Region-Graph Optimal Transport Routing for Mixture-of-Experts Whole-Slide Image Classification
On the map: Mixture-of-experts → Medical and biomedical MoE
Abstract (arXiv)
Multiple Instance Learning (MIL) is the dominant framework for gigapixel whole-slide image (WSI) classification in computational pathology. However, current MIL aggregators route all instances through a shared pathway, constraining their capacity to specialise across the pathological heterogeneity inherent in each slide. Mixture-of-Experts (MoE) methods offer a natural remedy by partitioning instances across specialised expert subnetworks; yet unconstrained softmax routing may yield highly imbalanced utilisation, where one or a few experts absorb most routing mass, collapsing the mixture back to a near-single-pathway solution. To address these limitations, we propose ROAM (Region-graph OptimAl-transport Mixture-of-experts), a spatially aware MoE-MIL aggregator that routes region tokens to expert poolers via capacity-constrained entropic optimal transport, promoting balanced expert utilisation by construction. ROAM operates on spatial region tokens, obtained by compressing dense patch bags into spatially binned units that align routing with local tissue neighbourhoods and introduces two key mechanisms: (i) region-to-expert assignment formulated as entropic optimal transport (Sinkhorn) with explicit per slide capacity marginals, enforcing balanced expert utilisation without auxiliary load-balancing losses; and (ii) graph-regularised Sinkhorn iterations that diffuse routing assignments over the spatial region graph, encouraging neighbouring regions to coherently route to the same experts. Evaluated on four WSI benchmarks with frozen foundation-model patch embeddings, ROAM achieves performance competitive against strong MIL and MoE baselines, and on NSCLC generalisation (TCGA-CPTAC) reaches external AUC 0.845 +- 0.019.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Medical and biomedical MoE, one of 12 directions in Mixture-of-experts. Builds on 12 of its 23 references that are in the map. First posted on arXiv 8 Apr 2026.
Builds on
12 of 23 references.
References · 12
- 2017Inductive Representation Learning on Large Graphscited by 6,284
- 2021Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsitycited by 3,014
- 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,277
- 2020Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Imagescited by 738
- 2022Mixture-of-Experts with Expert Choice Routingcited by 611
- 2020Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learningcited by 473
- 2024Auxiliary-Loss-Free Load Balancing Strategy for Mixture-of-Expertscited by 191
- 2023Scalable Optimal Transport Methods in Machine Learning: A Contemporary Surveycited by 27
- 2025OTSurv: A Novel Multiple Instance Learning Framework for Survival Prediction with Heterogeneity-aware Optimal Transportcited by 8
- 2024SAM-MIL: A Spatial Contextual Aware Multiple Instance Learning Approach for Whole Slide Image Classificationcited by 6
- 2025Improving Routing in Sparse Mixture of Experts with Graph of Tokenscited by 4
- 2026Mixture of Mini Experts: Overcoming the Linear Layer Bottleneck in Multiple Instance Learningcited by 3
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026SlideMix: Enhancing Whole Slide Image Analysis via Multimodal Shuffling
- 2024MamMIL: Multiple Instance Learning for Whole Slide Images with State Space Models
- 2025PathRWKV: Enhancing Whole Slide Image Inference with Asymmetric Recurrent Modeling
- 2024M4: Multi-Proxy Multi-Gate Mixture of Experts Network for Multiple Instance Learning in Histopathology Image Analysis
- 2025SemaMIL: Semantic-Aware Multiple Instance Learning with Retrieval-Guided State Space Modeling for Whole Slide Images
- 2026Geometry-Aware State Space Model: A New Paradigm for Whole-Slide Image Representation
- 2026MoEMambaMIL: Structure-Aware Selective State Space Modeling for Whole-Slide Image Analysis
- 2025REN: Anatomically-Informed Mixture-of-Experts for Interstitial Lung Disease Diagnosis