FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4212951676> ?p ?o ?g. }

• W4212951676 abstract "The issue of fairness in recommendation is becoming increasingly essential as Recommender Systems (RS) touch and influence more and more people in their daily lives. In fairness-aware recommendation, most of the existing algorithmic approaches mainly aim at solving a constrained optimization problem by imposing a constraint on the level of fairness while optimizing the main recommendation objective, e.g., click through rate (CTR). While this alleviates the impact of unfair recommendations, the expected return of an approach may significantly compromise the recommendation accuracy due to the inherent trade-off between fairness and utility. This motivates us to deal with these conflicting objectives and explore the optimal trade-off between them in recommendation. One conspicuous approach is to seek aPareto efficient/optimal solution to guarantee optimal compromises between utility and fairness. Moreover, considering the needs of real-world e-commerce platforms, it would be more desirable if we can generalize the wholePareto Frontier, so that the decision-makers can specify any preference of one objective over another based on their current business needs. Therefore, in this work, we propose a fairness-aware recommendation framework usingmulti-objective reinforcement learning (MORL), called MoFIR (pronounced more fair ''), which is able to learn a single parametric representation for optimal recommendation policies over the space of all possible preferences. Specially, we modify traditional Deep Deterministic Policy Gradient (DDPG) by introducingconditioned network (CN) into it, which conditions the networks directly on these preferences and outputs Q-value-vectors. Experiments on several real-world recommendation datasets verify the superiority of our framework on both fairness metrics and recommendation measures when compared with all other baselines. We also extract the approximate Pareto Frontier on real-world datasets generated by MoFIR and compare to state-of-the-art fairness methods." @default.
• W4212951676 created "2022-02-24" @default.
• W4212951676 creator A5020526977 @default.
• W4212951676 creator A5039197163 @default.
• W4212951676 creator A5061114236 @default.
• W4212951676 creator A5061512142 @default.
• W4212951676 creator A5083702071 @default.
• W4212951676 creator A5087294988 @default.
• W4212951676 creator A5089041560 @default.
• W4212951676 date "2022-02-11" @default.
• W4212951676 modified "2023-10-03" @default.
• W4212951676 title "Toward Pareto Efficient Fairness-Utility Trade-off in Recommendation through Reinforcement Learning" @default.
• W4212951676 cites W2033009633 @default.
• W4212951676 cites W2048531216 @default.
• W4212951676 cites W2049670925 @default.
• W4212951676 cites W2054141820 @default.
• W4212951676 cites W2094176536 @default.
• W4212951676 cites W2113885898 @default.
• W4212951676 cites W2117911558 @default.
• W4212951676 cites W2137063737 @default.
• W4212951676 cites W2748058847 @default.
• W4212951676 cites W2787991113 @default.
• W4212951676 cites W2788295351 @default.
• W4212951676 cites W2902572901 @default.
• W4212951676 cites W2908826212 @default.
• W4212951676 cites W2945488061 @default.
• W4212951676 cites W2950173087 @default.
• W4212951676 cites W2950260856 @default.
• W4212951676 cites W2963189767 @default.
• W4212951676 cites W2963619374 @default.
• W4212951676 cites W2972510393 @default.
• W4212951676 cites W3035523484 @default.
• W4212951676 cites W3100278010 @default.
• W4212951676 cites W3100521056 @default.
• W4212951676 cites W3104733330 @default.
• W4212951676 cites W3116873649 @default.
• W4212951676 cites W3153182568 @default.
• W4212951676 cites W3153675609 @default.
• W4212951676 cites W3156662033 @default.
• W4212951676 cites W3163155381 @default.
• W4212951676 cites W3179526152 @default.
• W4212951676 cites W3181882572 @default.
• W4212951676 cites W3210519732 @default.
• W4212951676 doi "https://doi.org/10.1145/3488560.3498487" @default.
• W4212951676 hasPublicationYear "2022" @default.
• W4212951676 type Work @default.
• W4212951676 citedByCount "15" @default.
• W4212951676 countsByYear W42129516762022 @default.
• W4212951676 countsByYear W42129516762023 @default.
• W4212951676 crossrefType "proceedings-article" @default.
• W4212951676 hasAuthorship W4212951676A5020526977 @default.
• W4212951676 hasAuthorship W4212951676A5039197163 @default.
• W4212951676 hasAuthorship W4212951676A5061114236 @default.
• W4212951676 hasAuthorship W4212951676A5061512142 @default.
• W4212951676 hasAuthorship W4212951676A5083702071 @default.
• W4212951676 hasAuthorship W4212951676A5087294988 @default.
• W4212951676 hasAuthorship W4212951676A5089041560 @default.
• W4212951676 hasBestOaLocation W42129516762 @default.
• W4212951676 hasConcept C111919701 @default.
• W4212951676 hasConcept C119857082 @default.
• W4212951676 hasConcept C126255220 @default.
• W4212951676 hasConcept C127413603 @default.
• W4212951676 hasConcept C137635306 @default.
• W4212951676 hasConcept C144024400 @default.
• W4212951676 hasConcept C154945302 @default.
• W4212951676 hasConcept C162324750 @default.
• W4212951676 hasConcept C175444787 @default.
• W4212951676 hasConcept C2776036281 @default.
• W4212951676 hasConcept C2778572836 @default.
• W4212951676 hasConcept C2781249084 @default.
• W4212951676 hasConcept C33923547 @default.
• W4212951676 hasConcept C36289849 @default.
• W4212951676 hasConcept C41008148 @default.
• W4212951676 hasConcept C46355384 @default.
• W4212951676 hasConcept C557471498 @default.
• W4212951676 hasConcept C78519656 @default.
• W4212951676 hasConcept C97541855 @default.
• W4212951676 hasConceptScore W4212951676C111919701 @default.
• W4212951676 hasConceptScore W4212951676C119857082 @default.
• W4212951676 hasConceptScore W4212951676C126255220 @default.
• W4212951676 hasConceptScore W4212951676C127413603 @default.
• W4212951676 hasConceptScore W4212951676C137635306 @default.
• W4212951676 hasConceptScore W4212951676C144024400 @default.
• W4212951676 hasConceptScore W4212951676C154945302 @default.
• W4212951676 hasConceptScore W4212951676C162324750 @default.
• W4212951676 hasConceptScore W4212951676C175444787 @default.
• W4212951676 hasConceptScore W4212951676C2776036281 @default.
• W4212951676 hasConceptScore W4212951676C2778572836 @default.
• W4212951676 hasConceptScore W4212951676C2781249084 @default.
• W4212951676 hasConceptScore W4212951676C33923547 @default.
• W4212951676 hasConceptScore W4212951676C36289849 @default.
• W4212951676 hasConceptScore W4212951676C41008148 @default.
• W4212951676 hasConceptScore W4212951676C46355384 @default.
• W4212951676 hasConceptScore W4212951676C557471498 @default.
• W4212951676 hasConceptScore W4212951676C78519656 @default.
• W4212951676 hasConceptScore W4212951676C97541855 @default.
• W4212951676 hasLocation W42129516761 @default.
• W4212951676 hasLocation W42129516762 @default.
• W4212951676 hasOpenAccess W4212951676 @default.
• W4212951676 hasPrimaryLocation W42129516761 @default.

• next