Prototype models are an important method for explainable artificial intelligence (XAI) and interpretable machine learning. In this paper, we perform an in-depth analysis of a set of prominent prototype models including ProtoPNet, ProtoPool and PIPNet. For their assessment, we apply a comprehensive set of metrics. In addition to applying standard metrics from literature, we propose several new metrics to further complement the analysis of model interpretability. In our experimentation, we apply the set of prototype models on a diverse set of datasets including fine-grained classification, Non-IID settings and multi-label classification to further contrast the performance. Furthermore, we also provide our code as an open-source library (https://github.com/uos-sis/quanproto), which facilitates simple application of the metrics itself, as well as extensibility -- providing the option for easily adding new metrics and models.

Deep learning-based electrocardiogram (ECG) classification has shown impressive performance but clinical adoption has been slowed by the lack of transparent and faithful explanations. Post hoc methods such as saliency maps may fail to reflect a model's true decision process. Prototype-based reasoning offers a more transparent alternative by grounding decisions in similarity to learned representations of real ECG segments, enabling faithful, case-based explanations. We introduce ProtoECGNet, a prototype-based deep learning model for interpretable, multi-label ECG classification. ProtoECGNet employs a structured, multi-branch architecture that reflects clinical interpretation workflows: it integrates a 1D CNN with global prototypes for rhythm classification, a 2D CNN with time-localized prototypes for morphology-based reasoning, and a 2D CNN with global prototypes for diffuse abnormalities. Each branch is trained with a prototype loss designed for multi-label learning, combining clustering, separation, diversity, and a novel contrastive loss that encourages appropriate separation between prototypes of unrelated classes while allowing clustering for frequently co-occurring diagnoses. We evaluate ProtoECGNet on all 71 diagnostic labels from the PTB-XL dataset, demonstrating competitive performance relative to state-of-the-art black-box models while providing structured, case-based explanations. To assess prototype quality, we conduct a structured clinician review of the final model's projected prototypes, finding that they are rated as representative and clear. ProtoECGNet shows that prototype learning can be effectively scaled to complex, multi-label time-series classification, offering a practical path toward transparent and trustworthy deep learning models for clinical decision support.

Federated Learning (FL) enables collaborative learning of large-scale distributed clients without data sharing. However, due to the disparity of computing resources among massive mobile computing devices, the performance of traditional homogeneous model-based Federated Learning (FL) is seriously limited. On the one hand, to achieve model training in all the diverse clients, mobile computing systems can only use small low-performance models for collaborative learning. On the other hand, devices with high computing resources cannot train a high-performance large model with their insufficient raw data. To address the resource-constrained problem in mobile computing systems, we present a novel heterogeneous FL approach named AdapterFL, which uses a model reassemble strategy to facilitate collaborative training of massive heterogeneous mobile devices adaptively. Specifically, we select multiple candidate heterogeneous models based on the computing performance of massive mobile devices and then divide each heterogeneous model into two partitions. By reassembling the partitions, we can generate models with varied sizes that are combined by the partial parameters of the large model with the partial parameters of the small model. Using these reassembled models for FL training, we can train the partial parameters of the large model using low-performance devices. In this way, we can alleviate performance degradation in large models due to resource constraints. The experimental results show that AdapterFL can achieve up to 12\% accuracy improvement compared to the state-of-the-art heterogeneous federated learning methods in resource-constrained scenarios.

In robotics, an end effector is a device at the end of a robotic arm that is designed to physically interact with objects in the environment or with the environment itself. Effectively, it serves as the hand of the robot, carrying out tasks on behalf of humans. But could we turn this concept on its head and consider using living organisms themselves as end effectors? This paper introduces a novel idea of using whole living organisms as end effectors for robotics. We showcase this by demonstrating that pill bugs and chitons -- types of small, harmless creatures -- can be utilized as functional grippers. Crucially, this method does not harm these creatures, enabling their release back into nature after use. How this concept may be expanded to other organisms and applications is also discussed.

A theory of categorization is presented in which knowledge of causal relationships between category features is represented as a Bayesian network. Referred to as causal-model theory, this theory predicts that objects are classified as category members to the extent they are likely to have been produced by a categorys causal model. On this view, people have models of the world that lead them to expect a certain distribution of features in category members (e.g., correlations between feature pairs that are directly connected by causal relationships), and consider exemplars good category members when they manifest those expectations. These expectations include sensitivity to higher-order feature interactions that emerge from the asymmetries inherent in causal relationships. Research on the topic of categorization has traditionally focused on the problem of learning new categories given observations of category members.

This article was published as a part of the Data Science Blogathon. Jupyter Notebook is a web-based interactive computing platform that many data scientists use for data wrangling, data visualization, and prototyping of their Machine Learning models. It is easy to use the platform, and we can do programming in many languages like Python, Julia, R, etc. By default, it comes with Ipython kernels, and if necessary, we can install other language kernels. We'll need more tools to see how our prototype model works in a production environment and how visualizations look in a dashboard because they can only be used to prototype models and do things like Data wrangling and Data Visualization.

Current graph neural network (GNN) architectures naively average or sum node embeddings into an aggregated graph representation---potentially losing structural or semantic information. We here introduce OT-GNN, a model that computes graph embeddings using parametric prototypes that highlight key facets of different graph aspects. Towards this goal, we are (to our knowledge) the first to successfully combine optimal transport with parametric graph models. Graph representations are obtained from Wasserstein distances between the set of GNN node embeddings and "prototype" point clouds as free parameters. We theoretically prove that, unlike traditional sum aggregation, our function class on point clouds satisfies a fundamental universal approximation theorem. Empirically, we address an inherent collapse optimization issue by proposing a noise contrastive regularizer to steer the model towards truly exploiting the optimal transport geometry. Finally, we consistently report better generalization performance on several molecular property prediction tasks, while exhibiting smoother graph representations.

Human categorization is one of the most important and successful targets of cognitive modeling in psychology, yet decades of development and assessment of competing models have been contingent on small sets of simple, artificial experimental stimuli. Here we extend this modeling paradigm to the domain of natural images, revealing the crucial role that stimulus representation plays in categorization and its implications for conclusions about how people form categories. Applying psychological models of categorization to natural images required two significant advances. First, we conducted the first large-scale experimental study of human categorization, involving over 500,000 human categorization judgments of 10,000 natural images from ten non-overlapping object categories. Second, we addressed the traditional bottleneck of representing high-dimensional images in cognitive models by exploring the best of current supervised and unsupervised deep and shallow machine learning methods. We find that selecting sufficiently expressive, data-driven representations is crucial to capturing human categorization, and using these representations allows simple models that represent categories with abstract prototypes to outperform the more complex memory-based exemplar accounts of categorization that have dominated in studies using less naturalistic stimuli.

The AlphaGo, AlphaGo Zero, and AlphaZero series of algorithms are a remarkable demonstration of deep reinforcement learning's capabilities, achieving superhuman performance in the complex game of Go with progressively increasing autonomy. However, many obstacles remain in the understanding of and usability of these promising approaches by the research community. Toward elucidating unresolved mysteries and facilitating future research, we propose ELF OpenGo, an open-source reimplementation of the AlphaZero algorithm. ELF OpenGo is the first open-source Go AI to convincingly demonstrate superhuman performance with a perfect (20:0) record against global top professionals. We apply ELF OpenGo to conduct extensive ablation studies, and to identify and analyze numerous interesting phenomena in both the model training and in the gameplay inference procedures. Our code, models, selfplay datasets, and auxiliary data are publicly available.

A key function of data science at Twitch is using behavioral data to build data products that improve our products and services. Some examples of products that data science has helped to launch include the AutoMod chat moderation system, the similar channel recommendations used for Auto Hosting, and the recommendation system for VODs. This post discusses some of the tradeoffs involved when building data products and presents our approach for scaling predictive models to millions of users. The decision to build a data product at Twitch is often the result of exploratory analysis performed by a data scientist. For example, an investigation of our user communities may result in findings about which types of channels different groups of users are likely to follow. We can use these insights to build predictive models, such as a recommendation system that identifies similar channels on our platform.