp 672--679, doi:10.1109/CEC.2014.6900333

    Wang S, Gong M, Ma L, et al (2014) Decomposition based multiobjective evolutionary algorithm for collaborative filtering recommender systems. In: 2014 IEEE Congress on Evolutionary Computation (CEC), pp 672--679, doi:10.1109/CEC.2014.6900333

    work page doi:10.1109/cec.2014.6900333 2014

  39. [39]

    Knowledge-Based Systems 104:145--155

    Wang S, Gong M, Li H, et al (2016) Multi-objective optimization for long tail recommendation. Knowledge-Based Systems 104:145--155. doi:https://doi.org/10.1016/j.knosys.2016.04.018

    work page doi:10.1016/j.knosys.2016.04.018 2016

  40. [40]

    IEEE Transactions on Knowledge and Data Engineering 35(5):4425--4445

    Wu L, He X, Wang X, et al (2023) A survey on accuracy-oriented neural recommendation: From collaborative filtering to information-rich recommendation. IEEE Transactions on Knowledge and Data Engineering 35(5):4425--4445. doi:10.1109/TKDE.2022.3145690

    work page doi:10.1109/tkde.2022.3145690 2023

  41. [41]

    Multi-objective optimization with recommender systems: A systematic review , journal =

    Zaizi FE, Qassimi S, Rakrak S (2023) Multi-objective optimization with recommender systems: A systematic review. Information Systems 117:102233. doi:https://doi.org/10.1016/j.is.2023.102233

    work page doi:10.1016/j.is.2023.102233 2023

  42. [42]

    In: Proceedings of the 2008 ACM Conference on Recommender Systems

    Zhang M, Hurley N (2008) Avoiding monotony: improving the diversity of recommendation lists. In: Proceedings of the 2008 ACM Conference on Recommender Systems. Association for Computing Machinery, New York, NY, USA, p 123–130, doi:10.1145/1454008.1454030

    work page doi:10.1145/1454008.1454030 2008

  43. [43]

    Memetic Computing 10:321--331

    Zhao X, Ma Z, Zhang Z (2018) A novel recommendation system in location-based social networks using distributed elm. Memetic Computing 10:321--331. doi:10.1007/s12293-017-0227-4

    work page doi:10.1007/s12293-017-0227-4 2018

  44. [44]

    IEEE Transactions on Knowledge and Data Engineering 36(11):6889--6907

    Zhao Z, Fan W, Li J, et al (2024) Recommender systems in the era of large language models (llms). IEEE Transactions on Knowledge and Data Engineering 36(11):6889--6907. doi:10.1109/TKDE.2024.3392335

    work page doi:10.1109/tkde.2024.3392335 2024

  45. [45]

    Association for Computing Machinery, New York, NY, USA, p 4098–4099, doi:10.1145/3447548.3470788

    Zheng Y, Wang DX (2021) Multi-objective recommendations. Association for Computing Machinery, New York, NY, USA, p 4098–4099, doi:10.1145/3447548.3470788

    work page doi:10.1145/3447548.3470788 2021

  46. [46]

    Neurocomputing 474:141--153

    Zheng Y, Wang DX (2022) A survey of recommender systems with multi-objective optimization. Neurocomputing 474:141--153. doi:https://doi.org/10.1016/j.neucom.2021.11.041

    work page doi:10.1016/j.neucom.2021.11.041 2022

  47. [47]

    PLOS ONE 8(8):1--11

    Zhou Y, Lü L, Liu W, et al (2013) The power of ground user in recommender systems. PLOS ONE 8(8):1--11. doi:10.1371/journal.pone.0070094

    work page doi:10.1371/journal.pone.0070094 2013

  48. [48]

    In: Eiben AE, B \"a ck T, Schoenauer M, et al (eds) Parallel Problem Solving from Nature --- PPSN V

    Zitzler E, Thiele L (1998) Multiobjective optimization using evolutionary algorithms --- a comparative case study. In: Eiben AE, B \"a ck T, Schoenauer M, et al (eds) Parallel Problem Solving from Nature --- PPSN V. Springer Berlin Heidelberg, Berlin, Heidelberg, pp 292--301

    work page 1998

  49. [49]

    Neurocomputing 452:716--727

    Zou F, Chen D, Xu Q, et al (2021) A two-stage personalized recommendation based on multi-objective teaching–learning-based optimization with decomposition. Neurocomputing 452:716--727. doi:https://doi.org/10.1016/j.neucom.2020.08.080

    work page doi:10.1016/j.neucom.2020.08.080 2021

  50. [50]

    IEEE Computational Intelligence Magazine 10(1):52--62

    Zuo Y, Gong M, Zeng J, et al (2015) Personalized recommendation based on evolutionary multi-objective optimization [research frontier]. IEEE Computational Intelligence Magazine 10(1):52--62. doi:10.1109/MCI.2014.2369894

    work page doi:10.1109/mci.2014.2369894 2015

  51. [51]

    sn-basic.bst

    FUNCTION identify.basic.version "sn-basic.bst" " [2024/07/19 v1.1 bibliography style]" * top ENTRY address archive author booktitle chapter doi edition editor eid eprint howpublished institution journal key keywords month note number organization pages publisher school series title type url volume year archivePrefix primaryClass adsurl adsnote version lab...

    work page 2024

  52. [52]

    write newline

    " write newline "" before.all 'output.state := FUNCTION add.period duplicate empty 'skip "." * add.blank if FUNCTION if.digit duplicate "0" = swap duplicate "1" = swap duplicate "2" = swap duplicate "3" = swap duplicate "4" = swap duplicate "5" = swap duplicate "6" = swap duplicate "7" = swap duplicate "8" = swap "9" = or or or or or or or or or FUNCTION ...

    work page