For each paper being presented at the workshop, we will host (1) the pre-recorded presentation from SlidesLive, (2) a RocketChat chatroom for text-based discussion, and (3) a Zoom meeting room at the main ICLR virtual workshop site. From each paper's landing page (which you can access by clicking on the title of the relevant paper below), you can find the Slideslive video for offline viewing.
You can see the schedule at Schedule, during which authors will join the Zoom Webinar in the main page to allow you to ask them questions face-to-face.
Invited Speakers
| Title | Authors | Paper | Slides |
|---|---|---|---|
| Practical Machine Learning for Developing Countries: Lessons and Reflections (Invited) | Charity Wayua | Slide | |
| Lessons learned from practicing and teaching data science in Latin America (Invited) | John Alexis Guerra Gómez | ||
| Learning with less resources - minimizing the labeling effort (Invited) | Negar Rouzmateh | Slide |
Contributed Oral Presentations 1 (10:50 AM - 12:35 PM EDT, New York Time)
| Title | Authors | Paper | Slides |
|---|---|---|---|
| Beyond Good Intentions - Data Sharing in and for Africa (Oral) | Kehinde Aruleba University of the Witwatersrand); Abeba Birhane (UCD); Sara Kingsley (CMU)*; George Obaido (University of the Witwatersrand, Johannesburg); Sekou Remy (IBM Research); Swathi Sadagopan (*) | Slide | |
| Measuring Changes in Poverty with Deep Learning and Satellite Imagery (Oral) | Lukas Kondmann (German Aerospace Center)*; Xiaoxiang Zhu (Technical University of Munich (TUM); German Aerospace Center (DLR)) | Paper | Slide |
| Rigging the Lottery - Making All Tickets Winners (Oral) | Utku Evci (Google AI)*; Erich Elsen (DeepMind); Pablo Samuel Castro (Google); Jacob Menick (DeepMind); Trevor Gale (Google Brain) | Paper | Slide |
| Distributed Learning - Sequential Decision Making in Resource-Constrained Environments (Oral) | Udari Madhushani (Princeton University)*; Naomi Leonard (Princeton University) | Paper | Slide |
| Distant Supervision and Noisy Label Learning for Low Resource Named Entity Recognition - A Study on Hausa and Yorùbá (Oral) | David Adelani (Saarland University); Michael Hedderich (Spoken Language Systems (LSV), Saarland University, Saarland Informatics Campus)*; Dawei Zhu (Saarland University); Esther van den Berg (Universität Heidelberg); Dietrich Klakow (Saarland University) | Paper | Slide |
Contributed Oral Presentations 2 (02:20 PM - 03:55 PM EDT, New York Time)
| Title | Authors | Paper | Slides |
|---|---|---|---|
| Streamlining Tensor and Network Pruning in PyTorch (Oral) | Michela Paganini (Facebook); Jessica Forde (Brown University)* | Paper | Slide |
| Convolutional Neural Network for ECG-based Virtual Pathology Stethoscope Tracking in Patient Heart Auscultation (Oral) | Haben Yhdego (Old Dominion University)* | Paper | Slide |
| Spanish pre-trained BERT model and evaluation data (Oral) | José Cañete (Universidad de Chile); Gabriel Chaperon (Universidad de Chile)*; Rodrigo Fuentes (Universidad de Chile); Jorge Pérez (universidad de Chile) | Paper | Slide |
| LOW RESOURCE BREAST CANCER DETECTION WITH MAMMOGRAMS (Oral) | Sara Ebrahim (AIMS Rwanda)*; Kris Sankaran (Mila) | Paper | Slide |
| Predicting Legal Proceedings Status: an Approach Based on Sequential Texts (Oral) | Felipe Polo (University of São Paulo)*, Itamar Ciochetti (Tikal Tech), Emerson Bertolo (Tikal Tech) | Paper | Slide |
Poster Session 1 (12:35 PM - 1:35 PM EDT, New York Time)
| Title | Authors | Paper | Slides |
|---|---|---|---|
| On Iterative Neural Network Pruning, Reinitialization, and the Similarity of Masks (Poster) | Michela Paganini (Facebook); Jessica Forde (Brown University)* | Paper | Slide |
| BiPedalNet: Binarized Neural Networks for Resource-Constrained On-Device Gait Identification (Poster) | Daniel Jeffrey Wu (Stanford University)*; Avoy Datta (Stanford University); Vinay Uday Prabhu (UnifyID Inc) | Paper | Slide |
| Afro-MNIST: Synthetic generation of MNIST-style datasets for low-resource languages (Poster) | Daniel Jeffrey Wu (Stanford University)*; Andrew Chuming Yang (Stanford University); Vinay Uday Prabhu (UnifyID Inc) | Paper | Slide |
| Deep Learning Mobile Application Towards Malaria Diagnosis (Poster) | Martha Shaka (The University of Dodoma)*; Frederick Apina (University of Dodoma) | Paper | Slide |
| Developing Machine Learning Competence in Africa in the Francophone Sahel Region (Poster) | Michael Leventhal (RobotsMali)*; Haby Sanou Diarra (Ministère de l'Enseignement Supérieur et de la Recherche Scientifique) | Paper | Slide |
| Lip Reading by Leveraging Hahn Convolutional Neural Network in Low-Resourced Environments (Poster) | Hicham Hammouchi (International University of Rabat)* | Paper | Slide |
| Location Information and Racial Biases in Credit Scoring (Poster) | Ramon Vilarino (Experian DataLab LatAm)*; Renato Vicente (Experian DataLab LatAm and University of São Paulo) | Paper | Slide |
| Bilateral Trade Modelling with Graph Neural Networks (Poster) | Kobby Panford-Quainoo (African Institute for Mathematical Sciences)* | Paper | Slide |
| Classification and Detection of Plasmodium Vivax Infected Cells in Blood Smears Images (Poster) | Erick Diaz (Universidad San Carlos de Guatemala)*; Jorge Balsells (Universidad San Carlos de Guatemala); Allan Orozco (University of Costa Rica) | Paper | Slide |
| Artificial Intelligence for Global Health: Learning From a Decade of Digital Transformation in Health Care (Poster) | Varoon Mathur (AI Now Institute)*; Judy Gichoya (Indiana University); Saptarshi Purkayastha (Indiana University Purdue University Indianapolis) | Paper | Slide |
Poster Session 2 (04:30 PM - 05:30 PM EDT, New York Time)
| Title | Authors | Paper | Slides |
|---|---|---|---|
| Modeling, Visualization, and Analysis of African Innovation Performance (Poster) | Muhammad Omer (Baylasan for Innovation)*; Moayad Elamin (Baylasan for Innovation); Ammar Khairi (University of Khartoum); Rami Ahmed (Baylasan for Innovation) | Paper | Slide |
| GRADIENT AND MAGNITUDE-BASED PRUNING FOR SPARSE DEEP NEURAL NETWORKS (Poster) | Kaleab Belay (Addis Ababa Institute of Technology)*; Naol Negassa (FARIS Technology Institute) | Paper | Slide |
| Transition Based Dependency Parser For Amharic Language Using Deep Learning (Poster) | Mizanu Degu (JImma university)*; Million Meshesha (Addis Ababa University) | Paper | Slide |
| HyperEmbed - Tradeoffs between Resources and Performance in NLP tasks with Hyperdimensional Computing enabled embedding of n-gram statistics (Poster) | kumar shridhar (TU Kaiserslautern)*; Pedro Alonso (Lulea Technical University); Denis Kleyko (Lulea University of Technology); Marcus Liwicki (University of Fribourg); Evgeny Osipov (Lulea University of Technology) | Paper | Slide |
| Data Parallelism in Training Sparse Neural Networks (Poster) | Namhoon Lee (University of Oxford)*; Philip Torr (University of Oxford); Martin Jaggi (EPFL) | Paper | Slide |
| Class Agnostic Object Segmentation using Few-Shot Weakly Supervised Guidance (Poster) | Mennatullah Siam (University of Alberta)*; Naren Doraiswamy (Indian Institute of Science (IISc)); Boris Oreshkin (Element AI); Hengshuai Yao (Huawei Technologies); Martin Jagersand (University of Alberta) | Paper | Slide |
| EXPLOITING GENERAL PURPOSE SEQUENCE REPRESENTATIONS FOR LOW RESOURCE NEURAL MACHINE TRANSLATION (Poster) | Hou Jeung Han (Samsung Research)*; Sathish Indurthi (Samsung Research); Sangha Kim (Samsung Research) | Paper | Slide |
| Selection via Proxy: Increasing the Computational Efficiency of Deep Active Learning (Poster) | Cody Coleman (Stanford University)*; Christopher Yeh (Stanford University); Stephen Mussmann (Stanford University); Baharan Mirzasoleiman (Stanford University); Peter Bailis (Stanford University); Percy Liang (Stanford University); Jure Leskovec (Stanford University); Matei Zaharia (Stanford and Databricks) | Paper | Slide |
| Practical Parallel Data Collection for Low-Resource Languages via Images (Poster) | Aman Madaan (Carnegie Mellon University)*; Shruti Rijhwani (Carnegie Mellon University); Antonios Anastasopoulos (Carnegie Mellon University); Yiming Yang (Carnegie Mellon University) | Paper | Slide |
| A Data and Compute Efficient Design for Limited-Resources Deep Learning (Poster) | Merghaney Mohammed (The African Institute for Mathematical Sciences); Gabriele Cesa (Qualcomm AI Research, University of Amsterdam)*; Taco Cohen (Qualcomm AI Research); Max Welling (Qualcomm AI Research) | Paper | Slide |