Cover Image

Prototype-Guided and Lightweight Adapters for Inherent Interpretation and Generalisation in Federated Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Mensah, Samuel Ofosu, Djoumessi, Kerol, Berens, Philipp
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

A Hybrid Fully Convolutional CNN-Transformer Model for Inherently Interpretable Disease Detection from Retinal Fundus Images
by: Djoumessi, Kerol, et al.
Published: (2025)

Towards Interpretable Foundation Models for Retinal Fundus Images
by: Mensah, Samuel Ofosu, et al.
Published: (2026)

Soft-CAM: Making black box models self-explainable for medical image analysis
by: Djoumessi, Kerol, et al.
Published: (2025)

TTE-CAM: Self-Explainable Class Activation Maps for Pretrained Black-Box CNNs
by: Djoumessi, Kerol, et al.
Published: (2026)

Beyond Accuracy: Evaluating Efficiency, Robustness and Explainability in Deep Learning for Malaria Diagnosis
by: Kanamugire, Olivier, et al.
Published: (2026)

This actually looks like that: Proto-BagNets for local and global interpretability-by-design
by: Djoumessi, Kerol, et al.
Published: (2024)

Inherently Interpretable Tree Ensemble Learning
by: Yang, Zebin, et al.
Published: (2024)

Hierarchical mixtures of Gaussians for combined dimensionality reduction and clustering
by: Sokoloski, Sacha, et al.
Published: (2022)

ProtoEFNet: Dynamic Prototype Learning for Inherently Interpretable Ejection Fraction Estimation in Echocardiography
by: Ghamary, Yeganeh, et al.
Published: (2025)

Mitigating Shortcut Learning via Feature Disentanglement in Medical Imaging: A Benchmark Study
by: Müller, Sarah, et al.
Published: (2026)

Learning Self-Interpretation from Interpretability Artifacts: Training Lightweight Adapters on Vector-Label Pairs
by: Pepper, Keenan, et al.
Published: (2026)

Estimating Causal Effects with Double Machine Learning -- A Method Evaluation
by: Fuhr, Jonathan, et al.
Published: (2024)

Federated Learning with Nonvacuous Generalisation Bounds
by: Jobic, Pierre, et al.
Published: (2023)

Inherently Interpretable and Uncertainty-Aware Models for Online Learning in Cyber-Security Problems
by: Kolicic, Benjamin, et al.
Published: (2024)

Attraction-Repulsion Spectrum in Neighbor Embeddings
by: Böhm, Jan Niklas, et al.
Published: (2020)

Persistent Homology for High-dimensional Data Based on Spectral Methods
by: Damrich, Sebastian, et al.
Published: (2023)

Causality is Key for Interpretability Claims to Generalise
by: Joshi, Shruti, et al.
Published: (2026)

Generalising Battery Control in Net-Zero Buildings via Personalised Federated RL
by: Avila, Nicolas M Cuadrado, et al.
Published: (2024)

Inherently Interpretable Time Series Classification via Multiple Instance Learning
by: Early, Joseph, et al.
Published: (2023)

Partial Knowledge Distillation for Alleviating the Inherent Inter-Class Discrepancy in Federated Learning
by: Gan, Xiaoyu, et al.
Published: (2024)

Federated Generalised Variational Inference: A Robust Probabilistic Federated Learning Framework
by: Mildner, Terje, et al.
Published: (2025)

Principal Prototype Analysis on Manifold for Interpretable Reinforcement Learning
by: Vamshi, Bodla Krishna, et al.
Published: (2026)

Learning Disease State from Noisy Ordinal Disease Progression Labels
by: Schmidt, Gustav, et al.
Published: (2025)

Optimizing Federated Graph Learning with Inherent Structural Knowledge and Dual-Densely Connected GNNs
by: Wang, Longwen, et al.
Published: (2024)

Cropping outperforms dropout as an augmentation strategy for self-supervised training of text embeddings
by: González-Márquez, Rita, et al.
Published: (2025)

Multi-Stage Prototype Learning for Interpretable Time Series Classification
by: Kalisetti, Bhavesh, et al.
Published: (2021)

Prototype-Based Learning for Healthcare: A Demonstration of Interpretable AI
by: Rana, Ashish, et al.
Published: (2026)

ProtoAda: Prototype-Guided Adaptive Adapter Expansion and Geometric Consolidation for Multimodal Continual Instruction Tuning
by: Shi, Yu-Cheng, et al.
Published: (2026)

Federated Class-Incremental Learning with Hierarchical Generative Prototypes
by: Salami, Riccardo, et al.
Published: (2024)

FedORGP: Guiding Heterogeneous Federated Learning with Orthogonality Regularization on Global Prototypes
by: Guo, Fucheng, et al.
Published: (2025)

GeoPro-Net: Learning Interpretable Spatiotemporal Prediction Models through Statistically-Guided Geo-Prototyping
by: An, Bang, et al.
Published: (2024)

Prototype Learning to Create Refined Interpretable Digital Phenotypes from ECGs
by: Sethi, Sahil, et al.
Published: (2025)

Federated Multimodal Learning with Dual Adapters and Selective Pruning for Communication and Computational Efficiency
by: Nguyen, Duy Phuong, et al.
Published: (2025)

Lightweight Fairness for LLM-Based Recommendations via Kernelized Projection and Gated Adapters
by: Cui, Nan, et al.
Published: (2026)

Towards Interpretable Federated Learning
by: Li, Anran, et al.
Published: (2023)

Breaking the Black Box: Inherently Interpretable Physics-Constrained Machine Learning With Weighted Mixed-Effects for Imbalanced Seismic Data
by: Sreenath, Vemula, et al.
Published: (2025)

Federated Adapter on Foundation Models: An Out-Of-Distribution Approach
by: Yang, Yiyuan, et al.
Published: (2025)

Prototype Guided Post-pretraining for Single-Cell Representation Learning
by: Weerasekara, Sachini, et al.
Published: (2026)

Federated Prototype Graph Learning
by: Wu, Zhengyu, et al.
Published: (2025)

ProtoSSL: Interpretable Prototype Learning from Unlabeled Time-Series Data
by: Song, Steven, et al.
Published: (2026)