Abstract

This document is the preface of the proceedings of the 8th International Workshop & Tutorial on Interactive Adaptive Learning, held on September 9th, 2024 in Vilnius, Lithuania. We received 11 submissions for peer-review, out of which we accepted 8 papers for this volume. In addition, we publish an extended abstract of the tutorial that we give as a part of the workshop program. Methods of machine learning are approaching their limits whenever training data of a high quality are scarce. The potential reasons for data scarcity are manifold: limited capabilities of human supervisors and processing systems, a need for early predictions which can later be refined, or transfer settings where the only available data stem from some diferent learning task.

Preface

CEUR Workshop Proceedings

ceur-ws.org ISSN1613-0073 2019 in Würzburg, a workshop at ECML-PKDD 2018 in Dublin, a tutorial at IJCNN 2018 in Rio, and a workshop & tutorial at ECML-PKDD 2017 in Skopje.

This year, we accepted 8 papers out of 11 submissions for their publication in these workshop proceedings. In addition to these contributions, we publish an extended abstract of a tutorial that belongs to the workshop program. We thank all authors for their valuable submissions and all members of the program committee for their great support.

August 2024

Organization

Organizing Committee

Mirko Bunse

Marek Herde

Georg Krempl

Vincent Lemaire

Minh Tuan Pham

Amal Saadallah

Alaa Tharwat

Steering Committee

Adrian Calma

Barbara Hammer

Andreas Holzinger

Daniel Kottke

Robi Polikar

Bernhard Sick

Program Committee

Bernhard Pfahringer

Minh Tuan Pham

Amal Saadallah

Contents

University of Waikato

University of Kassel, Germany Lamarr Institute for Machine Learning and Artificial Intelligence, Germany

Ghent University, Belgium

University of Magdeburg, Germany

Hochschule Bielefeld, Germany

Aalen University of Applied Sciences, Germany Preface . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . i–iii

Mirko Bunse, Marek Herde, Georg Krempl, Vincent Lemaire, Minh Tuan Pham, Amal Saadallah, and Alaa Tharwat

Extended Abstracts

Tutorial: Interactive Adaptive Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1–6

Marek Herde, Minh Tuan Pham, Alaa Tharwat, and Bernhard Sick

Research Papers

References

Deep Transfer Hashing for Adaptive Learning on Federated Streaming Data . . . . . . . . . . . . . . . . . . 7-11 Manuel Röder and Frank-Michael Schleif

Towards Deep Active Learning in Avian Bioacoustics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12 -17 Lukas Rauch , Denis Huseljic, Moritz Wirth, Jens Decke, Bernhard Sick, and Christoph Scholz

Amortized Active Learning for Nonparametric Functions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18 -32 Cen-You Li , Marc Toussaint , Barbara Rakitsch, and Christoph Zimmer

General Reusability : Ensuring Long-Term Benefits of Deep Active Learning . . . . . . . . . . . . . . . . . 33 -46 Paul Hahn , Denis Huseljic, Marek Herde, and Bernhard Sick

Optimization . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 47 -67 Martin Holeňa and Jan Koza

Active Learning with Physics-Informed Graph Neural Networks on Unstructured Meshes . . . . 68-76 Jens Decke , Alexander Heinen, Bernhard Sick, and Christian Gruhl

Assisted Review . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 77 -95 Michiel P. Bron, Berend Greijn, Bruno Messina Coimbra, Rens van de Schoot, and Ayoub Bagheri

Contextual kNN Ensemble Retrieval Approach for Semantic Postal Address Matching . . . . . . . 96 -111 El Moundir Faraoun , Nédra Mellouli, Stéphane Millot, and Myriam Lamolle