# Sparse Task Vector Mixup with Hypernetworks for Efficient Knowledge Transfer in Whole-Slide Image Prognosis

arXiv: https://arxiv.org/abs/2603.10526 · HTML: https://mlsanity.com/paper/2603.10526/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 50 references that are in the map.
- First posted on arXiv 11 Mar 2026.

## Builds on (most cited first, 30 of 33)

- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time](https://mlsanity.com/paper/2203.05482/) (2022)
- [Editing Models with Task Arithmetic](https://mlsanity.com/paper/2212.04089/) (2022)
- [Attention-based Deep Multiple Instance Learning](https://mlsanity.com/paper/1802.04712/) (2018)
- [TIES-Merging: Resolving Interference When Merging Models](https://mlsanity.com/paper/2306.01708/) (2023)
- [Robust fine-tuning of zero-shot models](https://mlsanity.com/paper/2109.01903/) (2021)
- [TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classification](https://mlsanity.com/paper/2106.00908/) (2021)
- [Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learning](https://mlsanity.com/paper/2011.08939/) (2020)
- [ST-MoE: Designing Stable and Transferable Sparse Expert Models](https://mlsanity.com/paper/2202.08906/) (2022)
- [Scaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learning](https://mlsanity.com/paper/2206.02647/) (2022)
- [DTFD-MIL: Double-Tier Feature Distillation Multiple Instance Learning for Histopathology Whole Slide Image Classification](https://mlsanity.com/paper/2203.12081/) (2022)
- [AdaMerging: Adaptive Model Merging for Multi-Task Learning](https://mlsanity.com/paper/2310.02575/) (2023)
- [Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Models](https://mlsanity.com/paper/2305.12827/) (2023)
- [How Does Mixup Help With Robustness and Generalization?](https://mlsanity.com/paper/2010.04819/) (2020)
- [Whole Slide Images based Cancer Survival Prediction using Attention Guided Deep Multiple Instance Learning Networks](https://mlsanity.com/paper/2009.11169/) (2020)
- [Visual Language Pretrained Multiple Instance Zero-Shot Transfer for Histopathology Images](https://mlsanity.com/paper/2306.07831/) (2023)
- [Localizing Task Information for Improved Model Merging and Compression](https://mlsanity.com/paper/2405.07813/) (2024)
- [Whole Slide Images are 2D Point Clouds: Context-Aware Survival Prediction using Patch-based Graph Convolutional Networks](https://mlsanity.com/paper/2107.13048/) (2021)
- [Representation Surgery for Multi-Task Model Merging](https://mlsanity.com/paper/2402.02705/) (2024)
- [No Task Left Behind: Isotropic Model Merging with Common and Task-Specific Subspaces](https://mlsanity.com/paper/2502.04959/) (2025)
- [On Mixup Regularization](https://mlsanity.com/paper/2006.06049/) (2020)
- [Morphological Prototyping for Unsupervised Slide Representation Learning in Computational Pathology](https://mlsanity.com/paper/2405.11643/) (2024)
- [Multimodal Prototyping for cancer survival prediction](https://mlsanity.com/paper/2407.00224/) (2024)
- [Modeling Multi-Task Model Merging as Adaptive Projective Gradient Descent](https://mlsanity.com/paper/2501.01230/) (2025)
- [AdvMIL: Adversarial Multiple Instance Learning for the Survival Analysis on Whole-Slide Images](https://mlsanity.com/paper/2212.06515/) (2022)
- [Interpretable Vision-Language Survival Analysis with Ordinal Inductive Bias for Computational Pathology](https://mlsanity.com/paper/2409.09369/) (2024)
- [Robust Multimodal Survival Prediction with the Latent Differentiation Conditional Variational AutoEncoder](https://mlsanity.com/paper/2503.09496/) (2025)
- [Task Groupings Regularization: Data-Free Meta-Learning with Heterogeneous Pre-trained Models](https://mlsanity.com/paper/2405.16560/) (2024)
- [DPsurv: Dual-Prototype Evidential Fusion for Uncertainty-Aware and Interpretable Whole-Slide Image Survival Prediction](https://mlsanity.com/paper/2510.00053/) (2025)

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

- [Semantic-Anchored Evidential Fusion for Domain-Robust Whole-Slide Survival Analysis](https://mlsanity.com/paper/2606.19966/) (2026)
- [Evidential Fusion Network for Multimodal Survival Prediction under Missing Modalities](https://mlsanity.com/paper/2606.20757/) (2026)

## Abstract (arXiv)

Whole-Slide Images (WSIs) are widely used for estimating the prognosis of cancer patients. Current studies generally follow a cancer-specific learning paradigm. However, the available training samples for one cancer type are usually scarce in pathology. Consequently, the model often struggles to learn generalizable knowledge, thus performing worse on the tumor samples with inherent high heterogeneity. Although multi-cancer joint learning and knowledge transfer approaches have been explored recently to address it, they either rely on large-scale joint training or extensive inference across multiple models, posing new challenges in computational efficiency. To this end, this paper proposes a new scheme, Sparse Task Vector Mixup with Hypernetworks (STEPH). Unlike previous ones, it efficiently absorbs generalizable knowledge from other cancers for the target via model merging: i) applying task vector mixup to each source-target pair and then ii) sparsely aggregating task vector mixtures to obtain an improved target model, driven by hypernetworks. Extensive experiments on 13 cancer datasets show that STEPH improves over cancer-specific learning and an existing knowledge transfer baseline by 5.14% and 2.01%, respectively. Moreover, it is a more efficient solution for learning prognostic knowledge from other cancers, without requiring large-scale joint training or extensive multi-model inference. Code is publicly available at https://github.com/liupei101/STEPH.