{"id":652389,"date":"2020-04-24T15:10:56","date_gmt":"2020-04-24T22:10:56","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-group&p=652389"},"modified":"2024-03-06T09:37:45","modified_gmt":"2024-03-06T17:37:45","slug":"microsoft-research-mila","status":"publish","type":"msr-group","link":"https:\/\/www.microsoft.com\/en-us\/research\/collaboration\/microsoft-research-mila\/","title":{"rendered":"Microsoft Research & Mila"},"content":{"rendered":"
\n\t
\n\t\t
\n\t\t\t\"photo\t\t<\/div>\n\t\t\n\t\t
\n\t\t\t\n\t\t\t
\n\t\t\t\t\n\t\t\t\t
\n\t\t\t\t\t\n\t\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t\n\n

Microsoft Research & Mila<\/h1>\n\n\t\t\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t<\/div>\n\t\t<\/div>\n\t<\/div>\n<\/section>\n\n\n\n\n\n

Partnership<\/h2>\n\n\n\n
\n

Microsoft Research has been a partner of Mila<\/a>\u2019s (Montreal Institute of Learning Algorithms) since its inception, forging strong collaborations between its researchers to advance state-of-the-art deep learning research. To cultivate these collaborations, we administer a variety of programs that provide resources and support to the students<\/a> and faculty<\/a> at Mila.<\/p>\n<\/div>

\"Mila<\/figure><\/div>\n\n\n\n
\n
\n
\"Presentation<\/figure>\n<\/div>\n\n\n\n
\n
\"Susan<\/figure>\n<\/div>\n\n\n\n
\n
\"Yoshua<\/figure>\n<\/div>\n<\/div>\n\n\n\n\n\n

Mila faculty engagement<\/h2>\n\n\n\n
<\/div>\n\n\n\n

Microsoft Research & Mila Call for Proposals<\/h3>\n\n\n\n

Semi-annually, Microsoft Research conducts a call for research proposals with the faculty at Mila to promote machine learning research collaborations between the Microsoft Research and Mila. The call for proposals aims to fund ambitious collaborative projects that have the potential to shape the future of artificial intelligence.<\/p>\n\n\n\n

Please see below a list of selected proposals funded by Microsoft Research during the most recent call for proposals. The next round of call for proposals will take place during May-June, 2020.<\/p>\n\n\n\n

<\/div>\n\n\n\n

March 2020<\/h4>\n\n\n\n\n\n

Devon Hjelm (MSR Montreal), Mihai Jalobeanu (MSR AI), Yonatan Bisk (MSR AI), Liam Paull (Mila), Florian Golemo (Mila), Aaron Courville (Mila)<\/em><\/p>\n\n\n\n

In this project we explore the role of interaction on revealing underlying properties of the world, notably those properties not easily discernible through visual observation alone.\u202f Specifically, we train models by curiosity and interaction within robotic control, as this setting allows us to concretely design experiments over which we can reasonably make progress on questions that relate interaction with representation learning. Our experimental setting will focus on learning invisible properties and affordances through interaction both in simulation and on real robot platforms.<\/p>\n\n\n\n\n\n

R\u00e9mi Tachet Des Combes (MSR Montreal), Pierre-Luc Bacon (Mila), Yoshua Bengio (Mila), Romain Laroche (MSR Montreal)<\/em><\/p>\n\n\n\n

We aim to explore the concept of parsimony bias<\/em> (PB) in reinforcement learning. The PB states that agents should reason about a small number of concepts from the current state (state-space PB), and over a small number of meaningful time steps in its trajectory (temporal PB). We hope to demonstrate that an agent trained using the PB has strong credit assignment<\/em> and planning<\/em> capabilities and can adapt rapidly to new environments.<\/p>\n\n\n\n\n\n

Will Hamilton (Mila\/McGill), Xingdi Yuan (MSR Montreal), Marc-Alexandre Cote (MSR Montreal), Romain Laroche (MSR Montreal), Adam Trischler (MSR Montreal)<\/em><\/p>\n\n\n\n

The ability to learn and generalize from small amounts of data is a fundamental aspect of human intelligence. In the context of machine learning, this ability is often studied under the umbrella of “meta learning”, in which models are trained to enable fast adaption to new tasks. Our project will explore a new approach to meta learning based on the concept of logical rule induction, where we will develop learning approaches that seek to extract the shared logical structure between related tasks.<\/p>\n\n\n\n\n\n

Jian Tang (Mila), Chenyan Xiong (MSR AI)<\/em><\/p>\n\n\n\n

Relational Reasoning, a key ingredient for System II reasoning, is important in a variety of complicated tasks such as question answering, image understanding, and knowledge graph completion. This problem has been extensively studied in traditional statistical relational learning community and recent growing graph representation learning community in an independent way. In this project, we aim to combine the advantages of both worlds and foster the collaboration between the two different communities.<\/p>\n\n\n\n\n\n

Shehzaad Dhuliawala (MSR Montreal), Kaheer Suleman (MSR Montreal), Siva Reddy (Mila\/McGill) <\/em><\/p>\n\n\n\n

In this proposal, we plan to develop\u202fnext-generation search engines which have the ability to answer conversational questions. The main challenge is building a joint inference model that understands conversations, perform information retrieval and read documents to answer questions.<\/p>\n\n\n\n\n\n

Xue Liu (Mila), Fernando Diaz (MSR Montreal)<\/em><\/p>\n\n\n\n

Two-sided recommendation systems bring together two populations such as buyers and sellers, listeners and musicians, and employers and job seekers.  While many existing recommendation systems have focused on optimizing metrics such as user satisfaction, they often do not incorporate the satisfaction of content producers.  As a result, the platforms become less attractive and content quality can suffer.  Moreover, even when multiple objectives are considered, they can result in unfair allocation of exposure for content from certain groups.  This project will develop models for multi-objective, fair recommendation.<\/p>\n\n\n\n\n\n

Carolyne Pelletier (Mila), Sandeep Subramanian (Mila), Samira Shabanian (MSR Montreal), Yoshua Bengio (Mila)<\/em><\/p>\n\n\n\n

This project investigates ways in which Gender Pronoun Bias (a type of implicit bias) can be mitigated when deploying natural language processing systems. This is important because, much like how humans incorporate their own biases into the text they write, language understanding models like BERT have been shown to propagate these types of biases that exist in their training data to downstream tasks. First, we propose a modification to BERT\u2019s pre-training task in order to mitigate for Gender Pronoun Bias. Second, we propose to fine-tune on an augmented dataset that aims to reduce Gender Pronoun Bias in tasks like Masked Language Modeling. Finally, we explore the possibility of training a model to identify and correct for Gender Pronoun Bias at the sentence level by using a pre-trained language understanding model like BERT and fine-tuning it on the Gender Pronoun Bias dataset which is being collected at Mila with BiaslyAI. This could be used as an end-user application or used to correct for Gender Pronoun Bias in training data.<\/p>\n\n\n\n\n\n

<\/div>\n\n\n\n

May 2019<\/h4>\n\n\n\n\n\n

Alessandro Sordoni (MSR Montreal) and Professor Timothy O\u2019Donnell (Mila)<\/em><\/p>\n\n\n\n\n\n

Marc-Alexandre Cote (MSR Montreal), Eric Yuan (MSR Montreal), Professor William Hamilton (Mila) and Professor Jian Tang (Mila)<\/em><\/p>\n\n\n\n\n\n

Remi Tachet Des Combes (MSR Montreal) and Professor Ioannis Mitliagkas (Mila)<\/em><\/p>\n\n\n\n\n\n

<\/p>\n\n\n\n

MSR Collaborating Faculty Members at Mila<\/h3>\n\n\n\n