HCMLP2019: Human-Centered Machine Learning Perspectives |
Website | https://aka.ms/hcmlperspectives |
Submission deadline | February 12, 2019 |
About
Machine Learning (ML) is currently one of the most important technologies used across systems affecting research, commerce, healthcare, entertainment, security, etc. As its use grows woven into our society, and affecting the lives of people, it has become important to study and design the interactions between ML and its stakeholders from a Human-Centered point of view. Human-Centered Machine Learning (HCML) shares this view and re-frames work on and related to ML in term of human goals.
This workshop continues prior workshops on HCML by inviting ideas focusing on (but not limited to) the themes of Teaching to Machines (Machine Teaching), and Explainable Decisions and ML Systems from a Human-Centered point of view. For example:
- What are the different ways to express and leverage human knowledge beyond labels: e.g., features, schema, concept decomposition, samples, etc
- How much should we allow a person to know about the underlying learning algorithm in a Machine Teaching system?
- How can we help a person map/decompose a problem to an ML-driven solution?
- What is a sufficient teaching language for different domains such as text, images, etc?
- Models created through Machine Teaching are semantic; i.e., the decisions made by these models are explainable in human terms. Are these explanations sufficient under the many different definitions and contexts of explainability?
- What is the cost of maintaining, debugging, sharing a Machine Teaching solution?
- How does one evaluate a Machine Teaching solution when there is no test set?
- What are the many definitions for explanations and intelligibility?
- What are proper metrics to measure explainability and intelligibility?
- What are the different ways to explain an algorithmic decision?
- When are explanations necessary, or aren't?
By articulating these emerging perspectives, we look at how, as a community, we keep moving the HCML field forward.
This workshop will take place at the ACM CHI 2019 Conference.
Submission Guidelines
We invite the submission of positions papers between 3-6 pages long. Position papers should follow the CHI Extended Abstract format and be submitted through this EasyChair submission site.
The workshop`s organizing committee will review the submissions and accepted papers will be presented at the workshop. We ask that at least one of the authors of each accepted position paper attends the workshop. Presenting authors must register for the workshop and at least one full day of the conference.
Each presentation will take place within a session focused around a particular theme. Sessions will consist of 3-4 presentations, each lasting approximately 10 minutes and will be followed by a group discussion.
Contact Us
For any additional questions, please contact us at goramos@microsoft.com