Matches in SemOpenAlex for { <https://semopenalex.org/work/W4320459058> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W4320459058 abstract "Recommender system based on historical user-item interactions is of vital importance for web-based services. However, the observed data used to train the recommender model suffers from severe bias issues. Practically, the item frequency distribution of the dataset is a highly skewed power-law distribution. Interactions of a small fraction of head items account for almost the whole training data. The normal training paradigm from such biased data tends to repetitively generate recommendations from the head items, which further exacerbates the biases and affects the exploration of potentially interesting items from the niche set. In this work, we innovatively explore the central theme of recommendation debiasing from an item cluster-wise multi-objective optimization perspective. Aiming to balance the learning on various item clusters that differ in popularity during the training process, we propose a model-agnostic framework namely Item Cluster-Wise Pareto-Efficient Recommendation (ICPE). In detail, we define our item cluster-wise optimization target as the recommender model should balance all item clusters that differ in popularity, thus we set the model learning on each item cluster as a unique optimization objective. To achieve this goal, we first explore items' popularity levels from a novel causal reasoning perspective. Then, we devise popularity discrepancy-based bisecting clustering to separate the item clusters. Next, we adaptively find the overall harmonious gradient direction for cluster-wise optimization objectives from a Pareto-efficient solver. Finally, in the prediction stage, we perform counterfactual inference to further eliminate the impact of global propensity. Extensive experimental results verify the superiorities of ICPE on overall recommendation performance and biases elimination." @default.
- W4320459058 created "2023-02-14" @default.
- W4320459058 creator A5043188795 @default.
- W4320459058 creator A5046454314 @default.
- W4320459058 creator A5047124158 @default.
- W4320459058 creator A5069298618 @default.
- W4320459058 creator A5076083959 @default.
- W4320459058 date "2021-09-27" @default.
- W4320459058 modified "2023-09-26" @default.
- W4320459058 title "ICPE: An Item Cluster-Wise Pareto-Efficient Framework for Recommendation Debiasing" @default.
- W4320459058 doi "https://doi.org/10.48550/arxiv.2109.12887" @default.
- W4320459058 hasPublicationYear "2021" @default.
- W4320459058 type Work @default.
- W4320459058 citedByCount "0" @default.
- W4320459058 crossrefType "posted-content" @default.
- W4320459058 hasAuthorship W4320459058A5043188795 @default.
- W4320459058 hasAuthorship W4320459058A5046454314 @default.
- W4320459058 hasAuthorship W4320459058A5047124158 @default.
- W4320459058 hasAuthorship W4320459058A5069298618 @default.
- W4320459058 hasAuthorship W4320459058A5076083959 @default.
- W4320459058 hasBestOaLocation W43204590581 @default.
- W4320459058 hasConcept C119857082 @default.
- W4320459058 hasConcept C124101348 @default.
- W4320459058 hasConcept C126255220 @default.
- W4320459058 hasConcept C12713177 @default.
- W4320459058 hasConcept C137635306 @default.
- W4320459058 hasConcept C154945302 @default.
- W4320459058 hasConcept C15744967 @default.
- W4320459058 hasConcept C177264268 @default.
- W4320459058 hasConcept C188147891 @default.
- W4320459058 hasConcept C199360897 @default.
- W4320459058 hasConcept C23123220 @default.
- W4320459058 hasConcept C2779458634 @default.
- W4320459058 hasConcept C2780586970 @default.
- W4320459058 hasConcept C33923547 @default.
- W4320459058 hasConcept C41008148 @default.
- W4320459058 hasConcept C557471498 @default.
- W4320459058 hasConcept C73555534 @default.
- W4320459058 hasConcept C77805123 @default.
- W4320459058 hasConceptScore W4320459058C119857082 @default.
- W4320459058 hasConceptScore W4320459058C124101348 @default.
- W4320459058 hasConceptScore W4320459058C126255220 @default.
- W4320459058 hasConceptScore W4320459058C12713177 @default.
- W4320459058 hasConceptScore W4320459058C137635306 @default.
- W4320459058 hasConceptScore W4320459058C154945302 @default.
- W4320459058 hasConceptScore W4320459058C15744967 @default.
- W4320459058 hasConceptScore W4320459058C177264268 @default.
- W4320459058 hasConceptScore W4320459058C188147891 @default.
- W4320459058 hasConceptScore W4320459058C199360897 @default.
- W4320459058 hasConceptScore W4320459058C23123220 @default.
- W4320459058 hasConceptScore W4320459058C2779458634 @default.
- W4320459058 hasConceptScore W4320459058C2780586970 @default.
- W4320459058 hasConceptScore W4320459058C33923547 @default.
- W4320459058 hasConceptScore W4320459058C41008148 @default.
- W4320459058 hasConceptScore W4320459058C557471498 @default.
- W4320459058 hasConceptScore W4320459058C73555534 @default.
- W4320459058 hasConceptScore W4320459058C77805123 @default.
- W4320459058 hasLocation W43204590581 @default.
- W4320459058 hasOpenAccess W4320459058 @default.
- W4320459058 hasPrimaryLocation W43204590581 @default.
- W4320459058 hasRelatedWork W2133515697 @default.
- W4320459058 hasRelatedWork W3115418111 @default.
- W4320459058 hasRelatedWork W3115685629 @default.
- W4320459058 hasRelatedWork W4206478093 @default.
- W4320459058 hasRelatedWork W4284965791 @default.
- W4320459058 hasRelatedWork W4287977863 @default.
- W4320459058 hasRelatedWork W4293302374 @default.
- W4320459058 hasRelatedWork W4308161774 @default.
- W4320459058 hasRelatedWork W4318813580 @default.
- W4320459058 hasRelatedWork W4376122795 @default.
- W4320459058 isParatext "false" @default.
- W4320459058 isRetracted "false" @default.
- W4320459058 workType "article" @default.