Explore the latest research from Facebook

All Publications

January 5, 2021 Nirbhay Modhe, Prithvijit Chattopadhyay, Mohit Sharma, Abhishek Das, Devi Parikh, Dhruv Batra, Ramakrishna Vedantam
Paper

IR-VIC: Unsupervised Discovery of Sub-goals for Transfer in RL

We propose a novel framework to identify subgoals useful for exploration in sequential decision making tasks under partial observability.
Paper
January 1, 2021 Mahmoud Assran, Michael Rabbat
Paper

Asynchronous Gradient-Push

We consider a multi-agent framework for distributed optimization where each agent has access to a local smooth strongly convex function, and the collective goal is to achieve consensus on the parameters that minimize the sum of the agents’ local functions. We propose an algorithm wherein each agent operates asynchronously and independently of the other agents.
Paper
October 26, 2020 Yangyang Shi, Yongqiang Wang, Chunyang Wu, Christian Fuegen, Frank Zhang, Duc Le, Ching-Feng Yeh, Michael L. Seltzer
Paper

Weak-Attention Suppression For Transformer Based Speech Recognition

In this paper, we propose Weak-Attention Suppression (WAS), a method that dynamically induces sparsity in attention probabilities. We demonstrate that WAS leads to consistent Word Error Rate (WER) improvement over strong transformer baselines.
Paper
September 22, 2020 Michael Bailey, Drew Johnston, Theresa Kuchler, Dominic Russel, Bogdan State, Johannes Stroebel
Paper

The Determinants of Social Connectedness in Europe

We use aggregated data from Facebook to study the structure of social networks across European regions.
Paper
September 14, 2020 Hugh Leather, Chris Cummins
Paper

Machine Learning in Compilers: Past, Present, and Future

In this paper we will give a retrospective of machine learning in compiler optimisation from its earliest inception, through some of the works that set themselves apart, to today’s deep learning, finishing with our vision of the field’s future. Index Terms—machine learning, compilers.
Paper
September 7, 2020 Devi Parikh, Larry Zitnick
Paper

Exploring Crowd Co-creation Scenarios for Sketches

As a first step towards studying the ability of human crowds and machines to effectively co-create, we explore several human-only collaborative co-creation scenarios. The goal in each scenario is to create a digital sketch using a simple web interface.
Paper
September 7, 2020 X. Alice Li, Devi Parikh
Paper

Lemotif: An Affective Visual Journal Using Deep Neural Networks

We present Lemotif, an integrated natural language processing and image generation system that uses machine learning to (1) parse a text-based input journal entry describing the user’s day for salient themes and emotions and (2) visualize the detected themes and emotions in creative and appealing image motifs.
Paper
September 7, 2020 Devi Parikh
Paper

Predicting A Creator’s Preferences In, and From, Interactive Generative Art

We train machine learning models to predict a subset of preferences from the rest. We find that preferences in the generative art form cannot predict preferences in other walks of life better than chance (and vice versa). However, preferences within the generative art form are reliably predictive of each other.
Paper
September 7, 2020 Gunjan Aggarwal, Devi Parikh
Paper

Neuro-Symbolic Generative Art: A Preliminary Study

As a preliminary study, we train a generative deep neural network on samples from the symbolic approach. We demonstrate through human studies that subjects find the final artifacts and the creation process using our neurosymbolic approach to be more creative than the symbolic approach 61% and 82% of the time respectively.
Paper
September 7, 2020 Purva Tendulkar, Abhishek Das, Aniruddha Kembhavi, Devi Parikh
Paper

Feel The Music: Automatically Generating A Dance For An Input Song

We present a general computational approach that enables a machine to generate a dance for any input music. We encode intuitive, flexible heuristics for what a ‘good’ dance is: the structure of the dance should align with the structure of the music.
Paper