Recsperts - Recommender Systems Experts

In episode 24 of Recsperts, I sit down with Amey Dharwadker, Machine Learning Engineering Manager at Facebook, to dive into the complexities of large-scale video recommendations. Amey, who leads the Video Recommendations Quality Ranking team at Facebook, sheds light on the intricate challenges of delivering personalized video feeds at scale. Our conversation covers content understanding, user interaction data, real-time signals, exploration, and evaluation techniques.

We kick off the episode by reflecting on the inaugural VideoRecSys workshop at RecSys 2023, setting the stage for a deeper discussion on Facebook’s approach to video recommendations. Amey walks us through the critical challenges they face, such as gathering reliable user feedback signals to avoid pitfalls like watchbait. With a vast and ever-growing corpus of billions of videos—millions of which are added each month—the cold start problem looms large. We explore how content understanding, user feedback aggregation, and exploration techniques help address this issue. Amey explains how engagement metrics like watch time, comments, and reactions are used to rank content, ensuring users receive meaningful and diverse video feeds.

A key highlight of the conversation is the importance of real-time personalization in fast-paced environments, such as short-form video platforms, where user preferences change quickly. Amey also emphasizes the value of cross-domain data in enriching user profiles and improving recommendations.

Towards the end, Amey shares his insights on leadership in machine learning teams, pointing out the characteristics of a great ML team.

Enjoy this enriching episode of RECSPERTS - Recommender Systems Experts.
Don't forget to follow the podcast and please leave a review

• (00:00) - Introduction

• Amey Dharwadker on LinkedIn
• Amey's Website
• RecSys Challenge 2021
• VideoRecSys Workshop 2023
• VideoRecSys + LargeRecSys 2024

Papers:

• Mahajan et al. (2023): CAViaR: Context Aware Video Recommendations
• Mahajan et al. (2023): PIE: Personalized Interest Exploration for Large-Scale Recommender Systems
• Raul et al. (2023): CAM2: Conformity-Aware Multi-Task Ranking Model for Large-Scale Recommender Systems
• Zhai et al. (2024): Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations
• Saket et al. (2023): Formulating Video Watch Success Signals for Recommendations on Short Video Platforms
• Wang et al. (2022): Surrogate for Long-Term User Experience in Recommender Systems
• Su et al. (2024): Long-Term Value of Exploration: Measurements, Findings and Algorithms

General Links:

• Follow me on LinkedIn
• Follow me on X
• Send me your comments, questions and suggestions to [email protected]
• Recsperts Website

In episode 23 of Recsperts, we welcome Yashar Deldjoo, Assistant Professor at the Polytechnic University of Bari, Italy. Yashar's research on recommender systems includes multimodal approaches, multimedia recommender systems as well as trustworthiness and adversarial robustness, where he has published a lot of work. We discuss the evolution of generative models for recommender systems, modeling paradigms, scenarios as well as their evaluation, risks and harms.

We begin our interview with a reflection of Yashar's areas of recommender systems research so far. Starting with multimedia recsys, particularly video recommendations, Yashar covers his work around adversarial robustness and trustworthiness leading to the main topic for this episode: generative models for recommender systems. We learn about their aspects for improving beyond the (partially saturated) state of traditional recommender systems: improve effectiveness and efficiency for top-n recommendations, introduce interactivity beyond classical conversational recsys, provide personalized zero- or few-shot recommendations.
We learn about the modeling paradigms and as well about the scenarios for generative models which mainly differ by input and modelling approach: ID-based, text-based, and multimodal generative models. This is how we navigate the large field of acronyms leading us from VAEs and GANs to LLMs.

Towards the end of the episode, we also touch on the evaluation, opportunities, risks and harms of generative models for recommender systems. Yashar also provides us with an ample amount of references and upcoming events where people get the chance to know more about GenRecSys.

Enjoy this enriching episode of RECSPERTS - Recommender Systems Experts.
Don't forget to follow the podcast and please leave a review

• (00:00) - Introduction

• Yashar Deldjoo on LinkedIn
• Yashar's Website
• KDD 2024 Tutorial: Modern Recommender Systems Leveraging Generative AI: Fundamentals, Challenges and Opportunities
• RecSys 2024 Workshop: The 1st Workshop on Risks, Opportunities, and Evaluation of Generative Models in Recommender Systems (ROEGEN@RECSYS'24)

Papers:

• Deldjoo et al. (2024): A Review of Modern Recommender Systems Using Generative Models (Gen-RecSys)
• Deldjoo et al. (2020): Recommender Systems Leveraging Multimedia Content
• Deldjoo et al. (2021): A Survey on Adversarial Recommender Systems: From Attack/Defense Strategies to Generative Adversarial Networks
• Deldjoo et al. (2020): How Dataset Characteristics Affect the Robustness of Collaborative Recommendation Models
• Liang et al. (2018): Variational Autoencoders for Collaborative Filtering
• He et al. (2016): Visual Bayesian Personalized Ranking from Implicit Feedback

General Links:

• Follow me on LinkedIn
• Follow me on X
• Send me your comments, questions and suggestions to [email protected]
• Recsperts Website

In episode 22 of Recsperts, we welcome Prabhat Agarwal, Senior ML Engineer, and Aayush Mudgal, Staff ML Engineer, both from Pinterest, to the show. Prabhat works on recommendations and search systems at Pinterest, leading representation learning efforts. Aayush is responsible for ads ranking and privacy-aware conversion modeling. We discuss user and content modeling, short- vs. long-term objectives, evaluation as well as multi-task learning and touch on counterfactual evaluation as well.

In our interview, Prabhat guides us through the journey of continuous improvements of Pinterest's Homefeed personalization starting with techniques such as gradient boosting over two-tower models to DCN and transformers. We discuss how to capture users' short- and long-term preferences through multiple embeddings and the role of candidate generators for content diversification. Prabhat shares some details about position debiasing and the challenges to facilitate exploration.
With Aayush we get the chance to dive into the specifics of ads ranking at Pinterest and he helps us to better understand how multifaceted ads can be. We learn more about the pain of having too many models and the Pinterest's efforts to consolidate the model landscape to improve infrastructural costs, maintainability, and efficiency. Aayush also shares some insights about exploration and corresponding randomization in the context of ads and how user behavior is very different between different kinds of ads.
Both guests highlight the role of counterfactual evaluation and its impact for faster experimentation.

Towards the end of the episode, we also touch a bit on learnings from last year's RecSys challenge.

Enjoy this enriching episode of RECSPERTS - Recommender Systems Experts.
Don't forget to follow the podcast and please leave a review

• (00:00) - Introduction

• Prabhat Agarwal on LinkedIn
• Aayush Mudgal on LinkedIn
• RecSys Challenge 2023
• Pinterest Engineering Blog
• Pinterest Labs
• Prabhat's Talk at GTC 2022: Evolution of web-scale engagement modeling at Pinterest
• Blogpost: How we use AutoML, Multi-task learning and Multi-tower models for Pinterest Ads
• Blogpost: Pinterest Home Feed Unified Lightweight Scoring: A Two-tower Approach
• Blogpost: Experiment without the wait: Speeding up the iteration cycle with Offline Replay Experimentation
• Blogpost: MLEnv: Standardizing ML at Pinterest Under One ML Engine to Accelerate Innovation
• Blogpost: Handling Online-Offline Discrepancy in Pinterest Ads Ranking System

Papers:

• Eksombatchai et al. (2018): Pixie: A System for Recommending 3+ Billion Items to 200+ Million Users in Real-Time
• Ying et al. (2018): Graph Convolutional Neural Networks for Web-Scale Recommender Systems
• Pal et al. (2020): PinnerSage: Multi-Modal User Embedding Framework for Recommendations at Pinterest
• Pancha et al. (2022): PinnerFormer: Sequence Modeling for User Representation at Pinterest
• Zhao et al. (2019): Recommending what video to watch next: a multitask ranking system

General Links:

• Follow me on LinkedIn
• Follow me on X
• Send me your comments, questions and suggestions to [email protected]
• Recsperts Website

In episode 21 of Recsperts, we welcome Martijn Willemsen, Associate Professor at the Jheronimus Academy of Data Science and Eindhoven University of Technology. Martijn's researches on interactive recommender systems which includes aspects of decision psychology and user-centric evaluation. We discuss how users gain control over recommendations, how to support their goals and needs as well as how the user-centric evaluation framework fits into all of this.

In our interview, Martijn outlines the reasons for providing users control over recommendations and how to holistically evaluate the satisfaction and usefulness of recommendations for users goals and needs. We discuss the psychology of decision making with respect to how well or not recommender systems support it. We also dive into music recommender systems and discuss how nudging users to explore new genres can work as well as how longitudinal studies in recommender systems research can advance insights.

Towards the end of the episode, Martijn and I also discuss some examples and the usefulness of enabling users to provide negative explicit feedback to the system.

Enjoy this enriching episode of RECSPERTS - Recommender Systems Experts.
Don't forget to follow the podcast and please leave a review

• (00:00) - Introduction

• Martijn Willemsen on LinkedIn
• Martijn Willemsen's Website
• User-centric Evaluation Framework
• Behaviorism is not Enough (Talk at RecSys 2016)
• Neil Hunt: Quantifying the Value of Better Recommendations (Keynote at RecSys 2014)
• What recommender systems can learn from decision psychology about preference elicitation and behavioral change (Talk at Boise State (Idaho) and Grouplens at University of Minnesota)
• Eric J. Johnson: The Elements of Choice
• Rasch Model
• Spotify Web API

Papers:

• Ekstrand et al. (2016): Behaviorism is not Enough: Better Recommendations Through Listening to Users
• Knijenburg et al. (2012): Explaining the user experience of recommender systems
• Ekstrand et al. (2014): User perception of differences in recommender algorithms
• Liang et al. (2022): Exploring the longitudinal effects of nudging on users’ music genre exploration behavior and listening preferences
• McNee et al. (2006): Being accurate is not enough: how accuracy metrics have hurt recommender systems

General Links:

• Follow me on LinkedIn
• Follow me on X
• Send me your comments, questions and suggestions to [email protected]
• Recsperts Website

In episode 20 of Recsperts, we welcome Bram van den Akker, Senior Machine Learning Scientist at Booking.com. Bram's work focuses on bandit algorithms and counterfactual learning. He was one of the creators of the Practical Bandits tutorial at the World Wide Web conference. We talk about the role of bandit feedback in decision making systems and in specific for recommendations in the travel industry.

In our interview, Bram elaborates on bandit feedback and how it is used in practice. We discuss off-policy- and on-policy-bandits, and we learn that counterfactual evaluation is right for selecting the best model candidates for downstream A/B-testing, but not a replacement. We hear more about the practical challenges of bandit feedback, for example the difference between model scores and propensities, the role of stochasticity or the nitty-gritty details of reward signals. Bram also shares with us the challenges of recommendations in the travel domain, where he points out the sparsity of signals or the feedback delay.

At the end of the episode, we can both agree on a good example for a clickbait-heavy news service in our phones.

Enjoy this enriching episode of RECSPERTS - Recommender Systems Experts.
Don't forget to follow the podcast and please leave a review

• (00:00) - Introduction

• Bram van den Akker on LinkedIn
• Practical Bandits: An Industry Perspective (Website)
• Practical Bandits: An Industry Perspective (Recording)
• Tutorial at The Web Conference 2020: Unbiased Learning to Rank: Counterfactual and Online Approaches
• Tutorial at RecSys 2021: Counterfactual Learning and Evaluation for Recommender Systems: Foundations, Implementations, and Recent Advances
• GitHub: Open Bandit Pipeline

Papers:

• van den Akker et al. (2023): Practical Bandits: An Industry Perspective
• van den Akker et al. (2022): Extending Open Bandit Pipeline to Simulate Industry Challenges
• van den Akker et al. (2019): ViTOR: Learning to Rank Webpages Based on Visual Features

General Links:

• Follow me on LinkedIn
• Follow me on X
• Send me your comments, questions and suggestions to [email protected]
• Recsperts Website

In episode 19 of Recsperts, we welcome Himan Abdollahpouri who is an Applied Research Scientist for Personalization & Machine Learning at Spotify. We discuss the role of popularity bias in recommender systems which was the dissertation topic of Himan. We talk about multi-objective and multi-stakeholder recommender systems as well as the challenges of music and podcast streaming personalization at Spotify.

In our interview, Himan walks us through popularity bias as the main cause of unfair recommendations for multiple stakeholders. We discuss the consumer- and provider-side implications and how to evaluate popularity bias. Not the sheer existence of popularity bias is the major problem, but its propagation in various collaborative filtering algorithms. But we also learn how to counteract by debiasing the data, the model itself, or it's output. We also hear more about the relationship between multi-objective and multi-stakeholder recommender systems.

At the end of the episode, Himan also shares the influence of popularity bias in music and podcast streaming at Spotify as well as how calibration helps to better cater content to users' preferences.

Enjoy this enriching episode of RECSPERTS - Recommender Systems Experts.
Don't forget to follow the podcast and please leave a review

• (00:00) - Introduction

• Himan Abdollahpouri on LinkedIn
• Himan Abdollahpouri on X
• Himan's Website
• Himan's PhD Thesis on "Popularity Bias in Recommendation: A Multi-stakeholder Perspective"
• 2nd Workshop on Multi-Objective Recommender Systems (MORS @ RecSys 2022)

Papers:

• Su et al. (2009): A Survey on Collaborative Filtering Techniques
• Mehrotra et al. (2018): Towards a Fair Marketplace: Counterfactual Evaluation of the trade-off between Relevance, Fairness & Satisfaction in Recommender Systems
• Abdollahpouri et al. (2021): User-centered Evaluation of Popularity Bias in Recommender Systems
• Abdollahpouri et al. (2019): The Unfairness of Popularity Bias in Recommendation
• Abdollahpouri et al. (2017): Controlling Popularity Bias in Learning-to-Rank Recommendation
• Wasilewsi et al. (2016): Incorporating Diversity in a Learning to Rank Recommender System
• Oh et al. (2011): Novel Recommendation Based on Personal Popularity Tendency
• Steck (2018): Calibrated Recommendations
• Abdollahpouri et al. (2023): Calibrated Recommendations as a Minimum-Cost Flow Problem
• Seymen et al. (2022): Making smart recommendations for perishable and stockout products

General Links:

• Follow me on LinkedIn
• Follow me on X
• Send me your comments, questions and suggestions to [email protected]
• Recsperts Website

In episode 18 of Recsperts, we hear from Professor Sole Pera from Delft University of Technology. We discuss the use of recommender systems for non-traditional populations, with children in particular. Sole shares the specifics, surprises, and subtleties of her research on recommendations for children.

In our interview, Sole and I discuss use cases and domains which need particular attention with respect to non-traditional populations. Sole outlines some of the major challenges like lacking public datasets or multifaceted criteria for the suitability of recommendations. The highly dynamic needs and abilities of children pose proper user modeling as a crucial part in the design and development of recommender systems. We also touch on how children interact differently with recommender systems and learn that trust plays a major role here.

Towards the end of the episode, we revisit the different goals and stakeholders involved in recommendations for children, especially the role of parents. We close with an overview of the current research community.

Enjoy this enriching episode of RECSPERTS - Recommender Systems Experts.
Don't forget to follow the podcast and please leave a review

• (00:00) - Introduction

• Sole Pera on LinkedIn
• Sole's Website
• Children and Recommenders
• KidRec 2022
• People and Information Retrieval Team (PIReT)

Papers:

• Beyhan et al. (2023): Covering Covers: Characterization Of Visual Elements Regarding Sleeves
• Murgia et al. (2019): The Seven Layers of Complexity of Recommender Systems for Children in Educational Contexts
• Pera et al. (2019): With a Little Help from My Friends: User of Recommendations at School
• Charisi et al. (2022): Artificial Intelligence and the Rights of the Child: Towards an Integrated Agenda for Research and Policy
• Gómez et al. (2021): Evaluating recommender systems with and for children: towards a multi-perspective framework
• Ng et al. (2018): Recommending social-interactive games for adults with autism spectrum disorders (ASD)

General Links:

• Follow me on LinkedIn
• Follow me on Twitter
• Send me your comments, questions and suggestions to [email protected]
• Recsperts Website

In episode 17 of Recsperts, we meet Miguel Fierro who is a Principal Data Science Manager at Microsoft and holds a PhD in robotics. We talk about the Microsoft recommenders repository with over 15k stars on GitHub and discuss the impact of LLMs on RecSys. Miguel also shares his view of the T-shaped data scientist.

In our interview, Miguel shares how he transitioned from robotics into personalization as well as how the Microsoft recommenders repository started. We learn more about the three key components: examples, library, and tests. With more than 900 tests and more than 30 different algorithms, this library demonstrates a huge effort of open-source contribution and maintenance. We hear more about the principles that made this effort possible and successful. Therefore, Miguels also shares the reasoning behind evidence-based design to put the users of microsoft-recommenders and their expectations first. We also discuss the impact that recent LLM-related innovations have on RecSys.

At the end of the episode, Miguel explains the T-shaped data professional as an advice to stay competitive and build a champion data team. We conclude with some remarks regarding the adoption and ethical challenges recommender systems pose and which need further attention.

Enjoy this enriching episode of RECSPERTS - Recommender Systems Experts.
Don't forget to follow the podcast and please leave a review

• (00:00) - Episode Overview

• Miguel Fierro on LinkedIn
• Miguel Fierro on Twitter
• Miguel's Website
• Microsoft Recommenders
• McKinsey (2013): How retailers can keep up with consumers
• Fortune (2012): Amazon's recommendation secret
• RecSys 2021 Keynote by Max Welling: Graph Neural Networks for Knowledge Representation and Recommendation

Papers:

• Geng et al. (2022): Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)

General Links:

• Follow me on LinkedIn
• Follow me on Twitter
• Send me your comments, questions and suggestions to [email protected]
• Recsperts Website

In episode 16 of Recsperts, we hear from Michael D. Ekstrand, Associate Professor at Boise State University, about fairness in recommender systems. We discuss why fairness matters and provide an overview of the multidimensional fairness-aware RecSys landscape. Furthermore, we talk about tradeoffs, methods and receive practical advice on how to get started with tackling unfairness.

In our discussion, Michael outlines the difference and similarity between fairness and bias. We discuss several stages at which biases can enter the system as well as how bias can indeed support mitigating unfairness. We also cover the perspectives of different stakeholders with respect to fairness. We also learn that measuring fairness depends on the specific fairness concern one is interested in and that solving fairness universally is highly unlikely.

Towards the end of the episode, we take a look at further challenges as well as how and where the upcoming RecSys 2023 provides a forum for those interested in fairness-aware recommender systems.

Enjoy this enriching episode of RECSPERTS - Recommender Systems Experts.

• (00:00) - Episode Overview

• Michael Ekstrand on LinkedIn
• Michael Ekstrand on Mastodon
• Michael's Website
• GroupLens Lab at University of Minnesota
• People and Information Research Team (PIReT)
• 6th FAccTRec Workshop: Responsible Recommendation
• NORMalize: The First Workshop on Normative Design and Evaluation of Recommender Systems
• ACM Conference on Fairness, Accountability, and Transparency (ACM FAccT)
• Coursera: Recommender Systems Specialization
• LensKit: Python Tools for Recommender Systems
• Chris Anderson - The Long Tail: Why the Future of Business Is Selling Less of More
• Fairness in Recommender Systems (in Recommender Systems Handbook)
• Ekstrand et al. (2022): Fairness in Information Access Systems
• Keynote at EvalRS (CIKM 2022): Do You Want To Hunt A Kraken? Mapping and Expanding Recommendation Fairness
• Friedler et al. (2021): The (Im)possibility of Fairness: Different Value Systems Require Different Mechanisms For Fair Decision Making
• Safiya Umoja Noble (2018): Algorithms of Oppression: How Search Engines Reinforce Racism

Papers:

• Ekstrand et al. (2018): Exploring author gender in book rating and recommendation
• Ekstrand et al. (2014): User perception of differences in recommender algorithms
• Selbst et al. (2019): Fairness and Abstraction in Sociotechnical Systems
• Pinney et al. (2023): Much Ado About Gender: Current Practices and Future Recommendations for Appropriate Gender-Aware Information Access
• Diaz et al. (2020): Evaluating Stochastic Rankings with Expected Exposure
• Raj et al. (2022): Fire Dragon and Unicorn Princess; Gender Stereotypes and Children's Products in Search Engine Responses
• Mitchell et al. (2021): Algorithmic Fairness: Choices, Assumptions, and Definitions
• Mehrotra et al. (2018): Towards a Fair Marketplace: Counterfactual Evaluation of the trade-off between Relevance, Fairness & Satisfaction in Recommender Systems
• Raj et al. (2022): Measuring Fairness in Ranked Results: An Analytical and Empirical Comparison
• Beutel et al. (2019): Fairness in Recommendation Ranking through Pairwise Comparisons
• Beutel et al. (2017): Data Decisions and Theoretical Implications when Adversarially Learning Fair Representations
• Dwork et al. (2018): Fairness Under Composition
• Bower et al. (2022): Random Isn't Always Fair: Candidate Set Imbalance and Exposure Inequality in Recommender Systems
• Zehlike et al. (2022): Fairness in Ranking: A Survey
• Hoffmann (2019): Where fairness fails: data, algorithms, and the limits of antidiscrimination discourse
• Sweeney (2013): Discrimination in Online Ad Delivery: Google ads, black names and white names, racial discrimination, and click advertising
• Wang et al. (2021): User Fairness, Item Fairness, and Diversity for Rankings in Two-Sided Markets

General Links:

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

In episode 15 of Recsperts, we delve into podcast recommendations with senior data scientist, Mirza Klimenta. Mirza discusses his work on the ARD Audiothek, a public broadcaster of audio-on-demand content, where he is part of pub. Public Value Technologies, a subsidiary of the two regional public broadcasters BR and SWR.

We explore the use and potency of simple algorithms and ways to mitigate popularity bias in data and recommendations. We also cover collaborative filtering and various approaches for content-based podcast recommendations, drawing on Mirza's expertise in multidimensional scaling for graph drawings. Additionally, Mirza sheds light on the responsibility of a public broadcaster in providing diversified content recommendations.

Towards the end of the episode, Mirza shares personal insights on his side project of becoming a novelist. Tune in for an informative and engaging conversation.

Enjoy this enriching episode of RECSPERTS - Recommender Systems Experts.

• (00:00) - Episode Overview

• Mirza Klimenta on LinkedIn
• ARD Audiothek
• pub. Public Value Technologies
• Implicit: Fast Collaborative Filtering for Implicit Datasets
• Fairness in Recommender Systems: How to Reduce the Popularity Bias

Papers:

• Steck (2019): Embarrasingly Shallow Auoencoders for Sparse Data
• Hu et al. (2008): Collaborative Filtering for Implicit Feedback Datasets
• Cer et al. (2018): Universal Sentence Encoder

General Links:

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