KATRec: Knowledge Aware aTtentive Sequential Recommendations release_j3jcvjacx5flhjrusrxi4dnuky

by Mehrnaz Amjadi, Danial Mohseni-Taheri, Theja Tulabandhula

Entity Metadata (schema)

abstracts[] {'sha1': 'd48c605b7a28ef568814a6b8cd43fb41956d63ee', 'content': "Sequential recommendation systems model dynamic preferences of users based on\ntheir historical interactions with platforms. Despite recent progress, modeling\nshort-term and long-term behavior of users in such systems is nontrivial and\nchallenging. To address this, we present a solution enhanced by a knowledge\ngraph called KATRec (Knowledge Aware aTtentive sequential Recommendations).\nKATRec learns the short and long-term interests of users by modeling their\nsequence of interacted items and leveraging pre-existing side information\nthrough a knowledge graph attention network. Our novel knowledge graph-enhanced\nsequential recommender contains item multi-relations at the entity-level and\nusers' dynamic sequences at the item-level. KATRec improves item representation\nlearning by considering higher-order connections and incorporating them in user\npreference representation while recommending the next item. Experiments on\nthree public datasets show that KATRec outperforms state-of-the-art\nrecommendation models and demonstrates the importance of modeling both temporal\nand side information to achieve high-quality recommendations.", 'mimetype': 'text/plain', 'lang': 'en'}
container
container_id
contribs[] {'index': 0, 'creator_id': None, 'creator': None, 'raw_name': 'Mehrnaz Amjadi', 'given_name': None, 'surname': None, 'role': 'author', 'raw_affiliation': None, 'extra': None}
{'index': 1, 'creator_id': None, 'creator': None, 'raw_name': 'Danial Mohseni-Taheri', 'given_name': None, 'surname': None, 'role': 'author', 'raw_affiliation': None, 'extra': None}
{'index': 2, 'creator_id': None, 'creator': None, 'raw_name': 'Theja Tulabandhula', 'given_name': None, 'surname': None, 'role': 'author', 'raw_affiliation': None, 'extra': None}
ext_ids {'doi': None, 'wikidata_qid': None, 'isbn13': None, 'pmid': None, 'pmcid': None, 'core': None, 'arxiv': '2012.03323v1', 'jstor': None, 'ark': None, 'mag': None, 'doaj': None, 'dblp': None, 'oai': None, 'hdl': None}
files[] {'state': 'active', 'ident': 'quhuvtmiqfahjmccl6ktk3szou', 'revision': '104467bd-b319-415f-a4bf-de0a635b50d0', 'redirect': None, 'extra': None, 'edit_extra': None, 'size': 485735, 'md5': 'a4441e8ac34da4d94f7e83535d2947ea', 'sha1': '882515808575c16d7bdba74374ac0cf0a3e5b64f', 'sha256': '5fed3fbef2884cece890efe0f8ca8fdf0cd1575eeefa1a778caf808c20b17d27', 'urls': [{'url': 'https://arxiv.org/pdf/2012.03323v1.pdf', 'rel': 'repository'}, {'url': 'https://web.archive.org/web/20201209055738/https://arxiv.org/pdf/2012.03323v1.pdf', 'rel': 'webarchive'}], 'mimetype': 'application/pdf', 'content_scope': None, 'release_ids': ['j3jcvjacx5flhjrusrxi4dnuky'], 'releases': None}
filesets []
issue
language en
license_slug ARXIV-1.0
number
original_title
pages
publisher
refs []
release_date 2020-12-06
release_stage submitted
release_type article
release_year 2020
subtitle
title KATRec: Knowledge Aware aTtentive Sequential Recommendations
version v1
volume
webcaptures []
withdrawn_date
withdrawn_status
withdrawn_year
work_id nbnxkgcvj5hddfk3kdusqbev7u
As JSON via API

Extra Metadata (raw JSON)

arxiv.base_id 2012.03323
arxiv.categories ['cs.IR']