Timezone: »

Machine Learning for the Developing World (ML4D): Challenges and Risks
Maria De-Arteaga · Amanda Coston · Tejumade Afonja

Fri Dec 13 08:00 AM -- 06:00 PM (PST) @ West 121 + 122
Event URL: https://sites.google.com/view/ml4d/home »

As the use of machine learning becomes ubiquitous, there is growing interest in understanding how machine learning can be used to tackle global development challenges. The possibilities are vast, and it is important that we explore the potential benefits of such technologies, which has driven the agenda of the ML4D workshop in the past. However, there is a risk that technology optimism and a categorization of ML4D research as inherently “social good” may result in initiatives failing to account for unintended harms or deviating scarce funds towards initiatives that appear exciting but have no demonstrated effect. Machine learning technologies deployed in developing regions have often been created for different contexts and are trained with data that is not representative of the new deployment setting. Most concerning of all, companies sometimes make the deliberate choice to deploy new technologies in countries with little regulation in order to experiment.

This year’s program will focus on the challenges and risks that arise when deploying machine learning in developing regions. This one-day workshop will bring together a diverse set of participants from across the globe to discuss essential elements for ensuring ML4D research moves forward in a responsible and ethical manner. Attendees will learn about potential unintended harms that may result from ML4D solutions, technical challenges that currently prevent the effective use of machine learning in vast regions of the world, and lessons that may be learned from other fields.

The workshop will include invited talks, a poster session of accepted papers and panel discussions. We welcome paper submissions featuring novel machine learning research that characterizes or tackle challenges of ML4D, empirical papers that reveal unintended harms of machine learning technology in developing regions, and discussion papers that examine the current state of the art of ML4D and propose paths forward.

Fri 8:30 a.m. - 8:45 a.m. [iCal]
Opening Remarks (Talk)
Fri 8:45 a.m. - 9:15 a.m. [iCal]

When we deploy machine learning models, what are the known scenarios in which the technology does not work? In this talk, we will go over the many potential blindspots in ML deployments, and how, as a fundamentally narrow and limited technology, we need to be careful to communicate, evaluate for and directly address these risks in a way that protects users and reinforces developer accountability.

Deborah Raji
Fri 9:15 a.m. - 9:45 a.m. [iCal]

As algorithmic systems become an ever more integral aspect of much of the social sphere, their application for “social good” has also increased. Western-made AI is deployed throughout the African continent with great enthusiasm and little regulation or critical engagement, in a manner that resembles past colonial conquests. This talk explores some of the critical and ethical questions that need to be raised with the “digitization” of the African continent and the use of AI for “social good”.

Abeba Birhane
Fri 9:45 a.m. - 10:30 a.m. [iCal]
Coffee Break (Break)
Fri 10:30 a.m. - 11:00 a.m. [iCal]

Since the turn of the millennium, the interdisciplinary field of information & communication technologies and development (ICTD) has explored how digital technologies could contribute to international socio-economic development. The associated research community includes both techno-utopians who imagine that just about any problem can be solved with the right application of technology, as well as extreme skeptics wary of any attempts at intervention. Debates continue, but in this talk, I will attempt to summarize some of the expressed consensus in ICTD -- things that not everyone necessarily believes, but will at least pay lip service to. I will also discuss what I call technology's "Law of Amplification," which reconciles some of the differing opinions in ICTD and also offers guidance for how machine learning can have real-world impact.

Kentaro Toyama
Fri 11:00 a.m. - 12:00 p.m. [iCal]
Poster session
Michael Melese Woldeyohannis, Bernardt Duvenhage, Nyamos Waigama, Asaye Bir Senay, Claire Babirye, Tensaye yibeltal Ayalew, Kelechi Ogueji, Vinay Prabhu, Prabu Ravindran, Olamilekan Wahab, chukwunonso H Nwokoye, Paul Duckworth, Hafte Abera, Abebe Mideksa, Loubna Benabbou, Anugraha Sinha, Ivan Kiskin, Robert Soden, Tupokigwe Isagah, Rehema Mwawado, Yimer Hussien, Bryan Wilder, Daniel Omeiza, Sunayana Rane, Richard Mgaya, Samsun Knight, Jessenia Gonzalez Villarreal, Eyob Beyene, Monika Obrocka Tulinska, Luis Fernando Cantu Diaz de Leon, Joseph Aro, Michael T Smith, Michael Famoroti, Praneeth Vepakomma, Ramesh Raskar, Debjani Bhowmick, Chukwunonso H Nwokoye, Alejandro Noriega Campero, Hope Mbelwa, Anusua Trivedi
Fri 12:00 p.m. - 2:00 p.m. [iCal]
Lunch (Break)
Fri 2:00 p.m. - 2:15 p.m. [iCal]

Data accessibility, including the ability to make data shareable, is important for knowledge creation, scientific learning, and progress. In many locations, including Africa, data is a central engine for economic growth and there have been recent calls to increase data access and sharability by organizations including the UN, AU, and many others. Discussions around data inaccessibility, however, revolve around lack of resources, human capital, and advanced technologies, hiding the complex and dynamic data ecosystem and intricate challenges faced in sharing data across the continent. In this piece, we shed light on these overlooked issues around data inaccessibility and sharing within the continent using a storytelling perspective. Using the perspectives of multiple stakeholders, we surface tensions and trade-offs that are that are inadequately captured in current discussions around data accessibility in the continent.

Sekou Remy
Fri 2:15 p.m. - 2:30 p.m. [iCal]

While applications of AI is now becoming more common in fields like retail and marketing, application of AI in solving problems related to developing countries is still an emerging topic. Specially, AI applications in resource-poor settings remains relatively nascent. There is a huge scope of AI being used in such settings. For example, researchers have started exploring AI applications to reduce poverty and deliver a broad range of critical public services. However, despite many promising use cases, there are many dataset related challenges that one has to overcome in such projects. These challenges often take the form of missing data, incorrectly collected data and improperly labeled variables, among other factors. As a result, we can often end up using data that is not representative of the problem we are trying to solve. In this case study, we explore the challenges of using such an open dataset from India, to predict an important health outcome. We highlight how the use of AI without proper understanding of reporting metrics can lead to erroneous conclusions

Anusua Trivedi
Fri 2:30 p.m. - 2:45 p.m. [iCal]

Many policymakers, academics and governments have advocated for exchangeable property rights over information as it presents a market solution to what could be considered a market failure. Particularly in jurisdictions such as Africa, Asia or South America, where weaker legal protections and fleeting regulatory enforcement leaves data subjects vulnerable or exploited regardless of the outcome. We argue that whether we could achieve this personal data economy in which individuals have ownership rights akin to property rights over their data should be approached with caution as a solution to ensuring individuals have agency over their data across different legal landscapes.

We present an objection to the use of property rights, a market solution, due to the noxious nature of personal data - which is founded on Satz and Sandell's objection to markets. Ultimately, our rights over personal data and privacy are borne out of our basic human rights and are a precondition for the self-development, personal fulfilment and the free enjoyment of other fundamental human rights - and putting it up for sale risks corrupting its essence and value.

Abdul Abdulrahim
Fri 2:45 p.m. - 3:00 p.m. [iCal]
HumBug Zooniverse: a crowdsourced acoustic mosquito dataset (Contributed Talk)
Ivan Kiskin
Fri 3:00 p.m. - 3:30 p.m. [iCal]

In September and October 2019, a three judge bench in Kenya heard a case protesting digital ID. The case arose after the state rolled out a mandatory digital ID system, known as Huduma Namba that would be a prerequisite for access to government services. Being a constitutional case, arguments on human rights such as privacy were expected. However, the state framed its case of digital ID as inevitable technological development and those opposed to the advancement as being fearful of technology. To understand whether there were human rights implications with the digital ID, parties had to explain about the technology choices taken, the data practices and parties involved in the project. Hence the court (and public at large) spent a significant amount of time getting to understand multi-modal deduplication. While judgement on the case is yet to be delivered, the case brings to fore the societal implications of technology. It also calls for dialogue between technologists and sociologists in design and execution of projects aimed at low and middle income countries.

Bomu Mutung'u
Fri 3:30 p.m. - 4:15 p.m. [iCal]
Coffee and Posters (Break)
Fri 4:15 p.m. - 4:20 p.m. [iCal]
Rockefeller Foundation and ML4D (Talk)
Eva Gjekmarkaj
Fri 4:20 p.m. - 4:25 p.m. [iCal]
Partnership on AI and ML4D (Talk)
Alice Xiang
Fri 4:25 p.m. - 4:30 p.m. [iCal]
Wadhwani AI and ML4D (Talk)
Amrita Mahale
Fri 4:30 p.m. - 5:30 p.m. [iCal]
Panel Discussion: Risks and Challenges in ML4D (Discussion Panel)
Fri 5:30 p.m. - 6:00 p.m. [iCal]
Closing Remarks and Town Hall (Discussion)

Author Information

Maria De-Arteaga (Carnegie Mellon University)

Maria is a joint PhD candidate in Machine Learning and Public Policy at Carnegie Mellon University’s Machine Learning Department and the Heinz College of Information Systems and Public Policy. Machine learning (ML) is increasingly being used to support decision-making in critical settings, where predictions have potentially grave implications over human lives. Examples include healthcare, hiring, child welfare, and criminal justice. Maria's research focuses on the risks and opportunities of ML-based predictions to support decision-making in the context of sustainable societies. As part of her work on algorithmic fairness and accountability, she characterizes how societal biases encoded in historical data may be reproduced and amplified by ML models, and develops algorithms to mitigate these risks. Moreover, even if data does not encode harmful societal biases, many challenges still prevent the effective use of predictions to improve decision-making, such as omitted payoff bias and the selective labels problem. In her research, Maria seeks to understand the limits and risks of using machine learning in these contexts, and to develop human-centered ML that can improve expert decision-making. She holds a M.Sc. in Machine Learning from Carnegie Mellon University (2017) and a B.Sc. in Mathematics from Universidad Nacional de Colombia (2013). She was an intern at Microsoft Research, Redmond, in 2017 and at Microsoft Research, New England, in 2018. Prior to graduate school, she worked as a data science researcher and as an investigative journalist. Her work has been awarded the Best Thematic Paper Award at NAACL’19, the Innovation Award on Data Science at Data for Policy’16, and has been featured by UN Women and Global Pulse in their report Gender Equality and Big Data: Making Gender Data Visible. She is a co-founder of the NeurIPS Machine Learning for the Developing World (ML4D) Workshop, and a recipient of a 2018 Microsoft Research Dissertation Grant.

Amanda Coston (Carnegie Mellon University)
Tejumade Afonja (Saarland University)

Tejumade Afonja is a Graduate Student at Saarland University studying Computer Science. Previously, she worked as an AI Software Engineer at InstaDeep Nigeria. She holds a B.Tech in Mechanical Engineering from Ladoke Akintola University of Technology (2015). She’s currently a remote research intern at Vector Institute where she is conducting research in the areas of privacy, security, and machine learning. Tejumade is the co-founder of AI Saturdays Lagos, an AI community in Lagos, Nigeria focused on conducting research and teaching machine learning related subjects to Nigerian youths. Tejumade is one of the 2020 Google EMEA Women Techmakers Scholar. Tejumade was a co-organizer for ML4D 2019 NeurIPS workshop and she is serving as the lead organizer this year. She is affiliated with several other workshops like BIA, WIML, ICLR, Deep Learning Indaba, AI4D, and DSA where she occasionally serves as a volunteer or mentor.

More from the Same Authors