# Attention-based Generative Latent Replay: A Continual Learning Approach for WSI Analysis

arXiv: https://arxiv.org/abs/2505.08524 · HTML: https://mlsanity.com/paper/2505.08524/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 29 references that are in the map.
- First posted on arXiv 13 May 2025.

## Builds on (most cited first, 18 of 18)

- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [Attention-based Deep Multiple Instance Learning](https://mlsanity.com/paper/1802.04712/) (2018)
- [Experience Replay for Continual Learning](https://mlsanity.com/paper/1811.11682/) (2018)
- [Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Images](https://mlsanity.com/paper/2004.09666/) (2020)
- [Don't forget, there is more than forgetting: new metrics for Continual Learning](https://mlsanity.com/paper/1810.13166/) (2018)
- [Predicting Axillary Lymph Node Metastasis in Early Breast Cancer Using Deep Learning on Primary Tumor Biopsy Slides](https://mlsanity.com/paper/2112.02222/) (2021)
- [LifeLonger: A Benchmark for Continual Disease Classification](https://mlsanity.com/paper/2204.05737/) (2022)
- [ConSlide: Asynchronous Hierarchical Interaction Transformer with Breakup-Reorganize Rehearsal for Continual Whole Slide Image Analysis](https://mlsanity.com/paper/2308.13324/) (2023)
- [Continual Learning in Medical Image Analysis: A Comprehensive Review of Recent Advancements and Future Prospects](https://mlsanity.com/paper/2312.17004/) (2023)
- [Importance Driven Continual Learning for Segmentation Across Domains](https://mlsanity.com/paper/2005.00079/) (2020)
- [EVCL: Elastic Variational Continual Learning with Weight Consolidation](https://mlsanity.com/paper/2406.15972/) (2024)
- [Lifelong Histopathology Whole Slide Image Retrieval via Distance Consistency Rehearsal](https://mlsanity.com/paper/2407.08153/) (2024)
- [Continual Domain Incremental Learning for Privacy-aware Digital Pathology](https://mlsanity.com/paper/2409.06455/) (2024)
- [Concept Drift Challenge in Multimedia Anomaly Detection: A Case Study with Facial Datasets](https://mlsanity.com/paper/2207.13430/) (2022)
- [Characterizing Continual Learning Scenarios and Strategies for Audio Analysis](https://mlsanity.com/paper/2407.00465/) (2024)
- [Domain-incremental White Blood Cell Classification with Privacy-aware Continual Learning](https://mlsanity.com/paper/2503.19819/) (2025)

## Built on by (most cited first, 2 of 2)

- [Footprint-Guided Exemplar-Free Continual Histopathology Report Generation](https://mlsanity.com/paper/2602.23817/) (2026)
- [Autonomous Drift Learning in Data Streams: A Unified Perspective](https://mlsanity.com/paper/2605.01295/) (2026)

## Abstract (arXiv)

Whole slide image (WSI) classification has emerged as a powerful tool in computational pathology, but remains constrained by domain shifts, e.g., due to different organs, diseases, or institution-specific variations. To address this challenge, we propose an Attention-based Generative Latent Replay Continual Learning framework (AGLR-CL), in a multiple instance learning (MIL) setup for domain incremental WSI classification. Our method employs Gaussian Mixture Models (GMMs) to synthesize WSI representations and patch count distributions, preserving knowledge of past domains without explicitly storing original data. A novel attention-based filtering step focuses on the most salient patch embeddings, ensuring high-quality synthetic samples. This privacy-aware strategy obviates the need for replay buffers and outperforms other buffer-free counterparts while matching the performance of buffer-based solutions. We validate AGLR-CL on clinically relevant biomarker detection and molecular status prediction across multiple public datasets with diverse centers, organs, and patient cohorts. Experimental results confirm its ability to retain prior knowledge and adapt to new domains, offering an effective, privacy-preserving avenue for domain incremental continual learning in WSI classification.