iStructTab improves multimodal learning by optimizing feature sequencing.
problem Redundancy, dispersion, and generalization issues in multimodal learning of images and tabular data.
method Graph-Enhanced Descriptor Sequencing (GEDS) algorithm that refines statistical descriptors through similarity graph-based computations.
result iStructTab effectively minimizes feature dispersion, improving predictive performance and robustness.
The study forecasts, reconstructs, and selects features of ocean waves using neural networks.
problem Forecasting, reconstructing, and feature selection of ocean waves.
method Recurrent and sequence-to-sequence neural networks, Bayesian hyperparameter optimization, Elastic Net method.
result Proposed methods outperform alternatives in significant wave height reconstruction.
Framework for renewable energy forecasting and feature engineering.
problem Forecasting and feature extraction for multivariate processes in renewable energy.
method Derivative-free optimization, ensemble of sequence-to-sequence networks, additive resampling, Bootstrap aggregating.
result The proposed method outperforms other machine learning techniques in long-term forecasts and feature selection.
A model learns stock trading rules from raw prices using encoder-decoder neural network.
problem Extracting features from long price sequences for profitable trading rules.
method Neural encoder-decoder framework combined with DRL.
result The model outperforms state-of-the-art models in dynamic environments.
Set-Sequence model learns cross-sectional dynamics directly from time series data.
problem Predicting large cross-sections of time series data with latent cross-sectional dynamics.
method A model that learns cross-sectional structure directly, enhancing expressivity and eliminating manual feature engineering.
result Significantly outperforms strong baselines in equity portfolio optimization and loan risk prediction.
Investigates neural TTS systems for Japanese and English.
problem Improving neural TTS systems for high-quality speech synthesis.
method Comparative study of neural sequence-to-sequence TTS vs. DNN pipeline TTS, varying model architecture, parameter size, and language.
result A neural sequence-to-sequence TTS system requires sufficient model parameters and a powerful encoder for high-quality speech synthesis.
A new approach models credit card transactions using HMMs to detect fraud.
problem Detecting credit card fraud using isolated event analysis.
method Model sequences from three perspectives using HMMs and combine likelihoods as features.
result Improved fraud detection effectiveness compared to state-of-the-art methods.
IGLOO slices features space to process long sequences efficiently.
problem Efficiency in processing long sequences with neural networks.
method Slicing features space into non-local patches and using their relationships to build sequence representations.
result IGLOO can handle dependencies up to 20,000 steps efficiently.
A new method predicts protein functions using variable-length sequences.
problem Computational methods for protein function prediction are slow and inaccurate for long sequences.
method Two feature sets: single fixed-sized segments and multi-sized segments, using bi-directional LSTM. Combined with MLDA features.
result Significant improvement in accuracy for long protein sequences.
MT-VAE learns motion transitions for generating diverse future motions.
problem Learning long-term human motion sequences with transitions.
method Jointly learns motion mode embeddings and transitions using Variational Auto-Encoders.
result Generates multiple plausible future motion sequences from input.
Machine learning identifies math sequences based on empirical laws.
problem Identifying interesting mathematical structures.
method Extract features from integer sequences using Benford's and Taylor's laws; experiment with classifiers.
result Machine learning can identify various mathematical properties in sequences.
Nowadays, hyperspectral image classification widely copes with spatial information to improve accuracy. One of the most popular way to integrate such information is to extract hierarchical features from a multiscale segmentation. In the classification context, the extracted features are commonly concatenated into a lon…
Unsupervised framework learns symmetry from time sequences.
problem Learning symmetry from time sequences without labeled data.
method Meta-sequential prediction (MSP) framework that leverages stationary properties.
result Hidden disentangled structure emerges as a by-product of training.
Graph-structured data appears frequently in domains including chemistry, natural language semantics, social networks, and knowledge bases. In this work, we study feature learning techniques for graph-structured inputs. Our starting point is previous work on Graph Neural Networks (Scarselli et al., 2009), which we modif…
Sequence feature embedding is a challenging task due to the unstructuredness of sequence, i.e., arbitrary strings of arbitrary length. Existing methods are efficient in extracting short-term dependencies but typically suffer from computation issues for the long-term. Sequence Graph Transform (SGT), a feature embedding …
Enhances sequence labeling with embedded-state latent CRFs.
problem Complex non-local constraints between sequence labels.
method Integrates multiple hidden states with low-rank log-potential scoring matrices.
result Model outperforms baseline CRF+RNN models with global constraints.
Seq-SetNet processes sequence sets directly, improving protein structure prediction.
problem Processing sequence sets (MSAs) for structural inference without considering sequence order.
method Developed a symmetric function module to integrate features from MSAs.
result Seq-SetNet outperforms state-of-the-art approaches by 3.6% in precision.
Study develops advanced models to forecast complex LOB data.
problem Forecasting high-frequency data in a limit order book (LOB).
method Advanced multidimensional sequence-to-sequence models with compound multivariate embedding.
result Method outperforms other multivariate forecasting methods, achieving lowest forecasting error.
Graph ConvNet improves ncRNA classification accuracy.
problem Classifying non-coding RNA sequences into families.
method Graph Convolutional Network model trained on raw RNA graphs.
result 85.73% accuracy and 85.61% F1-score over 13 classes.
Paper examines trade/no trade patterns in illiquid stocks, highlighting effects of varying zero returns probabilities.
problem Detecting long-run trade/no trade effects in illiquid stocks with varying zero returns probabilities.
method Proposes a framework considering constant and time-varying zero returns probabilities, analyzing trade/no trade categorical sequences.
result Long-run trade/no trade effects may be spuriously detected in presence of non-constant zero returns probabilities.
NCRF transducers improve sequence labeling across tasks.
problem Sequence labeling with non-linear node potentials.
method Two RNNs: one for features and one for long-range label dependencies.
result Consistent improvements over linear-chain NCRFs and RNN transducers.
New method classifies protein structures using network features.
problem Efficiently predicting protein function from structural data.
method Modelled protein structures as PSNs, used graphlets and deep learning for features.
result Proposed methods outperform existing PSC approaches in accuracy.
iPromoter-BnCNN identifies and classifies six types of sigma promoters.
problem Accurate classification of sigma promoters remains challenging.
method Convolutional Neural Network (CNN) combining local features.
result Supremacy on 5-fold cross-validation and independent test datasets.
Framework aligns datasets using harmonic expansion of intrinsic geometry.
problem Combining datasets from different modalities or correcting batch effects.
method Alignment through harmonic expansion of diffusion coordinates.
result Unified diffusion geometry for fused or corrected data.
Paper improves video feature learning for better downstream tasks.
problem Improving video feature learning for better performance on downstream tasks.
method Self-supervised learning approach using contrastive bidirectional transformer, extending BERT for real-valued feature vectors.
result Significantly improved performance on video classification, captioning, and segmentation tasks.
This study examines a single attention layer's capabilities using random features.
problem Understanding the learning and generalization of a single multi-head attention layer.
method Random feature setting with large number of heads, frozen query and key matrices, and trainable value matrices.
result Random-feature attention layer can express a broad class of permutation-invariant target functions.
GTI network learns linguistic features for multi-task sequence tagging.
problem Improving neural model performance on multi-task sequence tagging without explicit features.
method GTI network with neural gate modules to learn relations between tasks.
result GTI network outperforms baselines on chunking and NER tasks.
Paper presents a novel approach for global feature aggregation in Graph Neural Networks.
problem Graphs lack a straightforward way to perform non-local feature aggregation like images and texts.
method Utilizes Latent Fixed Data Structure (LFDS) to aggregate feature vectors from local extraction.
result Proposed methods achieve competitive or better results with linear computational complexity.
Interleaved RNNs detect fraud without costly features.
problem Real-time fraud detection in payment cards.
method Use interleaved sequence RNNs for fraud detection.
result Interleaved RNNs outperform state-of-the-art models in fraud detection.
Hybrid framework prevents forgetting in continual learning.
problem Avoiding forgetting in learning new tasks without forgetting old ones.
method Hybrid continual learning framework combining architecture growth and experience replay.
result Hybrid approach effectively avoids forgetting across multiple tasks.
New method embeds time span into self-attention for better temporal pattern recognition.
problem Capturing temporal patterns in event sequences without recurrent networks.
method Functional time representation learning with Bochner's and Mercer's Theorems.
result Proposed methods outperform baseline models in various continuous-time event sequence prediction tasks.
Extracts main content from web pages using neural sequence labeling.
problem Lack of generalization in existing web page content extraction models.
method Neural sequence labeling model using HTML tags and words as input.
result Model outperforms state-of-the-art and adapts to changes in web page structure.
Transformers handle infinite dimensional inputs effectively by feature extraction and dynamic feature selection.
problem Understanding the approximation and estimation ability of Transformers with infinite dimensional inputs.
method Anisotropic smoothness analysis and feature extraction properties of Transformers.
result Transformers avoid the curse of dimensionality and dynamically select important features.
Enhances fraud detection with multiple HMM perspectives.
problem Detecting credit card fraud from sequential transactions.
method Modeling credit card transactions from three perspectives (card-holder, terminal, amount/time) using HMMs and combining likelihoods as features.
result 15% increase in precision-recall AUC compared to state-of-the-art methods.
Study on recurrent neural networks' feature selection and memorization using F1B test.
problem Conflict between feature selection and memorization in sequence learning.
method Flagged-1-Bit (F1B) test, four recurrent network models studied analytically and experimentally.
result Conflict can be resolved by gating mechanism or increasing state dimension.
Recent advances in high-throughput cDNA sequencing (RNA-Seq) technology have revolutionized transcriptome studies. A major motivation for RNA-Seq is to map the structure of expressed transcripts at nucleotide resolution. With accurate computational tools for transcript reconstruction, this technology may also become us…
Seq-U-Net improves sequence modeling efficiency with dilated U-Net.
problem Efficiently modeling long-term dependencies in sequences.
method Causal U-Net architecture with dilated filters and slow feature hypothesis.
result Seq-U-Net achieves comparable performance with speed-ups of over 4x in audio generation.
Accelerates signature kernel computation for sequences.
problem Severe computational bottleneck in computing signature kernel.
method Random Fourier features to accelerate signature kernel computation.
result Uniform approximation guarantees for unbiased estimator with linear computation time.
Paper proposes deep learning models for k-NN classification.
problem Imbalanced datasets and complex feature vectors in classification.
method Sequence to sequence model and memory network models.
result Models outperform k-NN and other state-of-the-art models.
In this paper we consider a problem of searching a space of predictive models for a given training data set. We propose an iterative procedure for deriving a sequence of improving models and a corresponding sequence of sets of non-linear features on the original input space. After a finite number of iterations N, the n…
New algorithm improves interpretability in sequence classification.
problem Lack of human-independent interpretability metrics in sequence classification.
method Combines linear classifiers with background knowledge embeddings to create a new feature space.
result Preserves predictive power while delivering more interpretable models.
We consider the two problems of predicting links in a dynamic graph sequence and predicting functions defined at each node of the graph. In many applications, the solution of one problem is useful for solving the other. Indeed, if these functions reflect node features, then they are related through the graph structure.…
Existence of an infinite sequence of harmonic maps between spheres of certain dimensions was proven by Bizon and Chmaj. This sequence shares many features of the Bartnik-McKinnon sequence of solutions to the Einstein-Yang-Mills equations as well as sequences of solutions that have arisen in other physical models. We ap…
Deep learning predicts protein structures accurately.
problem Predicting the 3D structure of proteins from amino acid sequences.
method Embeddings and deep learning models for backbone atom distance matrices and torsion angles.
result Competitive results in CASP13 and CASP12, surpassing previous winners.
GMM-HMMs improve malware classification compared to discrete HMMs.
problem Improving malware classification accuracy using GMM-HMM models.
method Used GMM-HMM models for opcode and entropy-based features comparison with discrete HMMs.
result GMM-HMMs generally improve significantly on entropy-based features classification results.
LLT transforms time series features based on linear laws.
problem Classifying univariate and multivariate time series.
method Time-delay embedding, spectral decomposition, and feature transformation.
result Transformed features improve classification accuracy.
New method predicts protein features using statistical relational learning.
problem Challenges in automatic protein feature annotation due to limited homology data.
method Introduces Semantically Based Regularization to incorporate prior knowledge.
result Improved overall prediction quality with constraints.
New models for graph sequences capture link and community persistence.
problem Difficulties in extending block model results to graph sequences.
method Two models for graph sequences capturing link and community persistence, with efficient inference algorithms.
result Validated suitability of proposed models and methods on synthetic and real instances.