Recsperts - Recommender Systems Experts

In episode four my guest is Felice Merra, who is an applied scientist at Amazon. Felice obtained his PhD from Politecnico di Bari where he was a researcher at the Information Systems Lab (SisInf Lab). There, he worked on Security and Adversarial Machine Learning in Recommender Systems.

We talk about different ways to perturb interaction or content data, but also model parameters, and elaborated various defense strategies.
In addition, we touch on the motivation of individuals or whole platforms to perform attacks and look at some examples that Felice has been working on throughout his research.
The overall goals of research in Adversarial Machine Learning for Recommender Systems is to identify vulnerabilities of models and systems in order to derive proper defense strategies that make systems more robust against potential attacks.
Finally, we also briefly discuss privacy-preserving learning and the challenges of further robustification of multimedia recommender systems.

Felice has published multiple papers at KDD, ECIR, SIGIR, and RecSys. He also won the Best Paper Award at KDD's workshop on Adversarial Learning Methods.

Enjoy this enriching episode of RECSPERTS - Recommender Systems Experts.

Links from this Episode:

• Felice's Website
• Felice Merra on LinkedIn and Twitter
• Adversarial Machine Learning in Recommender Systems (PhD Thesis Final Presentation)
• Workshop on Adversarial Personalized Ranking Optimization at ACM KDD 2021 (awarded Best Paper)
• Adversarial Recommender Systems: Attack, Defense, and Advances (chapter in 3rd edition of Recommender Systems Handbook)
• Information Systems Lab (SisInf Lab)

Thesis and Papers:

• Merra et al. (2020): How Dataset Characteristics Affect the Robustness of Collaborative Recommendation Models
• Merra et al. (2021): A survey on Adversarial Recommender Systems: from Attack/Defense strategies to Generative Adversarial Networks
• find all the papers on Felice's website

General Links:

• Follow me on Twitter: https://twitter.com/LivesInAnalogia
• Send me your comments, questions and suggestions to [email protected]
• Podcast Website: https://www.recsperts.com/

In episode three I am joined by Olivier Jeunen, who is a postdoctoral scientist at Amazon. Olivier obtained his PhD from University of Antwerp with his work "Offline Approaches to Recommendation with Online Success". His work concentrates on Bandits, Reinforcement Learning and Causal Inference for Recommender Systems.

We talk about methods for evaluating online performance of recommender systems in an offline fashion and based on rich logging data. These methods stem from fields like bandit theory and reinforcement learning. They heavily rely on simulators whose benefits, requirements and limitations we discuss in greater detail. We further discuss the differences between organic and bandit feedback as well as what sets recommenders apart from advertising. We also talk about the right target for optimization and receive some advice to continue livelong learning as a researcher, be it in academia or industry.
Olivier has published multiple papers at RecSys, NeurIPS, WSDM, UMAP, and WWW. He also won the RecoGym challenge with his team from University of Antwerp. With research internships at Criteo, Facebook and Spotify Research he brings significant experience to the table.

Enjoy this enriching episode of RECSPERTS - Recommender Systems Experts.

Links from this Episode:

• Olivier's Website
• Olivier Jeunen on LinkedIn and Twitter
• Simulators:
  • RecoGym
  • RecSim
  • RecSimNG
  • Open Bandit Pipeline
• Blogpost: Lessons Learned from Winning the RecoGym Challenge
• RecSys 2020 REVEAL Workshop on Bandit and Reinforcement Learning from User Interactions
• RecSys 2021 Tutorial on Counterfactual Learning and Evaluation for Recommender Systems
• NeurIPS 2021 Workshop on Causal Inference and Machine Learning

Thesis and Papers:

• Dissertation: Offline Approaches to Recommendation with Online Success
• Chen et al. (2018): Top-K Off-Policy Correction for a REINFORCE Recommender System
• Jeunen et al. (2021): Disentangling Causal Effects from Sets of Interventions in the Presence of Unobserved Confounders
• Jeunen et al. (2021): Top-𝐾 Contextual Bandits with Equity of Exposure

General Links:

• Follow me on Twitter: https://twitter.com/LivesInAnalogia
• Send me your comments, questions and suggestions to [email protected]
• Podcast Website: https://www.recsperts.com/

In episode two I am joined by Even Oldridge, Senior Manager at NVIDIA, who is leading the Merlin Team. These people are working on an open-source framework for building large-scale deep learning recommender systems and have already won numerous RecSys competitions.

We talk about the relevance and impact of deep learning applied to recommender systems as well as the challenges and pitfalls of deep learning based recommender systems. We briefly touch on Even's early data science contributions at PlentyOfFish, a Canadian online-dating platform. Starting with personalized recommendations of people to people he transitioned to realtor, a real-estate marketplace. From the potentially biggest social decision in life to the probably biggest financial decision in life he has really been involved with recommender systems at the extremes. At NVIDIA - to which he refers as the one company that works with all the other AI companies - he pushes for Merlin as large-scale, accessible and efficient platform for developing and deploying recommender systems on GPUs.
This brought him also closer to the community which he served as industry Co-Chair at RecSys in 2021 as well as to winning multiple RecSys competitions with his team in the recent years.

Enjoy this enriching episode of RECSPERTS - Recommender Systems Experts.

Links from this Episode:

• Even Oldridge on LinkedIn and Twitter
• NVIDIA Merlin
• NVIDIA Merlin at GitHub
• Even's upcoming Talk at GTC 2021: Building and Deploying Recommender Systems Quickly and Easily with NVIDIA Merlin
• PlentyOfFish, realtor
• fast.ai
• Twitter RecSys Challenge 2021
• Recommending music on Spotify with Deep Learning

Papers

• Dacrema et al. (2019): Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approaches (best paper award at RecSys 2019)
• Jannach et al. (2020): Why Are Deep Learning Models Not Consistently Winning Recommender Systems Competitions Yet?: A Position Paper
• Moreira et al. (2021): Transformers4Rec: Bridging the Gap between NLP and Sequential / Session-Based Recommendation
• Deotte et al. (2021): GPU Accelerated Boosted Trees and Deep Neural Networks for Better Recommender Systems 

General Links:

• Follow me on Twitter: https://twitter.com/LivesInAnalogia
• Send me your comments, questions and suggestions to [email protected]
• Podcast Website: https://www.recsperts.com/

In this first interview we talk to Kim Falk, Senior Data Scientist, multiple RecSys Industry Chair and author of the book "Practical Recommender Systems". We introduce into recommenders from a practical perspective discussing the fundamental difference between content-based and collaborative filtering as well as the cold-start problem - no mathematical deep-dive yet, but expect it to follow. In addition, we reason what constitutes good recommendations and briefly touch on a couple of ways of finding that out.
Looking a bit into the history of the recommender systems community, we touch on the Netflix Prize that was running from 2006 to 2009 as well as on the RecSys - the leading conference in recommender systems, where we also met for the first time.
In the end, we discuss a couple of challenges the field faces, in particular associated with approaches based on deep learning. Besides that, Spiderman will accompany our conversation at certain times. Plus many practical recommendations included on how to get started. Stay tuned!

Links from this Episode:

• Kim Falk on LinkedIn and Twitter
• Book: Practical Recommender Systems (Manning) (get 37% discount with the code podrecsperts37 during checkout)
• GitHub Repository for PRS Book
• ACM Conference on Recommender Systems 2021 (Amsterdam)
• Recommender Systems Specialization at Coursera
• Amazon.com Recommendations: Item-to-Item Collaborative Filtering
• Netflix Prize
• Netflix Prize dataset on Kaggle
• New York Times: A $1 Million Research Bargain for Netflix, and Maybe a Model for Others
• Evaluation Measures for Information Retrieval
• Paper by Dacrema et al. (2019): Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approaches (best paper award at RecSys 2019)
• Recommending music on Spotify with Deep Learning
• MovieLens Recommenders

General Links:

• Follow me on Twitter: https://twitter.com/LivesInAnalogia
• Send me your comments, questions and suggestions to [email protected]
• Podcast Website: https://www.recsperts.com/

Twitter and LinkedIn posts for sharing:

• LinkedIn
• Twitter

Have you ever though about how Spotify is able to generate its fantastic Discover Weekly Playlist, how Amazon is generating a fortune by showing what other like you purchased in the past, or how Netflix achieves high user retention? The answer is personalization and in this show we focus on the most prominent way to achieve personalization: recommender systems.
Whether you are a beginner and new to the field or you have already build recommenders, this show is to bring you the experts in recommender systems to share their knowledge and expertise with all of us. It is for making the topic more accessible and to provide a regular coverage of basics and advances in recommender systems research and application. I invite the experts to share their insights and to provide you with the right knowledge to get started and gain expertise yourself.

In this introductory episode I am going to share some exemplary use cases from different industries (music streaming, e-commerce, travel, or social networks) along with challenges and problems in research and application. Plus, I am presenting the first guest for our upcoming episode.

Links from the show:

• ACM Conference on Recommender Systems 2021 (Amsterdam): https://recsys.acm.org/recsys21/
• Introductory Python RecSys Training: https://github.com/mkurovski/recsys_training
• Follow me on Twitter: https://twitter.com/LivesInAnalogia
• Read my RecSys Blogposts: https://medium.com/@marcel.kurovski
• Send me your comments, questions and suggestions to [email protected]
• Podcast Website: https://www.recsperts.com/