AI Research Graph Series: Towards Causal Representation Learning

A comprehensive graph mapping of knowledge areas and research paper presentations related to the new paper "Towards Causal Representation Learning" led by Yoshua Bengio and Bernhard Schölkopf.

By
Crossminds
on
April 15, 2021
Category:
Research Spotlights

A research team led by Turing Award winner Yoshua Bengio and MPII director Bernhard Schölkopf recently published a paper "Towards Causal Representation Learning" that reviews fundamental concepts of causal inference and discusses how causality can contribute to modern machine learning research. The paper co-authors also include Francesco Locatello, Stefan Bauer, Nan Rosemary Ke, Nal Kalchbrenner, and Anirudh Goyal from Max-Planck Institute for Intelligent Systems, ETH Zurich, Google Research Amsterdam, Mila and the University of Montreal. Built on Crossminds AI knowledge graph, this blog provides a comprehensive mapping of key knowledge areas and related research paper presentations derived from this new publication.

For an overview of "causal representation learning", check out Yoshua Bengio's talk in 2020:

Towards Causal Representation Learning

Top 10 Related Paper Presentations

We first create a mapping of key research papers, research areas, as well as their connections from the core paper. Then we rank all research papers with video based on three criteria: 1) relevance of knowledge area; 2) research impacts (i.e., number of citations); and 3) research recency (year published). The graph image below demonstrates a paper-knowledge mapping for the top 10 research papers with video based on an aggregate score calculated from the three criteria.

Click to view video presentations of the top papers.

Building Machines That Learn and Think Like People
Lake et al., 2017
Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems
Levine, 2020
Counterfactual Fairness
Kusner et al., 2018
An Analysis of the Adaptation Speed of Causal Models
Le Priol et al., 2020
Algorithmic recourse under imperfect causal knowledge: a probabilistic approach
Karimi et al., 2020
Language Models are Few-Shot Learners
Brown et al., 2020
Semi-Supervised Learning, Causality and the Conditional Cluster Assumption
von Kügelgen et al., 2020
A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms
Bengio et al., 2019
Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning
Grill et al., 2020

Check out our curated playlist for all related research videos on Causal Representation Learning.

Top 10 Related Paper Presentations by Knowledge Area

The graph image below demonstrates a paper-knowledge mapping for the top 10 research papers with video with the closest connection to the key knowledge area of causal inference.

Click to view video presentations of the top papers:

Learning Independent Causal Mechanisms
Parascandolo et al., 2018
Representation Learning: A Review and New Perspectives
Bengio et al., 2014
Discovering Causal Signals in Images
Lopez-Paz et al., 2017

More video presentations of top paper in the area of causal inference:

Top 10 Paper Presentations by Research Impacts

The graph image below demonstrates a paper-knowledge mapping for the top 10 research papers with video that have the highest citations.

Click to view video presentations of the top papers:

CLEVRER: CoLlision Events for Video REpresentation and Reasoning
Yi et al., 2020
Object-Centric Learning with Slot Attention
Locatello et al., 2020
Self-Supervised Learning of Video-Induced Visual Invariances
Tschannen et al., 2020

More video presentations of papers with the highest citations:

Top 10 Related Paper Presentations by Recency

The graph image below demonstrates a paper-knowledge mapping for the 10 newest research papers with video related to this core paper.

Click to view video presentations of the top papers:

A Simple Framework for Contrastive Learning of Visual Representations
Chen et al., 2020
Hidden Markov Nonlinear ICA: Unsupervised Learning from Nonstationary Time Series
Hälvä et al., 2020
Learning to Simulate Complex Physics with Graph Networks
Sanchez-Gonzalez et al., 2020

More video presentations of new papers published:

View more Knowledge Graph-Indexed AI research videos at Crossminds:

Crossminds.ai Knowledge Graph-Indexed AI research videos

Install "Crossminds Papers with Video" Chrome extension to instantly find research videos for AI papers on arXiv:

Crossminds Papers with Videos: Find research videos for AI research papers on arXiv While browsing arXiv.org, Crossminds papers with video extension instantly help you find research videos related to each paper. Powered by Crossminds.ai research video platform, this free extension currently covers over 6000 videos in artificial intelligence, machine learning, deep learning, computer vision, natural language processing (NLP), robotics and many other topics in the computer science domain.



Sign up with Crossminds.ai to get personalized recommendations of the latest tech research videos!

Join Crossminds Now!
Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form
Tags:
No items found.
Crossminds

Crossminds.ai is a personalized research video platform for tech professionals. We aim to empower your growth with the latest and most relevant research, industry, and career updates.