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.

169,291 papers · 148 categories

Trend · papers per month

5.2%10.4%15.6%20.8% · May 202619922001200920182026
48 results for citation prediction

The paper proposes a novel model to forecast patent citations using multi-attention recurrent networks.

problem Forecasting forward citations to patents to discover emerging technologies.
method The approach employs a sequence-to-sequence model with an attention-of-attention mechanism to capture dependencies in multiple time sequences.
result The proposed model outperforms state-of-the-art models in forward citation forecasting.

Interactive tool improves prediction accuracy in small datasets.

problem Challenges in machine learning with small data sets and tacit expert knowledge.
method Interactive visualization and user model to elicit feature relevance.
result User model significantly improves prediction accuracy and prior knowledge elicitation.

A multi-task model tackles citation purpose classification with limited data.

problem Classifying citations based on their purpose is challenging due to limited labeled data and subjectivity.
method Combines linguistic features, TF-IDF, and an LSTM-with-attention model for multi-task learning.
result Improves classification accuracy compared to single-task models.

Measuring the impact of scientific articles is important for evaluating the research output of individual scientists, academic institutions and journals. While citations are raw data for constructing impact measures, there exist biases and potential issues if factors affecting citation patterns are not properly account…

2015-02-25abs ↗pdf ↗

Advances citation and subject label recommendation using multi-modal adversarial autoencoders.

problem Improving recommendation systems for citations and subject labels.
method Multi-modal adversarial autoencoders with adversarial regularization, sparsity, and input modality analysis.
result Adversarial regularization consistently improves recommendation performance.

Synthetic reference strings are as effective as real ones for training citation parsing models.

problem Lack of training data for citation parsing, especially with deep neural networks.
method Trained Grobid with human-labelled and synthetically created reference strings, and evaluated retraining and out-of-sample data impact.
result Synthetic and real reference strings are equally effective for training Grobid, with retraining improving performance.

A combined model integrates latent factor and logistic regression for citation network analysis.

problem Insufficient representation by either latent factor or logistic regression alone.
method Proposes a combined model integrating latent factor and logistic regression, with parameter estimation through joint-likelihood and penalty terms.
result The proposed method captures both main technological trends and ad-hoc dependencies in citation networks.

A novel model-selection method for dynamic networks using synthetic data.

problem Classifying and understanding the growth mechanisms of dynamic networks.
method Training a classifier on synthetic network data generated by nine random graph models, using dynamic features that count new links.
result Achieves near-perfect classification of synthetic networks, outperforming state-of-the-art methods.

Network-assisted regression uses conformal prediction for valid inference.

problem Predicting node attributes using network and conventional covariates with valid statistical inference.
method Network analog of conformal prediction under mild joint exchangeability assumption.
result Achieves finite sample validity and asymptotic conditional validity for various network covariates.

VGAE learns latent representations for graphs using latent variables.

problem Learning interpretable latent representations for undirected graphs.
method Variational auto-encoder framework with graph convolutional network encoder and inner product decoder.
result VGAE achieves competitive link prediction results and improves performance with node features.

Bibliographic analysis considers author's research areas, the citation network and paper content among other things. In this paper, we combine these three in a topic model that produces a bibliographic model of authors, topics and documents using a non-parametric extension of a combination of the Poisson mixed-topic li…

2016-09-22abs ↗pdf ↗

Improves Graph Convolutional Network performance on citation datasets.

problem Improving Graph Convolutional Network performance on citation datasets.
method Exploring graph regularization and alternative graph convolution approaches.
result Explicit graph regularization was incorrectly rejected by Kipf & Welling (2016).

Visuals in scientific papers are used to express complex ideas; this study uses them to identify knowledge domains.

problem Scientific figures are underutilized in literature analysis.
method Encoded scientific figures into visual signatures and used distances between signatures to compare communities of practice.
result Figures can differentiate knowledge domains as effectively as text or citation patterns.

Researchers use estimated Kolmogorov complexity for better link prediction in graphs.

problem Improving link prediction accuracy in complex networks.
method Regularization based on an approximation of Kolmogorov complexity, which is differentiable and compatible with recent link prediction algorithms.
result The regularization method shows good performance on diverse real-world networks, but the success is likely due to an aggregation method rather than actual estimation of Kolmogorov complexity.

Improved AI patent classifier measures U.S. and China's AI patenting.

problem Measuring AI patents with high precision and generalization.
method Fine-tuning PatentSBERTa on manually labeled data from USPTO's AI Patent Dataset.
result Rapid growth in AI patenting in both countries, but different organizational patterns.

Derives formulae for general permutation equivariant layers and presents a second order graph variational encoder.

problem Tackles the limitation of previous equivariant neural networks by considering permutations of matrices.
method Derives formulae for general permutation equivariant layers, including matrix permutations. Presents a second order graph variational encoder.
result Latent distribution of equivariant generative models must be exchangeable.

Paper introduces a core-periphery model for identifying informative network structures.

problem Noise and bias in non-informative periphery structures obscure the informative core in complex networks.
method Spectral algorithms for core identification as a preprocessing step for network analysis.
result The proposed method outperforms traditional core-periphery methods in various downstream tasks.

Proposes dynamic graph and node feature learning in GCNNs for better adaptability.

problem Fixed graphs for all GCNN layers limit adaptability to node feature structures.
method Dynamic graph and node feature learning using Mahalanobis distance metric.
result Superior performance in point clouds and citation networks.

DREAM model improves computational efficiency for non-linear effects in relational event models.

problem Efficiently modeling non-linear effects in dynamic relational networks.
method Introduces Deep Relational Event Additive Model (DREAM) using Neural Additive Models.
result Demonstrates superior computational efficiency compared to traditional REM approaches.

A new HGNN framework for complex data representation learning.

problem Learning representation for complex data in hypergraph structures.
method Designing hyperedge convolution operations for hypergraph learning.
result HGNN outperforms state-of-the-art methods in citation network and visual object recognition tasks.

Many data sets contain rich information about objects, as well as pairwise relations between them. For instance, in networks of websites, scientific papers, and other documents, each node has content consisting of a collection of words, as well as hyperlinks or citations to other nodes. In order to perform inference on…

2013-03-28abs ↗pdf ↗

Many inference problems in structured prediction are naturally solved by augmenting a tractable dependency structure with complex, non-local auxiliary objectives. This includes the mean field family of variational inference algorithms, soft- or hard-constrained inference using Lagrangian relaxation or linear programmin…

2015-03-04abs ↗pdf ↗

EVGAE improves VGAE's latent representation learning by mitigating over-pruning.

problem Over-pruning in VGAE limits latent variable capacity and diversity.
method EVGAE uses epitomic approach with multiple sparse VGAE models (epitomes) to increase active latent units and improve generative ability.
result EVGAE outperforms VGAE in generative ability and link prediction on citation networks.

We present a scalable approach for semi-supervised learning on graph-structured data that is based on an efficient variant of convolutional neural networks which operate directly on graphs. We motivate the choice of our convolutional architecture via a localized first-order approximation of spectral graph convolutions.…

2016-09-09abs ↗pdf ↗