Date & Time: Sunday August 23, 2020 Venue: Zoom, join via this link: https://kddvirtual2020.vfairs.com/en/chat?cid=41106

• Part A: 8 AM - 12 PM PST || 4 PM onwards UK || 8:30 PM onwards India || 11PM onwards Beijing

• Part B: 1 PM - 5 PM PST || 9 PM onwards UK || 1:30 AM onwards India || 4 AM onwards Beijing

Part A: Recommendations in a Marketplace

Multi-sided marketplaces are steadily emerging as viable business models in many applications (e.g. Amazon, AirBnb, YouTube), wherein the platforms have customers not only on the demand side (e.g. users), but also on the supply side (e.g. retailer). In the first part of the tutorial, we consider a number of research problems which need to be addressed when developing a search & recommendation framework powering a multi-stakeholder marketplace. We highlight the importance of a multi-objective ranking/recommendation, discuss different ways in which stakeholders specify their objectives, discuss user specific characteristics (e.g. user receptivity) which could be leveraged when developing joint optimization modules and finally present a number of real world case-studies of such multi-stakeholder search and recommendation systems.

Outline of Tutorial

1. Part I: Introduction to Marketplaces [slides]

   1. (Quick) Overview of traditional RecSys approaches

   2. Introduction to Marketplace

   3. Types & examples of marketplaces

   4. Recommendation in a marketplace
      

2. Part II: Optimization Objectives in a Marketplace [slides]

   1. Case studies I - VII: Stakeholders & their objectives

   2. Families of objectives

   3. Interplay between Objectives: Correlation + Supporting vs Competing objectives
      

3. Part III: Methods for Multi-Objective Ranking & Recommendations [slides]

   1. Pareto optimality

   2. Scalarization approaches

   3. Multi-task Learning for recommendations

   4. Multi-objective bandits for ranking

   5. Multi-objective Reinforcement Learning
      

4. Part IV: Leveraging Consumer, Supplier & Content Understanding [slides]

   1. Consumption diversity of users

   2. Leveraging User intents

   3. Quantifying and estimating user receptivity

   4. Diversity across suppliers

   5. Personalizing Reward function

   6. Query Understanding
      

5. Part V: Industrial Applications [slides]

Tutorial Schedule (Part A)

(PST time zone)

08:00 - 08:10: Welcome + Introduction

08:10 - 08:30: Part I: Introduction to Marketplaces

08:30 - 09:00: Part II: Optimization Objectives in a Marketplace

09:00 - 09:30: Part III: Methods for Multi-Objective Recommendations

09:30 - 10:00: Break

10:00 - 10:30: Part III: Methods for Multi-Objective Recommendations

10:30 - 11:10: Part IV: Leveraging Consumer, Supplier & Content Understanding

11:10 - 11:40: Part V: Industrial Applications

11:40 - 11:50: Questions & Discussions

Part B: Automated Recommender System

As the recommendation tasks are getting more diverse and the recommending models are growing more complicated, it is increasingly challenging to develop a proper recommendation system that can adapt well to a new recommendation task. In this tutorial, we will focus on how automated machine learning (AutoML) techniques can benefit the design and usage of recommendation systems. Specifically, we will start from a full scope describing what can be automated for recommendation systems. Then, we will elaborate more on three important topics under such a scope, i.e., feature engineering, hyperparameter optimization/neural architecture search, and algorithm selection. The core issues and recent works under these topics will be introduced, summarized, and discussed. Finally, we will finalize the tutor with conclusions and some future directions.

Outline of Tutorial

1. What is Automated machine learning (AutoML) - A retrospective view

2. Recommender System: Basic and Why AutoML is Needed?

3. Recent Advances in Automated Recommender System

4. Automated Graph Neural Network for Recommender System

5. Automated Knowledge Graph Embedding

Slides and more information for Part B: https://github.com/AutoML-4Paradigm/KDD-2020-tutor