Multi-objective Ranking via Constrained Optimization

Momma, Michinari; Garakani, Alireza Bagheri; Ma, Nanxun; Sun, Yi

doi:10.1145/3366424.3382723

Cited by 4 publications

(4 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, a noteworthy observation is that these research investigations have generally omitted the provision of accompanying code packages, limiting the reproducibility of their findings. This observation holds true for studies such as those conducted by [4,[9][10][11]. Notably, within the relatively recent landscape of LTR research, there exists a scarcity of research tools dedicated to the Multiobjective Evolutionary Strategy.…”

Section: Literature Studymentioning

confidence: 95%

An Innovative Hybrid-Box tool for Ranking Preferences using Multi-objective Evolutionary Gradient Strategies

Ibrahim

2024

Preprint

View full text Add to dashboard Cite

Optimizing data features plays a crucial role in simplifying the process of selecting instances and analyzing datasets, especially when dealing with ranking problems. In scenarios such as ranking instances in medical diagnosis, search engine optimization, and information retrieval, there is a need for models that can rank data instances based on the significance of their features within the datasets. This paper provides a hybrid-box tool which is an efficient Multiobjective computational intelligence technique that generates ranking models by utilizing training and validation datasets. These models are then assessed using unseen test data to produce the predictive results. This tool uses a Multi-objective (1+1)-Evolutionary Gradient Strategy algorithm with a novel gradient methodology for adapting the mutation step-size. Furthermore, it uses five objective functions besides the mutation hybridizing by four probability distributions as random number generators. This tool is a novel technique in the continuous optimization research domain for ranking data instances. Regardless of the hidden details during the evolving procedure, it provides the best-evolved ranking model at the end of each run. This makes the tool is hybrid between Black and White Box tools.

show abstract

Section: Literature Studymentioning

confidence: 95%

An Innovative Hybrid-Box tool for Ranking Preferences using Multi-objective Evolutionary Gradient Strategies

Ibrahim

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Tail queries (e.g. a query never seen before) were strictly not covered in the We use the constraint-based optimization algorithm, AL-LambdaMART (Momma et al, 2020), for the multi-objective formulation:…”

Section: Objective For Optimizationmentioning

confidence: 99%

“…In our problem we assume two objectives -relevance quality and revenue -and our modeling goal is to maximize relevance quality [min s C p (s)] while remaining at least flat on revenue relative to the existing production model [C s (s) ≤ b]. For the latter, the upperbound value b is set accordingly to achieve this goal using the approach outlined in (Momma et al, 2020). The motivation for having both objectives, despite being generally aligned, is that relevance quality may be one of several factors important for a customer's shopping mission.…”

Section: Objective For Optimizationmentioning

confidence: 99%

Improving Relevance Quality in Product Search using High-Precision Query-Product Semantic Similarity

Garakani¹,

Yang²,

Hua³

et al. 2022

Proceedings of the Fifth Workshop on E-Commerce and NLP (ECNLP 5)

Self Cite

View full text Add to dashboard Cite

Ensuring relevance quality in product search is a critical task as it impacts the customer's ability to find intended products in the short-term as well as the general perception and trust of the e-commerce system in the long term. In this work we leverage a high-precision crossencoder BERT model for semantic similarity between customer query and products and survey its effectiveness for three ranking applications where offline-generated scores could be used: (1) as an offline metric for estimating relevance quality impact, (2) as a re-ranking feature covering head/torso queries, and (3) as a training objective for optimization. We present results on effectiveness of this strategy for the large e-commerce setting, which has general applicability for choice of other high-precision models and tasks in ranking.

show abstract

“…Each query-url pair is represented by a 136 dimensional feature vector, and 5-level relevance judgment (Rel) is given as the original level. To construct multiple labels, we followed [26], and used four 3 of its 136 features as additional relevance labels that are removed when training to avoid target leak. We selected all 10 pairs of labels for bi-ojective cases.…”

Section: Datasets and Experimental Settingsmentioning

confidence: 99%

Multi-Label Learning to Rank through Multi-Objective Optimization

Mahapatra¹,

Dong²,

Chen³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Learning to Rank (LTR) technique is ubiquitous in the Information Retrieval system nowadays, especially in the Search Ranking application. The query-item relevance labels typically used to train the ranking model are often noisy measurements of human behavior, e.g., product rating for product search. The coarse measurements make the ground truth ranking non-unique with respect to a single relevance criterion. To resolve ambiguity, it is desirable to train a model using many relevance criteria, giving rise to Multi-Label LTR (MLLTR). Moreover, it formulates multiple goals that may be conflicting yet important to optimize for simultaneously, e.g., in product search, a ranking model can be trained based on product quality and purchase likelihood to increase revenue. In this research, we leverage the Multi-Objective Optimization (MOO) aspect of the MLLTR problem and employ recently developed MOO algorithms to solve it. Specifically, we propose a general framework where the information from labels can be combined in a variety of ways to meaningfully characterize the trade-off among the goals. Our framework allows for any gradient based MOO algorithm to be used for solving the MLLTR problem. We test the proposed framework on two publicly available LTR datasets and one e-commerce dataset to show its efficacy. IntroductionResearch in Learning to Rank (LTR) has exploded in the last decade. It can be attributed to the increasing availability of labeled data for query-item relevance, either through manually labeling or tracking user behavior. In LTR, a scoring function is trained to score the retrieved items for ranking. Originally, LTR was developed to use only one relevance criterion for training. However, owing to the limitations of such uni-dimensional approach, e.g., subjectivity and noise in relevance articulation, inability to incorporate multiple goals, a multi-dimensional approach for relevance is adopted in Multi-Label Learning to Rank (MLLTR) [1]. The multidimensional aspect of MLLTR poses a fundamental challenge: different relevance criteria can be conflicting. For example, in web search, two conflicting criteria could be considering the user-history and increasing serendipitous items in the top results. Due to this conflict, it is virtually infeasible to find a scoring function that simultaneously optimizes for all relevance criteria, thus requires a trade-off among them.

show abstract

Multi-objective Ranking via Constrained Optimization

Cited by 4 publications

References 3 publications

An Innovative Hybrid-Box tool for Ranking Preferences using Multi-objective Evolutionary Gradient Strategies

An Innovative Hybrid-Box tool for Ranking Preferences using Multi-objective Evolutionary Gradient Strategies

Improving Relevance Quality in Product Search using High-Precision Query-Product Semantic Similarity

Multi-Label Learning to Rank through Multi-Objective Optimization

Contact Info

Product

Resources

About