Personalized retrieval seeks to retrieve items relevant to a user event (e.g. a page visit or a query) that are adapted to the user\u2019s personal preferences. For example, two users who happen to perform the same event such as visiting the same product page or asking the same query should receive potentially distinct recommendations adapted to their individual tastes. Personalization is seldom attempted over catalogs of millions of items since the cost of existing personalization routines scale linearly in the number of candidate items. For example, performing two-sided personalized retrieval (with both event and item embeddings personalized to the user) incurs prohibitive storage and compute costs. Instead, it is common to use non-personalized retrieval to obtain a small shortlist of items over which personalized re-ranking can be done quickly. Despite being scalable, this strategy risks losing items uniquely relevant to a user that fail to get shortlisted during non-personalized retrieval. This paper bridges this gap by developing the XPERT algorithm that identifies a form of two-sided personalization that can be scalably implemented over millions of items and hundreds of millions of users. Key to overcoming the computational challenges of personalized retrieval is a novel concept of morph operators that can be used with arbitrary encoder architectures, completely avoids the steep memory overheads of two-sided personalization, provides millisecond-time inference and offers multi-intent retrieval. On multiple public and proprietary datasets, XPERT offered upto 5% superior recall and AUC than state-of-the-art techniques. Code for XPERT is available at https:\/\/github.com\/personalizedretrieval\/xpert.<\/p>\n","protected":false},"excerpt":{"rendered":"
Personalized retrieval seeks to retrieve items relevant to a user event (e.g. a page visit or a query) that are adapted to the user\u2019s personal preferences. For example, two users who happen to perform the same event such as visiting the same product page or asking the same query should receive potentially distinct recommendations adapted […]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","footnotes":""},"msr-content-type":[3],"msr-research-highlight":[],"research-area":[13561,13556,13555],"msr-publication-type":[193716],"msr-product-type":[],"msr-focus-area":[],"msr-platform":[],"msr-download-source":[],"msr-locale":[268875],"msr-post-option":[],"msr-field-of-study":[],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-968232","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-algorithms","msr-research-area-artificial-intelligence","msr-research-area-search-information-retrieval","msr-locale-en_us"],"msr_publishername":"","msr_edition":"","msr_affiliation":"","msr_published_date":"2023-7-1","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"","msr_pages_string":"","msr_chapter":"","msr_isbn":"","msr_journal":"","msr_volume":"","msr_number":"","msr_editors":"","msr_series":"","msr_issue":"","msr_organization":"","msr_how_published":"","msr_notes":"","msr_highlight_text":"","msr_release_tracker_id":"","msr_original_fields_of_study":"","msr_download_urls":"","msr_external_url":"","msr_secondary_video_url":"","msr_longbiography":"","msr_microsoftintellectualproperty":1,"msr_main_download":"","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":[{"type":"url","viewUrl":"false","id":"false","title":"http:\/\/manikvarma.org\/pubs\/vemuri23.pdf","label_id":"243109","label":0}],"msr_related_uploader":"","msr_attachments":[],"msr-author-ordering":[{"type":"text","value":"Hemanth Vemuri","user_id":0,"rest_url":false},{"type":"guest","value":"sheshansh-agrawal","user_id":812950,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=sheshansh-agrawal"},{"type":"user_nicename","value":"Shivam Mittal","user_id":41125,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Shivam Mittal"},{"type":"guest","value":"deepak-saini","user_id":795476,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=deepak-saini"},{"type":"text","value":"Akshay Soni","user_id":0,"rest_url":false},{"type":"text","value":"Abhinav V. Sambasivan","user_id":0,"rest_url":false},{"type":"text","value":"Wenhao Lu","user_id":0,"rest_url":false},{"type":"text","value":"Yajun Wang","user_id":0,"rest_url":false},{"type":"text","value":"Mehul Parsana","user_id":0,"rest_url":false},{"type":"text","value":"Purushottam Kar","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Manik Varma","user_id":32791,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Manik Varma"}],"msr_impact_theme":[],"msr_research_lab":[],"msr_event":[],"msr_group":[144940],"msr_project":[],"publication":[],"video":[],"download":[],"msr_publication_type":"inproceedings","related_content":[],"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/968232"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-research-item"}],"version-history":[{"count":2,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/968232\/revisions"}],"predecessor-version":[{"id":968259,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/968232\/revisions\/968259"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=968232"}],"wp:term":[{"taxonomy":"msr-content-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-content-type?post=968232"},{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=968232"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=968232"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=968232"},{"taxonomy":"msr-product-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-product-type?post=968232"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=968232"},{"taxonomy":"msr-platform","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-platform?post=968232"},{"taxonomy":"msr-download-source","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-download-source?post=968232"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=968232"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=968232"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=968232"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=968232"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=968232"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=968232"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=968232"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}