Research
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
0111 · Oct 201919922001200920172026
4 results for “via-node”
Experiments on route choice set generation using a large GPS trajectory setphysics.soc-ph

A large GPS dataset reveals that a single route often covers 60% of travel observations.

problem Limited insights from small GPS datasets on route choice behavior.
method Evaluation of path generation algorithms including link penalty, link elimination, simulation, and via-node methods.
result Modified link penalty method achieves 97% coverage, significantly higher than previous studies.
GPS trajectoryroute choicepath generationlink penaltyvia-node
2020-05-22abs ↗pdf ↗
Active Learning for Graph Neural Networks via Node Feature Propagationcs.LG

New method uses GNNs and node feature propagation for active learning in graph node classification.

problem Lack of labeled data for graph neural networks.
method Node feature propagation followed by K-Medoids clustering for instance selection.
result Proposed method significantly outperforms other methods on benchmark datasets.
Graph Neural NetworksActive LearningNode ClassificationNode Feature PropagationK-Medoids Clustering
2019-10-16abs ↗pdf ↗
Understanding the Limitations of Network Online Learningcs.LG

The paper explores how to learn from incomplete online social networks.

problem Learning from partially observed networks via node querying.
method Developed algorithms NOL* for sequential node querying to maximize network observability.
result It is possible to sequentially learn which nodes to query for maximal network observability.
network learningonline social mediapartial observationnode queryingexploration-exploitation
2020-01-09abs ↗pdf ↗
Rate-optimal community detection near the KS threshold via node-robust algorithmsstat.ML

New algorithm detects communities near KS threshold with optimal rate, even in noisy conditions.

problem Community detection in symmetric stochastic block models with noisy data.
method Polynomial-time algorithm using Sum-of-Squares framework and robust majority voting.
result Achieves minimax-optimal misclassification rate near Kesten-Stigum threshold, even with node corruption.
community detectionstochastic block modelKS thresholdnode robustnessSum-of-Squares
2025-11-20abs ↗pdf ↗