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.

169,341 papers · 148 categories

Trend · papers per month

236473709945 · Jun 202019922001200920182026
48 results for network metadata

New research shows treating metadata as ground truth in network analysis leads to significant problems.

problem The use of metadata as ground truth in community detection leads to theoretical and practical issues.
method Theoretical analysis and statistical techniques to quantify the relationship between metadata and community structure.
result No algorithm can uniquely solve community detection, and treating metadata as ground truth is problematic.

MONET debiases graph embeddings by training on metadata-orthogonal dimensions.

problem Graph embeddings can be biased by node attributes, affecting fairness and interpretability.
method MONET trains embeddings on a hyperplane orthogonal to node metadata.
result MONET effectively removes bias from node embeddings, improving fairness and interpretability.

We introduce the nonparametric metadata dependent relational (NMDR) model, a Bayesian nonparametric stochastic block model for network data. The NMDR allows the entities associated with each node to have mixed membership in an unbounded collection of latent communities. Learned regression models allow these memberships…

2012-06-27abs ↗pdf ↗

The study uses supervised learning to classify research data by discipline.

problem Automatically categorizing research data by discipline for scientometric analysis.
method Used a large dataset of 609,524 records for training and evaluation, employing tree-based models and neural networks.
result Multi-layer perceptron models outperformed Long Short-Term Memory models in multi-label classification tasks.

Paper proposes a method to improve graph clustering by integrating node textual metadata with node signals in GGMs.

problem Graph learning in Gaussian Graphical Models with auxiliary node metadata.
method Laplacian-constrained Gaussian Graphical Models with majorization-minimization algorithm.
result The proposed method outperforms state-of-the-art approaches that use either signals or metadata alone.

FLAMECHE solves the CFL trilemma by enabling encryption-compatible metadata-based clustering.

problem The CFL trilemma: improving two dimensions of privacy, communication, and computation comes at the expense of the third.
method FLAMECHE reformulates metadata-based CFL as a distributed EM procedure, allowing compatibility with secure FL schemes.
result FLAMECHE improves the effectiveness of client models and enables encryption-compatible clustering.

Enhances topic-metadata relationship modeling using Bayesian methods.

problem Estimating relationships between latent topics and metadata in topic modeling.
method Proposes modifications to the method of composition, using Beta regression and a fully Bayesian approach.
result Improves quantification of uncertainty in topic-metadata relationships.

MetaDVFS uses device and application metadata to improve DVFS efficiency.

problem Improving energy efficiency in mobile platforms with diverse applications and hardware.
method Formulates DVFS as a multi-task reinforcement learning problem and introduces MetaDVFS, leveraging metadata for knowledge transfer.
result MetaDVFS achieves up to 26% improvement in Quality of Experience and up to 17% improvement in Performance-Power Ratio.

The paper examines how NFT valuations correlate with market data and social trends.

problem Predicting NFT valuations based on market data and social trends.
method Utilizes public market data, NFT metadata, and social trends data; employs linear regression and recurrent neural networks.
result Identifies correlations between NFT valuations and various features.

Deep neural network predicts cardiac shape from MRI images and patient data.

problem Automatic 3D cardiac shape analysis for large-scale studies.
method Uses deep neural networks combining MRI images and patient metadata.
result Significant agreement with reference shapes in cardiac parameters.

LLMs learn to recommend models and hyperparameters from dataset metadata.

problem Model and hyperparameter selection in machine learning is challenging and resource-intensive.
method Converted datasets into metadata and prompted LLMs to recommend models and hyperparameters.
result LLMs can recommend competitive models and hyperparameters without search.

Improved 3D MRI classification using contrastive learning with continuous proxy metadata.

problem Insufficient labelled data for 3D medical image classification.
method Proposed a new loss function (y-Aware InfoNCE) to leverage continuous proxy metadata in contrastive learning.
result 3D CNN model pre-trained on 10^4 multi-site healthy brain MRI scans outperforms fully-supervised methods.

SEMASIA provides a large dataset of latent representations for model comparison.

problem Difficulty in comparing semantic structures across different neural network models.
method Collection of latent representations from 1700 pretrained models across various benchmarks.
result Consistent semantic organization across models and datasets.

A novel multilayer network approach for text analysis.

problem Clustering documents and finding topics in large collections with metadata and hyperlinks.
method Multilayer Networks and Stochastic Block Models applied to multiple data types.
result Taking into account multiple types of information improves topic and document clustering.

Study improves ECG analysis accuracy using state space models, self-supervised learning, and patient metadata.

problem Improving quantitative accuracy of ECG analysis using deep learning.
method Explored state space models, self-supervised learning, and patient metadata integration.
result Improved ECG analysis accuracy through these components, no significant advantage from higher sampling rates or longer input sizes.

The paper evaluates machine learning for song similarity based on metadata and user tags.

problem Determining song similarity using metadata and user tags.
method Machine learning algorithms including tf-idf, Word2Vec, k-NN, and SVM were evaluated.
result tf-idf outperformed Word2Vec in modeling song metadata, and k-NN outperformed SVM and Linear Regression.

Meta-learning improves model performance by optimizing data acquisition.

problem Lack of operationally realistic data limits model performance.
method Gaussian process surrogate fit to metadata-driven training data variations.
result Meta-learning enhances model performance compared to random data acquisition.

Improved malware detection by adding auxiliary loss terms to a neural network.

problem Malware detection accuracy with a single label.
method Fit deep neural networks to multiple auxiliary prediction targets derived from metadata.
result Significant improvement in detection performance, reducing false negatives by 42.6% at a low false positive rate.

We create a large dataset for fact checking claims and improve prediction accuracy.

problem Fact checking claims from multiple sources is challenging.
method We created a comprehensive dataset and developed a novel method for automatic veracity prediction.
result Our model achieves a Macro F1 of 49.2%, showing significant performance improvements.

New feature mapping approach improves recommendation accuracy and explainability.

problem Balancing recommendation accuracy and explainability using metadata.
method Maps uninterpretable features to interpretable aspect features, minimizing both prediction and interpretation losses.
result Strong performance in recommendation and explainability, eliminating metadata need.

This research predicts the popularity of new video contents using a hybrid machine learning approach.

problem Predicting the popularity of new video contents before they are published.
method Hybrid machine learning approach combining XGBoosting and deep neural nets, using metadata and categorical embedding techniques.
result Achieved better performance than standalone methods, validated on a dataset from a top streaming service.

New method uses LLMs to extract financial insights from Q&A sections of reports.

problem Scalability and accuracy issues in extracting valuable insights from financial report Q&A sections.
method Combines retrieval-augmented generation technique with metadata.
result Empirically demonstrates superior performance of the proposed method.

New dissimilarity measures enhance affinity propagation for complex network clustering.

problem Improving community detection in complex networks using affinity propagation.
method Leverage network latent geometry to design dissimilarity matrices.
result Affinity propagation outperforms state-of-the-art methods in community detection.

Zero-shot understanding of accidents from surveillance videos using vision-language models

problem Accident understanding from surveillance videos
method Three-stage pipeline with vision-language similarity, metadata-driven multi-prompt reasoning, and entropy-gated pairwise adjudicator
result Substantial improvement in harmonic-mean score over baseline

A novel deep learning method predicts Twitter users' locations using multiple data types.

problem Predicting Twitter users' locations on large social networks.
method Combines content-based and network-based approaches using a multi-entry neural network architecture (MENET).
result MENET outperforms state-of-the-art methods by a large margin on three benchmark datasets.

TorchIO simplifies medical image processing for deep learning.

problem Challenges in processing medical images like MRI and CT.
method Efficient loading, preprocessing, augmentation, and patch-based sampling.
result Enables researchers to focus on deep learning experiments.