Deep Learning, Case-Based Reasoning, and AutoML:
Present and Future Synergies

In Conjuction with IJCAI 2021

Date: Friday, Aug 20, 2021

Location: Online

For more information, please contact

Accepted papers now available

Workshop overview

Deep learning (DL) research has made dramatic progress in recent years, achieving high performance on supervised learning tasks for numerous problem domains. Simultaneously, there remain well-known challenges such as the need for large amounts of labeled training data, solving synthesis problems with structured solutions (e.g., designs, plans, or schedules), and explainability. Case-based reasoning is a knowledge-based methodology for reasoning from prior episodes, with complementary capabilities--such as to solve problems with small data sets or those requiring structured solutions, and to generate concrete explanations--and limitations. AutoML concerns processes for automatically generating end-to-end-machine learning (e.g., DL) pipelines, and could use techniques that build pipelines from prior cases (of successful pipeline components). This workshop will bring together researchers interested in DL, CBR, and AutoML to identify new opportunities and beneficial strategies for integrating these approaches to address current challenges.

Our goal for this workshop is to bring together members of the DL, CBR, and AutoML communities to identify new opportunities for leveraging the case-based reasoning methodology to advance deep learning and DL to advance CBR, to identify opportunities and challenges for leveraging CBR for AutoML, to examine related efforts from all three subareas, and to develop approaches for advancing such integrations. The workshop will include a substantial discussion component.

Potential subtopics include, but are not limited to:

For further discussion of some of these topics, see On Bringing Case-Based Reasoning Methodology to Deep Learning.

Important dates


Twin Systems for DeepCBR: A Menagerie of Deep Learning and Case-Based Reasoning Pairings for Explanation and Data Augmentation

Mark T Keane, Eoin M Kenny, Mohammed Temraz, Derek Greene, Barry Smyth

Recently, it has been proposed that fruitful synergies may exist between Deep Learning (DL) and Case Based Reasoning (CBR); that there are insights to be gained by applying CBR ideas to problems in DL (what could be called DeepCBR). In this paper, we report on a program of research that applies CBR solutions to the problem of Explainable AI (XAI) in the DL. We describe a series of twin-systems pairings of opaque DL models with transparent CBR models that allow the latter to explain the former using factual, counterfactual and semi-factual explanation strategies. This twinning shows that functional abstractions of DL (e.g., feature weights, feature importance and decision boundaries) can be used to drive these explanatory solutions. We also raise the prospect that this research also applies to the problem of Data Augmentation in DL, underscoring the fecundity of these DeepCBR ideas.

Applying the Case Difference Heuristic to Learn Adaptations from Deep Network Features

Xiaomeng Ye, Ziwei Zhao, David Leake, Xizi Wang, David Crandall

The case difference heuristic (CDH) approach is a knowledge-light method for learning case adaptation knowledge from the case base of a case-based reasoning system. Given a pair of cases, the CDH approach attributes the difference in their solutions to the difference in the problems they solve, and generates adaptation rules to adjust solutions accordingly when a retrieved case and new query have similar problem differences. As an alternative to learning adaptation rules, several researchers have applied neural networks to learn to predict solution differences from problem differences. Previous work on such approaches has assumed that the feature set describing problems is predefined. This paper investigates a two-phase process combining deep learning for feature extraction and neural network based adaptation learning from extracted features. Its performance is demonstrated in a regression task on an image data: predicting age given the image of a face. Results show that the combined process can successfully learn adaptation knowledge applicable to nonsymbolic differences in cases. The CBR system achieves slightly lower performance overall than a baseline deep network regressor, but better performance than the baseline on novel queries.

Informed Machine Learning for Improved Similarity Assessment in Process-Oriented Case-Based Reasoning

Maximilian Hoffmann, Ralph Bergmann

Currently, Deep Learning (DL) components within a Case-Based Reasoning (CBR) application often lack the comprehensive integration of available domain knowledge. The trend within machine learning towards so-called Informed machine learning can help to overcome this limitation. In this paper, we therefore investigate the potential of integrating domain knowledge into Graph Neural Networks (GNNs) that are used for similarity assessment between semantic graphs within process-oriented CBR applications. We integrate knowledge in two ways: First, a special data representation and processing method is used that encodes structural knowledge about the semantic annotations of each graph node and edge. Second, the message-passing component of the GNNs is constrained by knowledge on legal node mappings. The evaluation examines the quality and training time of the extended GNNs, compared to the stock models. The results show that both extensions are capable of providing better quality, shorter training times, or in some configurations both advantages at once.

Interpretable Mammographic Image Classification using Cased-Based Reasoning and Deep Learning

Alina Jade Barnett, Fides Regina Schwartz, Chaofan Tao, Chaofan Chen, Yinhao Ren, Joseph Y. Lo, Cynthia Rudin

When we deploy machine learning models in high-stakes medical settings, we must ensure these models make accurate predictions that are consistent with known medical science. Inherently interpretable networks address this need by explaining the rationale behind each decision while maintaining equal or higher accuracy compared to black-box models. In this work, we present a novel interpretable neural network algorithm that uses case-based reasoning for mammography. Designed to aid a radiologist in their decisions, our network presents both a prediction of malignancy and an explanation of that prediction using known medical features. In order to yield helpful explanations, the network is designed to mimic the reasoning processes of a radiologist: our network first detects the clinically relevant semantic features of each image by comparing each new image with a learned set of prototypical image parts from the training images, then uses those clinical features to predict malignancy. Compared to other methods, our model detects clinical features (mass margins) with equal or higher accuracy, provides a more detailed explanation of its prediction, and is better able to differentiate the classification-relevant parts of the image.


David Aha
Naval Research Laboratory

David Crandall
Indiana University

David Leake
Indiana University

Organizing Committee

Yue Chen
Indiana University

Xiaomeng Ye
Indiana University

Xizi Wang
Indiana University

Program Committee

Klaus-Dieter Althoff
University of Hildesheim

Kerstin Bach
Norwegian University of Science and Techology

Chaofan Chen
University of Maine

Ralph Bergmann
University of Trier

Stelios Kapetanakis
University of Brighton

Sadiq Sani
British Telecommunications PLC

Swaroop Vattam
MIT Lincoln Laboratory

Rosina Weber
Drexel University

Nirmalie Wiratunga
Robert Gordon University