7th International Workshop & Tutorial on

Interactive Adaptive Learning (IAL 2023)

Co-Located With ECML-PKDD 2023

Friday, 22 September 2023 – Aula 9T, Torino, Italy

Call for Papers

Science, technology, and commerce increasingly recognise the importance of machine learning approaches for data-intensive, evidence-based decision making.

Moreover, the number of machine learning applications and the volumes of data increase permanently. Nevertheless, the capacities of processing systems, human supervisors, or domain experts remain limited in real-world applications. Furthermore, many applications require an early availability of predictive models, which then have to be refined as the data volume increases. Due to these requirements, approaches that optimise the whole learning process are needed, including the interaction with human supervisors, processing systems, and data of various kinds and at different points in time: techniques for estimating the impact of additional resources (e.g.~data) on the learning progress; methods for the active selection of the information that is processed or queried; techniques for reusing knowledge across time, domains, or tasks, by identifying similarities and adaptation to changes between them; methods for making use of different types of information, such as labelled or unlabelled data, constraints, or domain knowledge. Such techniques are studied, for example, in the fields of adaptive, active, semi-supervised, and transfer learning -- mostly in separate lines of research. Combinations that are capable of operating under various constraints, and thereby address the inherent real-world challenges of volume, velocity, and variability of data and data mining systems, are rarely reported.

Therefore, this combination of a workshop and tutorial will continue to bring together researchers and practitioners from these different areas, thereby stimulating research in interactive and adaptive machine learning systems as a whole. The event continues a successful series of workshops and tutorials at ECML-PKDD 2017 in Skopje (Workshop \& Tutorial), IJCNN 2018 in Rio (Tutorial), ECML-PKDD 2018 in Dublin (Workshop), ECML-PKDD 2019 in Würzburg (Workshop \& Tutorial), ECML-PKDD 2020 (hosted in Ghent, online Workshop), ECML-PKDD 2021 (hosted in Bilbao, online Workshop), and ECML-PKDD 2022 in Grenoble (Workshop).

This workshop evolves around techniques and approaches for optimising the whole learning process, including the interaction with human supervisors, processing systems, and includes adaptive, active, semi-supervised, and transfer learning techniques, and combinations thereof in interactive and adaptive machine learning systems. Our objective is to bridge the communities researching and developing these techniques and systems in machine learning and data mining. Therefore, we welcome contributions that present a new problem setting, propose a novel approach, or report experience with the practical deployment of such a system and raise unsolved questions to the research community.

In particular, we welcome contributions that address aspects including, but not limited to:

    Novel Techniques for Active, Semi-Supervised, Transfer, or Weakly Supervised Learning
  • methods for big, evolving, or streaming data
  • methods for recent complex model structures such as deep learning neural networks or recurrent neural networks
  • methods for interacting with imperfect or multiple oracles, e.g., learning from crowds
  • methods for incorporating domain knowledge and constraints
  • methods for timing the interaction and for combining different types of information
  • online and ensemble methods for evolving models and systems, with specific switching and fusion techniques, and (inter-)active data integration techniques
  • Innovative Use and Applications of Active, Semi-Supervised, Transfer, or Weakly Supervised Learning
  • for filtering, forgetting, resampling
  • for active class or feature selection, e.g., from multi-modal data
  • for detection of change, outliers, frauds, or attacks
  • new interactive learning protocols and application scenarios, e.g., brain-computer interfaces, crowdsourcing, ...
  • in application in data-intensive science
  • in applications with real-world deployment
  • Techniques for Combined Interactive Adaptive Learning
  • methods combining adaptive, active, semi-supervised, or transfer learning techniques
  • cost-aware methods and methods for estimating the impact of employing additional resources, such as data or processing capacities, on the learning progress
  • methodologies for the evaluation of such techniques and for comparative studies
  • methods for automating the control of an interactive adaptive learning process.


Important dates

  • Submission open

    Monday, 15 May 2023

  • Abstract deadline NEW

    Monday, 12 June 2023

  • Submission deadline EXTENDED

    Monday, 12 June 2023
    Wednesday, 21 June 2023

    You find the submission instructions below.

  • Notification POSTPONED

    Wednesday, 12 July 2023
    Monday, 24 July 2023

  • Camera Ready EXTENDED

    Tuesday, 25 July 2023
    Sunday, 13 August 2023

  • Workshop and Tutorial (full day)

    Friday, 22 September 2023 – Aula 9T

    Co-located with ECML-PKDD 2023, the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery.


    At least one author of each accepted paper must be registered.

Submit your contribution

Submission is now closed.

Full Papers

8-16 pages (excluding references)

This track covers new innovative contributions in the area of interactive adaptive learning. If you have a new method already evaluated briefly, a new tool to simplify interaction or some new insights the community might benefit from, please submit a regular paper.

Extended Abstracts

2-4 pages (excluding references)

This track is ideal to discuss new ideas in the area of interactive adaptive learning. We encourage you to submit open challenges in research or industrial applications to initiate a discussion and find colleagues to collaborate with.

Indexed Publishing

All accepted papers will be published at ceur-ws.org, which is indexed, e.g., by Google Scholar. Reviews are double-blind; papers must not include information that reveal the authors' identities.

CEUR Style

The paper must be be written in English and be submitted as a PDF file in the CEUR format. Download the LaTeX template or edit the template in Overleaf.

Presentation

All accepted papers are presented in spotlight talks and/or poster sessions. At least one author of each accepted paper must be registered at ECML-PKDD.

Dual Submission Policy

Submissions should report original work. Submissions that are identical or substantially similar to papers that have been published, have been submitted elsewhere, or are submitted elsewhere during the review period, will be rejected.

Keynote

From Insights to Impact: A Metrics-Driven Active Learning Journey

by Alexandre Abraham (Lead Data Scientist, Implicity)
In active learning, setting up experiments, especially for industrial practitioners, poses a challenge due to uncertainties in hyperparameters like batch size. Our research is dedicated to providing practitioners with the means to take control of their experiments. We've developed metrics monitoring aspects such as exploration and exploitation, and developped cardinal, a Python package, for their validation. This process led to the creation of a customized active learning strategy, rigorously assessed within an open benchmark. My presentation will elucidate the connections between these pivotal contributions and delve into our latest advancements in federated active learning.

Alexandre Abraham serves as the lead data scientist at Implicity, with a focus on causal inference. Throughout his career, he has specialized in unsupervised methods and human interaction. He earned his PhD at Inria developing unsupervised clustering to segment brain regions. After that, he worked on recommender systems at Criteo and Active Learning at Dataiku. His contributions revolve around developing metrics to empower active learning practitioners, enabling adaptability across various tasks. Additionally, he's the creator of the "cardinal" Python package designed for active learning metric research.

Program

Friday, 22 September 2023 – Aula 9T, Torino, Italy

The full proceedings of this workshop are published at CEUR-WS. Registered ECML attendees can access the recordings of all morning and afternoon talks. You can also download the slides of our tutorials.

Time Program Presenter / Author
09:00–11:00 Session 1: Tutorials & Poster Session
09:00–09:30 Tutorial Part I: Foundations of Active Learning A. Tharwat
09:30–10:30 Tutorial Part II: Beyond Pool-Based Scenarios G. Krempl
10:30–11:00 Poster Session
Coffee Break (11:00–11:30)
11:30–13:00 Session 2: Tutorials
11:30–12:00 Tutorial Part III: Beyond Active Labelling M. Bunse
12:00–12:30 Tutorial Part IV: Towards Explainable Active Learning using Meta-Learning A. Saadallah
12:30–13:00 Tutorial Part V: Practical Challenges and New Research Directions A. Tharwat
Lunch Break (13:00–14:00)
14:00–16:00 Session 3: Keynote & Workshop Contributions
14:00–14:40 Keynote: From Insights to Impact: A Metrics-Driven Active Learning Journey A. Abraham
14:40–14:55 Towards Enhancing Deep Active Learning with Weak Supervision and Constrained Clustering M. Aßenmacher, L. Rauch, J. Goschenhofer, A. Stephan, B. Bischl, B. Roth & B. Sick
14:55–15:15 Active Learning for Survival Analysis with Incrementally Disclosed Label Information K. Dedja, F.K. Nakano & C. Vens
15:15–15:30 Who knows best? A Case Study on Intelligent Crowdworker Selection via Deep Learning M. Herde, D. Huseljic, B. Sick, U. Bretschneider & S. Oeste-Reiß
15:30–15:45 Role of Hyperparameters in Deep Active Learning D. Huseljic, M. Herde, P. Hahn & B. Sick
15:45–16:00 Challenges for Active Feature Acquisition and Imputation on Data Streams C. Beyer, M. Büttner & M. Spiliopoulou
Coffee Break (16:00–16:30)
16:30–17:40 Session 4: Workshop Contributions & Closing
16:30–16:50 Active Learning with Fast Model Updates and Class-Balanced Selection for Imbalanced Datasets Z. Huang, Y. He, M. Herde, D. Huseljic & B. Sick
16:50–17:10 Interpretable Meta-Active Learning for Regression Ensemble Learning O. Saadallah & Z. Rouissi
17:10–17:30 Look and You Will Find It: Fairness-Aware Data Collection through Active Learning H. Weerts, R. Theunissen & M. Willemsen
17:30–17:40 Closing

Committee

Organizing Committee:
ial2023 (at) easychair.org

Mirko Bunse

mirko.bunse (at) cs.tu-dortmund.de
TU Dortmund University, Germany

Barbara Hammer

bhammer (at) techfak.uni-bielefeld.de
University of Bielefeld, Germany

Georg Krempl

g.m.krempl (at) uu.nl
Utrecht University, Netherlands

Vincent Lemaire

vincent.lemaire (at) orange.com
Orange Innovation, France

Alaa Othman

alaa.othman (at) fh-bielefeld.de
Fachhochschule Bielefeld, Germany

Amal Saadallah

amal.saadallah (at) cs.tu-dortmund.de
TU Dortmund University, Germany

Steering Committee:

Adrian Calma
University of Kassel, Germany

Andreas Holzinger
University of Natural Resources and Life Sciences Vienna, Austria

Daniel Kottke
Deutsche Bahn, Germany

Robi Polikar
Rowan University, USA

Bernhard Sick
University of Kassel, Germany

Program Committee:

to be determined.