Feature Engineering for Recommender Systems
by Benedikt Schifferer (Nvidia), Chris Deotte (Nvidia) and Even Oldridge (Nvidia)
The selection of features and proper preparation of data for deep learning or machine learning models plays a significant role in the performance of recommender systems. To address this we propose a tutorial highlighting best practices and optimization techniques for feature engineering and preprocessing of recommender system datasets. The tutorial will explore feature engineering using pandas and Dask, and will also cover acceleration on the GPU using open source libraries like RAPIDS cuDF and NVTabular. We’ve designed the tutorial as a combination of a lecture covering the mathematical and theoretical background and an interactive session based on jupyter notebooks. Participants will practice the discussed features by writing their own implementation in Python. NVIDIA will host the tutorial on their infrastructure, providing dataset, jupyter notebooks and GPUs. Participants will be able to easily attend the tutorial via their web browsers, avoiding any complicated setup. Beginner to intermediate users are the target audience, which should have prior knowledge in python programming using libraries, such as pandas and NumPy. In addition, they should have a basic understanding of recommender systems, decision trees and feed forward neural networks.
The tutorial is designed as a combination of theoretical lectures and practical exercises for the participants. We provide the lectures as pre-recordings and recommend all participants to watch them in advance to the 1 hour live session. In the 2×1 hour live sessions, participants get access to NVIDIA’s Deep Learning Institute (DLI) infrastructure and are able to explore the tutorial hands-on and work on the exercises. If participants have questions, we will answer/support the exercises in the chat. In parallel, we will provide a shortened version of our tutorial for participants, who haven’t had the opportunity to watch the pre-recordings.
Date
Session A on 15:30 – 16:30, Attend in Whova
Session B on 2:30 – 3:30, Attend in Whova
Bayesian Value Based Recommendation: A Modelling based Alternative to Proxy and Counterfactual Policy based Recommendation
by David Rohde (Criteo), Flavian Vasile (Criteo), Sergey Ivanov (Criteo), and Otmane Sakhi (Criteo)
We develop the value based approach to Recommender systems. The value approach is a model based approach that allows forecasting of actual A/B test performance. It contrasts with the proxy based approach, which attempts to order the performance of different recommendation systems, but not forecast actual performance. It also contrasts with policy based approaches which also produce a performance forecast but use propensity scores to by-pass the requirement for a model. Value based approaches are a state of the art approach for combining organic and bandit signals that can utilise the three fundamental distances of recommendation. Their deployment requires sophisticated modelling and Bayesian computation.
This tutorial develops the theory of value based recommendation and demonstrates the approach with examples in python notebooks.
Date
Session A on 20:00 – 21:00, Attend in Whova
Session B on 7:00 – 8:00, Attend in Whova
Counteracting Bias and Increasing Fairness in Search and Recommender Systems
by Ruoyuan Gao (Rutgers University) and Chirag Shah (University of Washington)
Search and recommender systems have unprecedented influence on how and what information people access. These gateways to information on the one hand create an easy and universal access to online information, and on the other hand create biases that have shown to cause knowledge disparity and ill-decisions for information seekers. Most of the algorithms for indexing, retrieval, ranking, and recommendation are heavily driven by the underlying data that itself is biased. In addition, ordering of the search and recommendation results create position bias and exposure bias due to their considerable focus on relevance and user satisfaction. These and other forms of biases that are implicitly and some times explicitly woven in search and recommender systems are becoming increasing threats to information seeking and sense-making processes. In this tutorial, we will introduce the issues of biases in search and recommendation and show how we could think about and create systems that are fairer, with increasing diversity and transparency. Specifically, the tutorial will present several fundamental concepts such as relevance, novelty, diversity, bias, and fairness using socio-technical terminologies taken from various communities, and dive deeper into metrics and frameworks that allow us to understand, extract, and materialize them. The tutorial will cover some of the most recent works in this area and show how this interdisciplinary research has opened up new challenges and opportunities for communities such as RecSys.
Date
Session A on 17:00 – 18:00, Attend in Whova
Session B on 4:00 – 5:00, Attend in Whova
Adversarial Learning for Recommendation: Applications for Security and Generative Tasks – Concept to Code
by Vito Walter Anelli (Polytechnic University of Bari), Yashar Deldjoo (Polytechnic University of Bari), Tommaso Di Noia (Polytechnic University of Bari) and Felice Antonio Merra (Polytechnic University of Bari)
Adversarial Machine Learning (AML) has emerged as the field of study that, starting from the identification of vulnerabilities in computer vision tasks (e.g., image classification), investigates security issues on modern machine learning (ML) recommenders.
In this tutorial, we present a comprehensive overview of the application of AML techniques in the two-fold categorization: (i) AML for the attack/defense purposes, and (ii) AML to build GAN-based recommender models. Furthermore, we will integrate the presentation of AML in RS with two hands-on sessions, one for each of the previous categorization, to show the efficacy of AML application and push up novel ideas and advances in many recommendation tasks.
The tutorial is divided into four parts. Firstly, we present a summary of the state-of-the-art recommender models, including deep learning ones, and we define the fundamentals of AML. Then, we present the Adversarial Recommendation Framework, to represent attack/defense strategies on RSs, and the GAN-based Recommendation Framework, from which we present novel adversarial-based generative recommenders. The presentation of both frameworks also includes a practical session. Finally, we conclude with open challenges and possible future works in both applications.
Date
Session A on 21:30 – 22:30, Attend in Whova
Session B on 8:30 – 9:30, Attend in Whova
Introduction to Bandits in Recommender Systems
by Andrea Barraza-Urbina (NUI Galway) and Dorota Glowacka (University of Helsinki)
The multi-armed bandit problem models an agent that simultaneously attempts to acquire new knowledge (exploration) and optimize his decisions based on existing knowledge (exploitation). The agent attempts to balance these competing tasks in order to maximize his total value over the period of time considered. There are many practical applications of the bandit model, such as clinical trials, adaptive routing or portfolio design. Over the last decade there has been an increased interest in developing bandit algorithms for specific problems in recommender systems, such as news and ad recommendation, the cold start problem in recommendation, personalization, collaborative filtering with bandits, or combining social networks with bandits to improve product recommendation.
The aim of this tutorial is to provide participants with the basic knowledge of the following concepts: (a) the exploration-exploitation dilemma and its connection to learning through interaction; (b) framing of the recommender systems problem as an interactive sequential decision-making task that needs to balance exploration and exploitation; (c) basic fundamentals behind bandit approaches that address the exploration-exploitation dilemma; and (d) a general picture of the state-of-the-art of bandit-based recommender systems. With this tutorial we hope to enable participants to start working on bandit-based recommender systems and to provide a framework that would empower them to develop more advanced approaches.
The tutorial is divided into three sections focused on: (1) general motivation and introduction to classic bandit approaches; (2) hands-on session where a simple synthetic recommendation task representing a bandit problem with linear rewards will be used; and (3) overview of a variety of applications of bandit algorithms in recommendation systems summarizing the current state and an outline of challenges applying bandit algorithms in recommendation systems.
This introductory tutorial is aimed at an audience with background in computer science, information retrieval or recommender systems who have a general interest in the application of machine learning techniques in recommender systems. The prerequisite knowledge is basic familiarity with machine learning and basic knowledge of statistics and probability theory. The tutorial will provide practical examples based on Python code and Jupyter Notebooks.
Date
Session A on 18:30 – 19:30, Attend in Whova
Session B on 5:30 – 6:30, Attend in Whova
Tutorial on Conversational Recommender Systems
by Yongfeng Zhang (Rutgers University), Zuohui Fu (Rutgers University), Yikun Xian (Rutgers University), and Yi Zhang (University of California Santa Cruz)
Recent years have witnessed the emerging of conversational systems, including both physical devices and mobile-based applications. Both the research community and industry believe that conversational systems will have a major impact on human-computer interaction, and specifically, the RecSys community has begun to explore Conversational Recommendation Systems.
Conversational recommendation aims at finding or recommending the most relevant information (e.g., web pages, answers, movies, products) for users based on textual- or spoken-dialogs, through which users can communicate with the system more efficiently using natural language conversations. Due to users’ constant need to look for information to support both work and daily life, conversational recommendation system will be one of the key techniques towards an intelligent web.
The tutorial focuses on the foundations and algorithms for conversational recommendation, as well as their application in real-world systems such as search engine, e-commerce and social networks. The tutorial aims at introducing and communicating conversational recommendation methods to the community, as well as gathering researchers and practitioners interested in this research direction for discussions, idea communications, and research promotions.
Date
Session A on 14:00 – 15:00, Attend in Whova
Session B on 1:00 – 2:00, Attend in Whova
Current time in :
