Proceedings of the 4th Workshop on the Interactions between Analogical Reasoning and Machine Learning (IARML 2025) co-located with the International Joint Conference on Artificial Intelligence (IJCAI 2025)
Year: 2025
Type: conference-paper
Abstract: Analogical reasoning is a remarkable human capability that is used to solve hard reasoning tasks.It involves transferring knowledge from a source domain to a different but somewhat similar target domain by relying simultaneously on similarities and differences.Analogies have preoccupied humanity at least since antiquity (cf the works of Atistotle, Theon of Smyrna, among others) and have been in more recent years characterized as being "at the core of cognition" (Hofstadter 2001) showing that they permeate almost every aspect of cognition (Hofstadter and Sanders, 2013).Analogies have been tackled from various angles.Traditionally, analogical proportions, i.e., statements of the form "A is to B as C is to D", are the basis of analogical inference.They contributed to case-based reasoning and to multiple machine learning tasks such as classification, decision making and machine translation with competitive results.Also, analogical extrapolation can support dataset augmentation (analogical extension) for model learning, especially in environments with few labeled examples.Other approaches include the Structure Mapping approach of Dedre Gentner, which is based on logical descriptions (in the form of predicate-argument structures) of two domains: the more relational similarity one has between the two domains, the more analogous they can be considered.According to Hofstadter and the Fluid Analogies Research Group, analogy making is intimately related with abstraction and the search of a "common essence", which can lead to deep understanding of any concept or situation.Recent neural techniques, such as representation learning, enabled efficient approaches to detecting and solving analogies in domains where symbolic approaches had shown their limits.Transformer architectures trained using vast amounts of data have given us Large Language Models (LLMs) such as Chat-GPT, LLama and Mistral, which are capable of exhibiting human-like conversational and analogy making capacities (Webb et al. 2022).However, better evaluation metrics are needed in order to measure elusive concepts such as intelligence and understanding (Mitchel 2023).More than ever, we need to understand the role that analogies, abstraction and similarities between concepts play in language and cognition.The series of workshops Interactions between Analogical Reasoning and Machine Learning (IARML), organized on behalf of the International Joint Conferences on Artificial Intelligence (IJCAI), aims to bring together AI researchers at the crossroads of machine learning, natural language processing, knowledge representation and reasoning, who are interested in the various applications of analogical reasoning in machine learning or, conversely, of machine learning techniques to improve analogical reasoning.The first three editions were co-located with the IJCAI-ECAI 2022 (Vienna, Austria) and IJCAI 2023 (Macao, China), and IJCAI 2024 (Jeju, Korea) conferences, respectively.These first editions showed a promising impact with contributions from 5 continents, and that led to the edition of a special volume in Annals of Mathematics and Artificial Intelligence (under final reviewing), in addition to the CEUR and HAL workshop proceedings (e.g., IARML2022, IARML2023 and IARML2024).This fourth edition of the IARML workshop was hosted by the 34th International Joint Conference on Artificial Intelligence (IJCAI) and took place on August 17, 2024 in Montréal, Canada.It welcomed submissions of research papers on all topics at the intersection of analogical reasoning and machine learning.The submissions were subjected to a strict reviewing process that resulted in the selection of five original contributions, one contributed and three keynote talks:1
Source: HAL
Authors: Bouraoui, Zied, Couceiro, Miguel
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funder: Agence Nationale de la Recherche
OpenAlex ID: W4415195805