Deep Learning for Recommender Systems

The Data Science Chair develops new methods to recommend items to users to enhance their overall user experience in a variety of application scenarios. For example, we help users to find relevant products to buy or users of our social bookmarking system BibSonomy to annotate websites and publication with keywords (tags). In this context we leverage various information like navigation paths, user behavior or buying behavior. We utilize different machine learning algorithms, including deep learning, for our recommendation methods. To validate some of our methods, we can deploy and test our methods in our live system BibSonomy, which is run and developed by the Data Science Chair.

Projects

We are currently working on the following projects:

Publications

Here is a list of selected publications. You can find the full list here.

A Case Study on Sampling Strategies for Evaluating Neural Sequential Item Recommendation Models Dallmann, Alexander; Zoller, Daniel; Hotho, Andreas in Fifteenth {ACM} Conference on Recommender Systems (2021).
- [ BibTeX ]
- [ DOI ]
- [ Download ]
@inproceedings{dallmann2021study, author = {Dallmann, Alexander and Zoller, Daniel and Hotho, Andreas}, booktitle = {Fifteenth {ACM} Conference on Recommender Systems}, keywords = {from:dallmann}, month = {sep}, publisher = {{ACM}}, title = {A Case Study on Sampling Strategies for Evaluating Neural Sequential Item Recommendation Models}, year = 2021 }
Comparison of Transformer-Based Sequential Product Recommendation Models for the Coveo Data Challenge Fischer, Elisabeth; Zoller, Daniel; Hotho, Andreas in SIGIR Workshop On eCommerce (2021).
- [ BibTeX ]
- [ Download ]
@article{fischer2021comparison, author = {Fischer, Elisabeth and Zoller, Daniel and Hotho, Andreas}, journal = {SIGIR Workshop On eCommerce}, keywords = {transformer}, month = {July}, title = {Comparison of Transformer-Based Sequential Product Recommendation Models for the Coveo Data Challenge}, year = 2021 }
Integrating Keywords into BERT4Rec for Sequential Recommendation Fischer, Elisabeth; Zoller, Daniel; Dallmann, Alexander; Hotho, Andreas in KI 2020: Advances in Artificial Intelligence (2020).
- [ BibTeX ]
- [ Download ]
@inproceedings{fischer2020integrating, author = {Fischer, Elisabeth and Zoller, Daniel and Dallmann, Alexander and Hotho, Andreas}, booktitle = {KI 2020: Advances in Artificial Intelligence}, keywords = {sequential}, title = {Integrating Keywords into BERT4Rec for Sequential Recommendation}, year = 2020 }
Improving Session Recommendation with Recurrent Neural Networks by Exploiting Dwell Time. Dallmann, Alexander; Grimm, Alexander; Pölitz, Christian; Zoller, Daniel; Hotho, Andreas in CoRR (2017). abs/1706.10231
- [ BibTeX ]
- [ URL ]
- [ Download ]
@article{journals/corr/DallmannGPZH17, author = {Dallmann, Alexander and Grimm, Alexander and Pölitz, Christian and Zoller, Daniel and Hotho, Andreas}, journal = {CoRR}, keywords = {session}, title = {Improving Session Recommendation with Recurrent Neural Networks by Exploiting Dwell Time.}, volume = {abs/1706.10231}, year = 2017 }
Leveraging User-Interactions for Time-Aware Tag Recommendations Zoller, Daniel; Doerfel, Stephan; Pölitz, Christian; Hotho, Andreas in Proceedings of the Workshop on Temporal Reasoning in Recommender Systems, {CEUR} Workshop Proceedings (2017).
- [ Abstract ]
- [ BibTeX ]
- [ Download ]
For the popular task of tag recommendation, various (complex) approaches have been proposed. Recently however, research has focused on heuristics with low computational effort and particularly, a time-aware heuristic, called BLL, has been shown to compare well to various state-of-the-art methods. Here, we follow up on these results by presenting another time-aware approach leveraging user interaction data in an easily interpretable, on-the-fly computable approach that can successfully be combined with BLL. We investigate the influence of time as a parameter in that approach, and we demonstrate the effectiveness of the proposed method using two datasets from the popular public social tagging system BibSonomy.

@inproceedings{zoller2017leveraging, abstract = {For the popular task of tag recommendation, various (complex) approaches have been proposed. Recently however, research has focused on heuristics with low computational effort and particularly, a time-aware heuristic, called BLL, has been shown to compare well to various state-of-the-art methods. Here, we follow up on these results by presenting another time-aware approach leveraging user interaction data in an easily interpretable, on-the-fly computable approach that can successfully be combined with BLL. We investigate the influence of time as a parameter in that approach, and we demonstrate the effectiveness of the proposed method using two datasets from the popular public social tagging system BibSonomy.}, author = {Zoller, Daniel and Doerfel, Stephan and Pölitz, Christian and Hotho, Andreas}, booktitle = {Proceedings of the Workshop on Temporal Reasoning in Recommender Systems}, keywords = {user}, series = {{CEUR} Workshop Proceedings}, title = {Leveraging User-Interactions for Time-Aware Tag Recommendations}, year = 2017 }
Tag Recommendations in Social Bookmarking Systems Jäschke, Robert; Marinho, Leandro; Hotho, Andreas; Schmidt-Thieme, Lars; Stumme, Gerd in AI Communications, (E. Giunchiglia, ed.) (2008). 21(4) 231–247.
- [ Abstract ]
- [ BibTeX ]
- [ URL ]
- [ DOI ]
- [ Download ]
Collaborative tagging systems allow users to assign keywords - so called "tags" - to resources. Tags are used for navigation, finding resources and serendipitous browsing and thus provide an immediate benefit for users. These systems usually include tag recommendation mechanisms easing the process of finding good tags for a resource, but also consolidating the tag vocabulary across users. In practice, however, only very basic recommendation strategies are applied. In this paper we evaluate and compare several recommendation algorithms on large-scale real life datasets: an adaptation of user-based collaborative filtering, a graph-based recommender built on top of the FolkRank algorithm, and simple methods based on counting tag occurences. We show that both FolkRank and Collaborative Filtering provide better results than non-personalized baseline methods. Moreover, since methods based on counting tag occurrences are computationally cheap, and thus usually preferable for real time scenarios, we discuss simple approaches for improving the performance of such methods. We show, how a simple recommender based on counting tags from users and resources can perform almost as good as the best recommender.

@article{jaeschke2008tag, abstract = {Collaborative tagging systems allow users to assign keywords - so called "tags" - to resources. Tags are used for navigation, finding resources and serendipitous browsing and thus provide an immediate benefit for users. These systems usually include tag recommendation mechanisms easing the process of finding good tags for a resource, but also consolidating the tag vocabulary across users. In practice, however, only very basic recommendation strategies are applied. In this paper we evaluate and compare several recommendation algorithms on large-scale real life datasets: an adaptation of user-based collaborative filtering, a graph-based recommender built on top of the FolkRank algorithm, and simple methods based on counting tag occurences. We show that both FolkRank and Collaborative Filtering provide better results than non-personalized baseline methods. Moreover, since methods based on counting tag occurrences are computationally cheap, and thus usually preferable for real time scenarios, we discuss simple approaches for improving the performance of such methods. We show, how a simple recommender based on counting tags from users and resources can perform almost as good as the best recommender.}, address = {Amsterdam}, author = {Jäschke, Robert and Marinho, Leandro and Hotho, Andreas and Schmidt-Thieme, Lars and Stumme, Gerd}, editor = {Giunchiglia, Enrico}, journal = {AI Communications}, keywords = {taggingsurvey}, number = 4, pages = {231-247}, publisher = {IOS Press}, title = {Tag Recommendations in Social Bookmarking Systems}, volume = 21, year = 2008 }

Challenges

We also co-organized recommendation challenges to allow other researchers to develop new recommendation methods:

ECML PKDD Discovery Challenge 2013
Recommending given names for babies
ECML PKDD Discovery Challenge 2009
Content-based, graph-based and online tag recommendation
ECML PKDD Discovery Challenge 2008
Recommendation of tags in our social tagging system BibSonomy (second task)

Deep Learning for Recommender Systems

Projects

adidas

BibSonomy

DZ.PTM

REGIO

Publications

Challenges

Hinweis zum Datenschutz

Hinweis zum Datenschutz

Bildnachweise