Conference paper Open Access

Multi-Modal Adversarial Autoencoders for Recommendations of Citations and Subject Labels

Galke, Lukas; Mai, Florian; Vagliano, Iacopo; Scherp, Ansgar


JSON-LD (schema.org) Export

{
  "inLanguage": {
    "alternateName": "eng", 
    "@type": "Language", 
    "name": "English"
  }, 
  "description": "<p>We present multi-modal adversarial autoencoders for recommendation and evaluate them on two different tasks: citation recommendation and subject label recommendation.&nbsp; We analyze the effects of adversarial regularization, sparsity, and different input modalities.&nbsp; By conducting 408 experiments, we show that adversarial regularization consistently improves the performance of autoencoders for recommendation.&nbsp; We demonstrate, however, that the two tasks differ in the semantics of item co-occurrence in the sense that item co-occurrence resembles relatedness in case of citations, yet implies diversity in case of subject labels.&nbsp; Our results reveal that supplying the partial item set as input is only helpful, when item co-occurrence resembles relatedness.&nbsp; When facing a new recommendation task it is therefore crucial to consider the semantics of item co-occurrence for the choice of an appropriate model.</p>", 
  "license": "http://creativecommons.org/licenses/by/4.0/legalcode", 
  "creator": [
    {
      "affiliation": "Kiel University", 
      "@id": "https://orcid.org/0000-0001-6124-1092", 
      "@type": "Person", 
      "name": "Galke, Lukas"
    }, 
    {
      "affiliation": "Kiel University", 
      "@type": "Person", 
      "name": "Mai, Florian"
    }, 
    {
      "affiliation": "ZBW -- Leibniz Information Centre for Economics", 
      "@id": "https://orcid.org/0000-0002-3066-9464", 
      "@type": "Person", 
      "name": "Vagliano, Iacopo"
    }, 
    {
      "affiliation": "Kiel University", 
      "@id": "https://orcid.org/0000-0002-2653-9245", 
      "@type": "Person", 
      "name": "Scherp, Ansgar"
    }
  ], 
  "headline": "Multi-Modal Adversarial Autoencoders for Recommendations of Citations and Subject Labels", 
  "image": "https://zenodo.org/static/img/logos/zenodo-gradient-round.svg", 
  "datePublished": "2018-07-11", 
  "url": "https://zenodo.org/record/1313577", 
  "keywords": [
    "Recommender Systems", 
    "Neural Networks", 
    "Learning from implicit feedback", 
    "Adversarial Autoencoders", 
    "Multi-modal", 
    "Sparsity"
  ], 
  "@context": "https://schema.org/", 
  "identifier": "https://doi.org/10.1145/3209219.3209236", 
  "@id": "https://doi.org/10.1145/3209219.3209236", 
  "@type": "ScholarlyArticle", 
  "name": "Multi-Modal Adversarial Autoencoders for Recommendations of Citations and Subject Labels"
}
60
74
views
downloads
Views 60
Downloads 74
Data volume 55.3 MB
Unique views 57
Unique downloads 71

Share

Cite as