On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,742 papers · 148 categories

Trend · papers per month

count % of corpus

3 results for “topology-guided”

PTOPOFL: Privacy-Preserving Personalised Federated Learning via Persistent Homologycs.LG

PTOPOFL uses topological descriptors to protect privacy in federated learning.

problem Privacy and data reconstruction attacks in federated learning.

method PTOPOFL replaces gradient communication with persistent homology feature vectors for privacy and topology-guided aggregation.

result PTOPOFL achieves higher AUC and reduces reconstruction risk compared to gradient sharing.

federated learning persistent homology privacy-preserving federated aggregation topology-guided

2026-03-04abs ↗pdf ↗

Topological Inductive Bias fosters Multiple Instance Learning in Data-Scarce Scenarioscs.LG

Enhances MIL performance in scarce data scenarios using topological inductive biases.

problem Low performance of MIL in data-scarce scenarios.

method Incorporates topological inductive biases into MIL framework.

result Average performance improvements of 15.3% for synthetic datasets, 2.8% for benchmarks, and 5.5% for rare anemia classification.

MIL topological inductive biases data scarcity weakly supervised learning sparse data

2023-07-26abs ↗pdf ↗

Combining Geometric and Topological Information for Boundary Estimationeess.IV

A fundamental problem in computer vision is boundary estimation, where the goal is to delineate the boundary of objects in an image. In this paper, we propose a method which jointly incorporates geometric and topological information within an image to simultaneously estimate boundaries for objects within images with mo…

2019-10-10abs ↗pdf ↗