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

6 results for “graph-driven”

Graph-Driven Generative Models for Heterogeneous Multi-Task Learningcs.LG

Unified model for multiple healthcare tasks using graph structure.

problem Multiple healthcare tasks with shared graph structure.

method Graph-Convolutional Network (GCN) with multiple variational autoencoders.

result Boosted performance across all tasks, outperforming state-of-the-art.

Graph-Driven Generative Models Heterogeneous Multi-Task Healthcare

2019-11-20abs ↗pdf ↗

Block Model Guided Unsupervised Feature Selectioncs.LG

A new method selects features for clustering using a block model.

problem Finding high-quality features for clustering in linked data.

method Building a block model on the graph and using it for feature selection.

result BMGUFS outperforms state-of-the-art methods in clustering performance.

feature selection graph-driven unsupervised block model clustering

2020-07-05abs ↗pdf ↗

CREIMBO: Cross-Regional Ensemble Interactions in Multi-view Brain Observationsq-bio.NC

CREIMBO models diverse brain activity by identifying hidden neural sub-circuits and their non-stationary interactions.

problem Lack of alignment in neural recordings limits analysis of brain-wide dynamics.

method CREIMBO learns a unified model of neural dynamics by assuming multiple hidden global sub-circuits representing ensemble interactions.

result CREIMBO discovers session-specific neural ensembles and their non-stationary interactions, revealing cross-subject neural mechanisms.

neural dynamics ensemble interactions multi-view brain observations graph-driven dictionary learning low-dimensional manifold

2024-05-27abs ↗pdf ↗

An experimental study of graph-based semi-supervised classification with additional node informationstat.ML

The volume of data generated by internet and social networks is increasing every day, and there is a clear need for efficient ways of extracting useful information from them. As those data can take different forms, it is important to use all the available data representations for prediction. In this paper, we focus our…

2017-05-24abs ↗pdf ↗

Zero-Copy Semantic Contagion: An In-Memory Streaming Architecture for Evolving Attention Graphscs.LG

Zero-Copy Architecture Detects Cross-Company Financial Signals Instantly.

problem Financial models miss cross-company disruptions due to static data.

method Heterogeneous Rust-Python streaming architecture that maps cross-company attention as a continuous-time graph.

result Zero-copy parsing and inference process delivers real-time cross-company signal detection.

financial forecasting cross-company propagation Rust-Python Neural Hawkes Process continuous-time graph

2026-06-04abs ↗pdf ↗

Combinatorially random curves on surfacesmath.GT

Random curves on surfaces have predictable properties as they grow.

problem Characterizing topological properties of random curves on surfaces.

method Analyzing a simple random walk on the Cayley graph of surface groups.

result The properties of random curves are generic and predictable as they grow.

random curves Teichmüller space self-intersection dilatation pseudo-Anosov

2022-09-22abs ↗pdf ↗