==================================

Workshop on the Interactions between Analogical Reasoning and Machine Learning (IARML @ IJCAI-ECAI 2022)

Call For Papers

Dates: July 23rd-25th, 2022

Location: Vienna, Austria

Website: https://iarml2022-ijcai-ecai.loria.fr

Important dates:

* May 20, 2022: Workshop Paper Due Date

* June 10, 2022: Notification of Paper Acceptance

* June 24, 2022: Camera-ready papers due

================================================================

Analogical reasoning is a remarkable capability of human reasoning, used to solve hard reasoning tasks. It consists in transferring knowledge from a source domain to a different, but somewhat similar, target domain by relying simultaneously on similarities and dissimilarities. In particular, analogical proportions, i.e., statements of the form “A is to B as C is to D”, are the basis of analogical inference.

Analogical inference is pertaining to case-based reasoning and it has contributed to multiple machine learning tasks such as classification, decision making, and automatic translation with competitive results. Moreover, analogical extrapolation can support dataset augmentation (analogical extension) for model learning, especially in environments with few labeled examples. Conversely, advanced neural techniques, such as representation learning, enabled efficient approaches to detecting and solving analogies in domains where symbolic approaches had shown their limits. However, recent approaches using deep learning architectures remain task and domain specific, and strongly rely on ad-hoc representations of objects, i.e., tailor made embeddings.

The purpose of this workshop is to bring together AI researchers at the cross roads of machine learning and knowledge representation and reasoning, who are interested by the various applications of analogical reasoning in machine learning or, conversely, of machine learning techniques to improve analogical reasoning. The IARML workshop aims at bridging gaps between different communities of AI researchers, including case-based reasoning, deep learning and neuro-symbolic machine learning.

===========

Themes and topics

===========

We invite submissions of research papers on all topics at the intersection of analogical reasoning and machine learning. Topics of interest include, but are not limited to:

Machine learning for analogical reasoning:

* Representation learning;

* Transfer learning;

* Neuro-symbolic models for analogical inference.

Analogical reasoning for machine learning:

* Classification using analogical reasoning;

* Recommendation using analogical reasoning;

* Case-Based Reasoning.

Applications:

* Analogical reasoning in visual domains;

* Analogical reasoning in Natural Language Processing;

* Analogical reasoning in healthcare;

* Analogies in software engineering.

===========

Submission

===========

We welcome contributions in the form of extended abstracts (up to two pages) and long papers (up to six pages plus 1 page for references). Submissions can describe either work in progress or mature work that has already been published at other research venues. Previously published work in whole or in part may be in the form of a resubmission of a previous paper, or in the form of a survey or position paper that overviews and cites a body of work. Submitted papers must be formatted according to IJCAI-ECAI 2022 guidelines, which can be downloaded: https://www.ijcai.org/authors_kit

All papers will be thoroughly reviewed. Overlength papers will be rejected without review. The reviewing process will be double-blind.

Submission link: https://cmt3.research.microsoft.com/IARML2022

===========

Proceedings

===========

Accepted papers will appear in the preproceedings published in HAL and made available at the workshop. Selected papers will be invited for publication in a CEUR-WS postproceedings.

===========

Confirmed keynote speakers

===========

* Kenneth Forbus (Northwestern University)

* Yves Lepage (Waseda University)

===========

Chairs

===========

* Miguel Couceiro (University of Lorraine, CNRS, LORIA, Miguel.couceiro@loria.fr )

* Pierre-Alexandre Murena (Aalto University, pierre-alexandre.murena@aalto.fi )

The organizers would be grateful if you could inform potentially interested participants of this conference.