David Leake
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
David Leake has a total of 43 co-authors. Here are the top co-authors by number of shared publications:
David Crandall
Indiana University
5 shared publications- David Crandall
Indiana University, Bloomington, USA
5 shared publications - Zachary Wilkerson
Indiana University
4 shared publications Brian Schack
Indiana University
3 shared publications- Xiaomeng Ye
Indiana University
3 shared publications - Xiaomeng Ye
Berry College
3 shared publications
Latest Publications
- 1 August 2026
- Published by Springer Nature
- p. 119-134
Combining Deep Learning and Large Language Models for Retrieval-Based Image Classification
- 1 August 2026
- Published by Springer Nature
- p. 119-134
Combining Deep Learning and Large Language Models for Retrieval-Based Image Classification
- 1 August 2026
- Published by Springer Nature
- p. 270-284
Hallucinations Considered Helpful: Increasing Case Base Competence with LLM-Hallucinated Cases
- 1 August 2026
- Published by Springer Nature
- p. 270-284
Hallucinations Considered Helpful: Increasing Case Base Competence with LLM-Hallucinated Cases
- 1 August 2026
- Published by Springer Nature
- p. 285-300
Keep Adaptation Simple: Implicit vs. Explicit Adaptation for LLM-Based CBR
- 1 August 2026
- Published by Springer Nature
- p. 285-300
Keep Adaptation Simple: Implicit vs. Explicit Adaptation for LLM-Based CBR
- Open Access
- 1 September 2025
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 8, 6857-6865
Run Like a Neural Network, Explain Like k-Nearest Neighbor
Deep neural networks have achieved remarkable performance across a variety of applications. However, their decision-making processes are opaque. In contrast, k-nearest neighbor (k-NN) provides interpretable predictions by relying on similar cases, but it lacks important capabilities of neural networks. The neural network k-nearest neighbor (NN-kNN) model is designed to bridge this gap, combining the benefits of neural networks with the instance-based interpretability of k-NN. However, the initial formulation of NN-kNN had limitations including scalability issues, reliance on surface-level features, and an excessive number of parameters. This paper improves NN-kNN by enhancing its scalability, parameter efficiency, ease of integration with feature extractors, and training simplicity. An evaluation of the revised architecture for image and language classification tasks illustrates its promise as a flexible and interpretable method.
- 1 September 2025
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 8, 6857-6865
Open AccessRun Like a Neural Network, Explain Like k-Nearest Neighbor
Deep neural networks have achieved remarkable performance across a variety of applications. However, their decision-making processes are opaque. In contrast, k-nearest neighbor (k-NN) provides interpretable predictions by relying on similar cases, but it lacks important capabilities of neural networks. The neural network k-nearest neighbor (NN-kNN) model is designed to bridge this gap, combining the benefits of neural networks with the instance-based interpretability of k-NN. However, the initial formulation of NN-kNN had limitations including scalability issues, reliance on surface-level features, and an excessive number of parameters. This paper improves NN-kNN by enhancing its scalability, parameter efficiency, ease of integration with feature extractors, and training simplicity. An evaluation of the revised architecture for image and language classification tasks illustrates its promise as a flexible and interpretable method.
- Open Access
- 1 September 2025
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 5, 4339-4346
EnergyCompress: A General Case Base Learning Strategy
Case-based prediction (CBP) methods do not learn a model of the target decision function but instead perform an inference process that depends on two similarity measures and a reference case base. This paper proposes a strategy, called EnergyCompress, to learn an effective case base by selecting relevant cases from an initial set. Use of EnergyCompress decreases CBP inference time, through case base compression, and also increases prediction performance, for a wide variety of CBP algorithms. EnergyCompress relies on the proposition of a general formulation of the CBP task in the framework of energy-based models, which leads to a new and valuable characterization of the notion of competence in case-based reasoning, in particular at the source case level. Extensive experimental results on 18 benchmark datasets comparing EnergyCompress to 5 reference algorithms for case base maintenance support the benefit of the proposed strategy.
- 1 September 2025
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 5, 4339-4346
Open AccessEnergyCompress: A General Case Base Learning Strategy
Case-based prediction (CBP) methods do not learn a model of the target decision function but instead perform an inference process that depends on two similarity measures and a reference case base. This paper proposes a strategy, called EnergyCompress, to learn an effective case base by selecting relevant cases from an initial set. Use of EnergyCompress decreases CBP inference time, through case base compression, and also increases prediction performance, for a wide variety of CBP algorithms. EnergyCompress relies on the proposition of a general formulation of the CBP task in the framework of energy-based models, which leads to a new and valuable characterization of the notion of competence in case-based reasoning, in particular at the source case level. Extensive experimental results on 18 benchmark datasets comparing EnergyCompress to 5 reference algorithms for case base maintenance support the benefit of the proposed strategy.
- 23 June 2025
- Published by Springer Nature
- p. 345-359
Extracting Features with Deep Learning for Ensemble-Driven Case-Based Classification
- 23 June 2025
- Published by Springer Nature
- p. 345-359
Extracting Features with Deep Learning for Ensemble-Driven Case-Based Classification
- 23 June 2025
- Published by Springer Nature
- p. 313-327
Learning Case Features with Proxy-Guided Deep Neural Networks
- 23 June 2025
- Published by Springer Nature
- p. 313-327
Learning Case Features with Proxy-Guided Deep Neural Networks
- Open Access
Case-Enhanced Vision Transformer: Improving Explanations of Image Similarity with a ViT-based Similarity Metric
This short paper presents preliminary research on the Case-Enhanced Vision Transformer (CEViT), a similarity measurement method aimed at improving the explainability of similarity assessments for image data. Initial experimental results suggest that integrating CEViT into k-Nearest Neighbor (k-NN) classification yields classification accuracy comparable to state-of-the-art computer vision models, while adding capabilities for illustrating differences between classes. CEViT explanations can be influenced by prior cases, to illustrate aspects of similarity relevant to those cases.
Open AccessCase-Enhanced Vision Transformer: Improving Explanations of Image Similarity with a ViT-based Similarity Metric
This short paper presents preliminary research on the Case-Enhanced Vision Transformer (CEViT), a similarity measurement method aimed at improving the explainability of similarity assessments for image data. Initial experimental results suggest that integrating CEViT into k-Nearest Neighbor (k-NN) classification yields classification accuracy comparable to state-of-the-art computer vision models, while adding capabilities for illustrating differences between classes. CEViT explanations can be influenced by prior cases, to illustrate aspects of similarity relevant to those cases.
- 24 June 2024
- Published by Springer Nature
- p. 143-158
Extracting Indexing Features for CBR from Deep Neural Networks: A Transfer Learning Approach
- 24 June 2024
- Published by Springer Nature
- p. 143-158
Extracting Indexing Features for CBR from Deep Neural Networks: A Transfer Learning Approach
- 24 June 2024
- Published by Springer Nature
- p. 404-417
On Implementing Case-Based Reasoning with Large Language Models
- 24 June 2024
- Published by Springer Nature
- p. 404-417
On Implementing Case-Based Reasoning with Large Language Models