tf_geometric simplifies graph deep learning in TensorFlow.
problem Efficient graph deep learning in TensorFlow.
method Kernel libraries and infrastructures for GNNs.
result tf_geometric supports various graph tasks and provides efficient GNN models.
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
48 results for “TF Model”
TF-GNN simplifies graph neural networks in TensorFlow.
problem Handling rich heterogeneous graph data in machine learning.
method A scalable library with a Keras message passing API.
result Enables low-code solutions for broader developers.
One of the fundamental tasks in understanding genomics is the problem of predicting Transcription Factor Binding Sites (TFBSs). With more than hundreds of Transcription Factors (TFs) as labels, genomic-sequence based TFBS prediction is a challenging multi-label classification task. There are two major biological mechan…
Time-frequency (TF) representations provide powerful and intuitive features for the analysis of time series such as audio. But still, generative modeling of audio in the TF domain is a subtle matter. Consequently, neural audio synthesis widely relies on directly modeling the waveform and previous attempts at unconditio…
We describe TF-Replicator, a framework for distributed machine learning designed for DeepMind researchers and implemented as an abstraction over TensorFlow. TF-Replicator simplifies writing data-parallel and model-parallel research code. The same models can be effortlessly deployed to different cluster architectures (i…
Improved TF-IDF for word relevance in health-care social media documents.
problem Determining word relevance in informal documents.
method Semantic Sensitive TF-IDF (STF-IDF) method.
result Decreased TF-IDF mean error rate by 50% to 13.7%.
A new term weighting scheme TF-IDFC-RF outperforms others in sentiment analysis.
problem Improving text classification in sentiment analysis.
method Proposes a novel supervised term weighting scheme TF-IDFC-RF and compares it with other schemes.
result TF-IDFC-RF outperforms all other schemes on two sentiment analysis datasets.
Switched latent force models for reverse-engineering transcriptional regulation in gene expression dataphysics.bio-ph
To survive environmental conditions, cells transcribe their response activities into encoded mRNA sequences in order to produce certain amounts of protein concentrations. The external conditions are mapped into the cell through the activation of special proteins called transcription factors (TFs). Due to the difficult …
Orthogonal matching pursuit (OMP) is a widely used compressive sensing (CS) algorithm for recovering sparse signals in noisy linear regression models. The performance of OMP depends on its stopping criteria (SC). SC for OMP discussed in literature typically assumes knowledge of either the sparsity of the signal to be e…
TF-Coder simplifies tensor manipulation programming in TensorFlow.
problem Difficulty in programming with TensorFlow due to steep learning curve.
method Bottom-up weighted enumerative search with value-based pruning and type/value filtering.
result Solves 63 out of 70 real-world tasks within 5 minutes.
We study on a new kind of surface covered by translation and factorable (TF-type) surfaces in the three dimensional Euclidean space. We consider I and III Laplace-Beltrami operator surfaces of a TF-type surface. Then we obtain degrees and classes of algebraic surfaces of the surfaces using eliminate methods on software…
A training-free message passing module improves hypergraph neural networks.
problem Computational intensive training process in hypergraph neural networks.
method Decoupling hypergraph structural information from model learning stage.
result TF-HNN achieves superior performance and training efficiency.
Unified approach to trend-following systems, deriving exact relationships and expected returns.
problem Designing and understanding trend-following systems in financial markets.
method Derive exact relationships, analyze expected returns, and use fractional ARFIMA processes.
result Profitability of trend-following systems depends on positive long-term autocorrelation and excess spectral mass at low frequencies.
ARA combines aggregated RAPPOR and Tf-Idf estimation for centralized DP analysis.
problem Gap between local and central DP approaches in terms of data storage, analysis speed, and amount of data.
method Collects RAPPOR reports from multiple clients, pushes them to a Tf-Idf estimation model, and analyzes them for centralized DP.
result Successfully and efficiently analyzed major truth values from multiple clients.
We consider a portfolio allocation problem for trend following (TF) strategies on multiple correlated assets. Under simplifying assumptions of a Gaussian market and linear TF strategies, we derive analytical formulas for the mean and variance of the portfolio return. We construct then the optimal portfolio that maximiz…
Paper solves convertible bond valuation using finite elements with penalty method.
problem Valuation of convertible bonds under penalty TF model.
method Solves TF system of equations using P1 and P2 finite elements with penalty method.
result Numerical solutions compare favorably with finite difference method.
TF-MoDISco (Transcription Factor Motif Discovery from Importance Scores) is an algorithm for identifying motifs from basepair-level importance scores computed on genomic sequence data. This technical note focuses on version v0.5.6.5. The implementation is available at https://github.com/kundajelab/tfmodisco/tree/v0.5.6…
We investigate the problem of wealth distribution from the viewpoint of asset exchange. Robust nature of Pareto's law across economies, ideologies and nations suggests that this could be an outcome of trading strategies. However, the simple asset exchange models fail to reproduce this feature. A yardsale(YS) model in w…
TF Boosted Trees (TFBT) is a new open-sourced frame-work for the distributed training of gradient boosted trees. It is based on TensorFlow, and its distinguishing features include a novel architecture, automatic loss differentiation, layer-by-layer boosting that results in smaller ensembles and faster prediction, princ…
Develops probabilistic models for gene regulatory network inference.
problem Challenges in reconstructing gene regulatory networks from genome-wide data.
method Two complementary frameworks: PMF-GRN and GLM-Prior.
result Probabilistic inference refines regulatory estimates with quantified uncertainty.
Improves document summarization by combining word embeddings and n-grams.
problem Exact word matching fails to measure semantic similarity between sentences.
method Uses deep embedding features and tf-idf features to improve sentence similarity measure; builds an improved sentence similarity graph; employs a submodular objective function; develops a Transformer-based compression model.
result Outperforms tf-idf based approach and achieves state-of-the-art performance on DUC04 dataset.
Orthogonal matching pursuit (OMP) and orthogonal least squares (OLS) are widely used for sparse signal reconstruction in under-determined linear regression problems. The performance of these compressed sensing (CS) algorithms depends crucially on the \textit{a priori} knowledge of either the sparsity of the signal ($k_…
The paper shows non-aspherical path components in G2-moduli spaces.
problem Characterizing non-aspherical path components in G2-moduli spaces.
method Using generalised Kummer construction and resolving singularities with Eguchi-Hanson spaces, the authors establish a fibration over each path component with Eilenberg Mac Lane spaces as fibres.
result The comparison map is a fibration over each path component with Eilenberg Mac Lane spaces as fibres, indicating non-trivial families of G2-manifolds.
PCGS-TF uses a Transformer to adaptively control expert switching in non-stationary environments.
problem Static regret is insufficient for strictly online prediction in non-stationary settings.
method Policy-Controlled Generalized Share (PCGS) with a Transformer as an update controller.
result PCGS-TF achieves the lowest dynamic regret in non-stationary families and expert pools.
Topological Data Analysis in Text Classification: Extracting Features with Additive Informationcs.LG
Paper explores applying TDA to text classification, improving model performance.
problem Applying TDA to text classification is challenging due to the complexity of text geometry.
method Used word embeddings and TF-IDF vectors to extract topological features from text.
result Topological features improve classification results, especially in ensemble models.
Robust Bayesian Tensor Factorization with Zero-Inflated Poisson Model and Consensus Aggregationstat.ML
Paper introduces ZIPTF and C-ZIPTF for better tensor factorization of zero-inflated count data.
problem Inefficient tensor factorization for zero-inflated count data, especially in scRNA-seq.
method Zero Inflated Poisson Tensor Factorization (ZIPTF) and Consensus Zero Inflated Poisson Tensor Factorization (C-ZIPTF).
result ZIPTF and C-ZIPTF improve tensor factorization accuracy and consistency for zero-inflated count data.
A Pathology report is arguably one of the most important documents in medicine containing interpretive information about the visual findings from the patient's biopsy sample. Each pathology report has a retention period of up to 20 years after the treatment of a patient. Cancer registries process and encode high volume…
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.
Anchors explain text model decisions by highlighting key words.
problem Explaining neural network decisions for text data.
method Formalized Anchors for text classification, analyzing different models.
result Neural network words with highest partial derivatives are selected by Anchors.
While deep learning has shown tremendous success in a wide range of domains, it remains a grand challenge to incorporate physical principles in a systematic manner to the design, training, and inference of such models. In this paper, we aim to predict turbulent flow by learning its highly nonlinear dynamics from spatio…
Anchors explains text classifiers by highlighting key words.
problem Interpreting machine learning models, especially for text classifiers.
method Formalizes Anchors' algorithm and analyzes its behavior on linear text classifiers.
result Anchors produces meaningful results on linear text classifiers.
In this paper, we compare various methods to compress a text using a neural model. We find that extracting tokens as latent variables significantly outperforms the state-of-the-art discrete latent variable models such as VQ-VAE. Furthermore, we compare various extractive compression schemes. There are two best-performi…
X-DC improves speech separation by making DNNs more interpretable.
problem Black-box nature of DNNs in speech separation tasks.
method Introduces X-DC, a DNN architecture that interprets as spectrogram template fitting followed by Wiener filtering.
result X-DC achieves comparable speech separation performance to DC but with enhanced interpretability.
While there has been much recent progress using deep learning techniques to separate speech and music audio signals, these systems typically require large collections of isolated sources during the training process. When extending audio source separation algorithms to more general domains such as environmental monitori…
This study analyzes app reviews to understand students' behavior in the app market.
problem Extracting sentiment from growing app reviews manually is impractical.
method Used machine learning algorithms with TF-IDF for text representation and ensemble learning for evaluation.
result SVM achieved the highest accuracy (93.37%) on tri-gram + TF-IDF scheme.
BERT outperforms traditional machine learning in text classification tasks.
problem Comparing BERT to traditional machine learning methods for text classification.
method Empirical testing of BERT against TF-IDF-based machine learning models in various scenarios.
result BERT demonstrates superior performance and independence from text features.
In text mining, information retrieval, and machine learning, text documents are commonly represented through variants of sparse Bag of Words (sBoW) vectors (e.g. TF-IDF). Although simple and intuitive, sBoW style representations suffer from their inherent over-sparsity and fail to capture word-level synonymy and polyse…
In spite of the amazing results obtained by deep learning in many applications, a real intelligent behavior of an agent acting in a complex environment is likely to require some kind of higher-level symbolic inference. Therefore, there is a clear need for the definition of a general and tight integration between low-le…
Punctuated Equilibrium (PE) states that after long periods of evolutionary quiescence, species evolution can take place in short time intervals, where sudden differentiation makes new species emerge and some species extinct. In this paper, we introduce and study the effect of punctuated equilibrium on two different ass…
We consider the two logarithmic strain measures\[ω_{\rm iso}=\|\mathrm{dev}_n\log U\|=\|\mathrm{dev}_n\log \sqrt{F^TF}\|\quad\text{ and }\quad ω_{\rm vol}=|\mathrm{tr}(\log U)|=|\mathrm{tr}(\log\sqrt{F^TF})|\,,\]which are isotropic invariants of the Hencky strain tensor , and show that they can be uniquely char…
Influence functions help study large language model generalization, revealing surprising decay patterns.
problem Understanding and mitigating risks in large language models (LLMs).
method Eigenvalue-corrected Kronecker-Factored Approximation (EK-FAC) to scale influence functions to LLMs.
result Influences decay to near-zero when key phrases order is flipped, revealing a surprising limitation.
In previous papers (arxiv:math/0612370 and arxiv:0909.1342) we defined the C*-algebra and the longitudinal pseudodifferential calculus of any singular foliation (M,F). Here we construct the analytic index of an elliptic operator as a KK-theory element, and prove that the same element can be obtained from an "adiabatic …
OLinear forecasts time series more efficiently by transforming data orthogonally.
problem Efficiently forecasting time series with entangled dependencies.
method OLinear uses OrthoTrans to transform data orthogonally, then applies NormLin for linear layer.
result OLinear achieves state-of-the-art performance with high efficiency.
Study detects fake news in Brazilian Portuguese using machine learning.
problem Spread of misinformation through fake news in Brazilian Portuguese.
method Machine learning, TF-IDF, Word2Vec, classification algorithms.
result High accuracy and F1-Score in identifying fake news.
E-commerce websites such as Amazon, Alibaba, Flipkart, and Walmart sell billions of products. Machine learning (ML) algorithms involving products are often used to improve the customer experience and increase revenue, e.g., product similarity, recommendation, and price estimation. The products are required to be repres…
Study the limit of Calabi-Yau metrics with degenerate skeletons.
problem Understanding the behavior of Calabi-Yau metrics with degenerate skeletons.
method Using polarised degenerations and optimal transport problems.
result Describe the limiting behaviour of the Calabi-Yau potential.
This paper describes multichannel speech enhancement for improving automatic speech recognition (ASR) in noisy environments. Recently, the minimum variance distortionless response (MVDR) beamforming has widely been used because it works well if the steering vector of speech and the spatial covariance matrix (SCM) of no…
The task of determining item similarity is a crucial one in a recommender system. This constitutes the base upon which the recommender system will work to determine which items are more likely to be enjoyed by a user, resulting in more user engagement. In this paper we tackle the problem of determining song similarity …