At this workshop, we wish to stimulate the exchange of novel ideas and interdisciplinary perspectives. To do this, we will accept two different types of submissions:
Full papers
Present novel and original work.
Follow the submission format as main conference (in the same template, max. 16 pages including references).
Are ‘best-effort’ anonymized (follow double-blind instructions for the main conference).
Authors of accepted full papers can opt for their camera-ready papers to be included in the ECML PKDD post-workshop proceedings of the CCIS series of Springer.
Abstracts
Present already published work, including papers in other conferences or journals, demo's, datasets, or projects that are publicly available.
Consist of max. 2 pages, excluding references.
Are not expected to be anonymized.
Will not be published in the proceedings.
Both types of papers may be submitted here on CMT. The deadline is 15.06.2024.
We invite contributions that deal with bias and fairness in any ML approach (including but not limited to supervised learning, unsupervised learning, ranking, generative models, etc.) and ML system (e.g., recommender systems, search engines, chatbots, content moderation, etc.) on any type of data (tables, text, images, videos, speech, multimodal, ...) and learning setup (batch, non i.i.d., federated, …). We especially welcome interdisciplinary work, bridging computer science with fields like human-computer interaction, law, and social sciences.
Contributions may concern the fairness auditing/assessment of ML systems, surrounding topics like:
Auditing practices, tools, and metrics
Bias in generative and multimodal models
Best practices and legal frameworks around audits
Case studies
Privacy-aware fairness audits
xAI for understanding/auditing biases
Visual analytics for understanding/auditing biases
Society’s perception of algorithmic fairness
Other contributions may deal with the development and deployment of fairer algorithms:
Human in the loop approaches for fairness
Case studies on fairness-aware algorithms
Fairness-aware learning in multimodal and multi-attribute data
Fairness-aware data collection
Fairness-aware data processing
Fairness-aware algorithms
Paper Submission Deadline: 15.06.2024
Paper Acceptance Notification: 15.07.2024
Workshop Date: 13.09.2024
All Deadlines are Anytime on Earth (AoE) at 23:59.