LERI 2023
Learning and Evaluating Recommendations with Impressions 2023

Table of Contents

• Workshop on Learning and Evaluating Recommendations with Impressions (LERI 2023) 1-8
  Maurizio Ferrari Dacrema, Pablo Castells, Justin Basilico, Paolo Cremonesi
  Summary: There were 11 papers submitted for peer-review to this workshop. Out of these, 7 papers were accepted for this volume, 2 as regular papers and 5 as short papers.

Keynote

• Recommendation Modeling with Impression Data at Netflix
  Jiangwei Pan

Session 1

• Impression-Informed Multi-Behavior Recommender System: A Hierarchical Graph Attention Approach 9-21
  Dong Li, Divya Bhargavi, Vidya Sagar Ravipati
• Characterizing Impression-Aware Recommender Systems 22-33
  Fernando Benjamín Pérez Maurera, Maurizio Ferrari Dacrema, Pablo Castells, Paolo Cremonesi
• Effects of Human-curated Content on Diversity in PSM: ARD-M Dataset (short paper) 34-40
  Marcel Hauck, Ahtsham Manzoor, Sven Pagel

Session 2

• Formulating Video Watch Success Signals for Recommendations on Short Video Platforms (short paper) 41-48
  Srijan Saket, Sai Baba Reddy Velugoti, Rishabh Mehrotra
• Offline Evaluation using Interactions to Decide Cross-selling Recommendations Algorithm for Online Food Delivery (short paper) 49-54
  Manchit Madan
• Contextual Position Bias Estimation Using a Single Stochastic Logging Policy (short paper) 55-61
  Giuseppe Di Benedetto, Alexander Buchholz, Ben London, Matej Jakimov, Yannik Stein, Jan Malte Lichtenberg, Vito Bellini, Matteo Ruffini, Thorsten Joachims
• Incorporating Impressions to Graph-Based Recommenders (short paper) 62-67
  Fernando Benjamín Pérez Maurera, Maurizio Ferrari Dacrema, Pablo Castells, Paolo Cremonesi

Panel discussion

• Panel discussion moderated by Paolo Cremonesi:
  Jiangwei Pan, Arnab Bhadury, Srijan Saket