Panel: Causality in search and recommendation systems

Channel:
Microsoft Research
Subscribers:
344,000
Published on ● Video Link: https://www.youtube.com/watch?v=XI4M3SwNlE0


Duration: 36:55
569 views
14

Moderator: Emre Kiciman, Senior Principal Researcher, Microsoft Research Redmond
Panelists:
Amit Sharma, Senior Researcher, Microsoft Research India
Dean Eckles, Associate Professor, Massachusetts Institute of Technology
Eren Manavoglu, Vice President, Search Ads, Microsoft
Yixin Wang, LSA Collegiate Fellow, University of Michigan

With the scale of search and recommendation, real-time robust and explainable decision-making is at the heart of search and recommendation systems that work robustly even as the user-base changes, new content appears, and topics rise and fall in popularity. These changes can lead to brittle models that fail to capture knowledge about the domain, for example, how people search or which trends are expected to be related based on external knowledge. In addition, since user feedback is only available for items that were shown by the current system, the training data and labels are skewed towards items that were recommended previously, leading to unintended feedback loops. In this talk, we discuss advances in causality that increase model robustness against anchoring too strongly to past observational data. We also speculate on the future of more robust and explainable models as we advance learning methods that go beyond correlation to causation. 

Learn more about the 2021 Microsoft Research Summit: https://Aka.ms/researchsummit



Other Videos By Microsoft Research


2022-01-24Research talk: Challenges in multi-tenant graph representation learning for recommendation problems
2022-01-24Research talk: IGLU: Interactive grounded language understanding in a collaborative environment
2022-01-24Research talk: Is phrase retrieval all we need?
2022-01-24Research talk: DeepXML: A deep extreme classification framework for recommending millions of items
2022-01-24Talk series: Developer productivity
2022-01-24Fireside Conversation Series: Building an equitable environment for hybrid work
2022-01-24Practical tips for productivity & wellbeing: Transitioning across the work-life boundary
2022-01-24Research talk: Attentive knowledge-aware graph neural networks for recommendation
2022-01-24Practical tips for productivity & wellbeing: Lessons from COVID-19 around time management
2022-01-24Tutorial, Research talk, and Q&A: ElectionGuard: Enabling voters to verify election integrity
2022-01-24Panel: Causality in search and recommendation systems
2022-01-20Unsupervised Speech Enhancement
2022-01-20Developing a Brain-Computer Interface Based on Visual Imagery
2022-01-04Panel: Theory Research in Big Data Era
2022-01-04Talk: Sequential Search Problems Beyond The Pandora Box Setting
2022-01-04Recap video of 2021 MSR Asia Theory Workshop (Short version)
2022-01-04Talk: The implicit bias of optimization algorithms in deep learning
2022-01-04Talk: Coresets for Clustering with Missing Values
2022-01-04MSR Asia Theory Center Introduction
2022-01-04Inauguration Ceremony of MSR Asia Theory Center Opening Speech from Tie-Yan Liu
2022-01-04Talk: Batch Online Learning and Decision


Tags:
Search & information retrieval
Microsoft Search
Productivity
search
recommendation
future of search
microsoft research summit