Study compares deep learning models for volatility prediction using multivariate data.
problem Predicting volatility using multivariate data.
method Evaluated multiple deep learning models including MLP, RNN, TCN, and Temporal Fusion Transformer.
result Temporal Fusion Transformer and TCN variants outperform classical models and shallow networks.
Hybrid model improves geopolitical conflict forecasting.
problem Forecasting geopolitical events from sparse, bursty data.
method Sparse Temporal Fusion Transformer (TFT) + Variational Nearest Neighbor Gaussian Process (VNNGP).
result Consistently outperforms standalone TFT in long-range horizons.
CMTF improves financial market forecasting by fusing multiple data types.
problem Lack of effective integration of diverse financial data sources.
method Transformer-based deep learning framework with tensor interpretation and auto-training.
result CMTF outperforms classical and deep learning models in price direction classification.
Adaptive TFTs improve cryptocurrency price prediction accuracy.
problem Precise short-term price prediction in volatile cryptocurrency markets.
method Dynamic subseries lengths and pattern-based categorization.
result Significantly outperforms baseline models in prediction accuracy and profitability.
Multi-horizon forecasting problems often contain a complex mix of inputs -- including static (i.e. time-invariant) covariates, known future inputs, and other exogenous time series that are only observed historically -- without any prior information on how they interact with the target. While several deep learning model…
Financial fraud detection in digital banking requires reasoning over multiple heterogeneous event streams.
problem Financial fraud detection in digital banking requires reasoning over multiple heterogeneous event streams.
method Multi-Stream Fraud Transformer (MSFT) architecture that encodes each event stream with independent Transformer encoders and fuses their representations through configurable mechanisms.
result Sequence models significantly outperform gradient-boosted trees operating on aggregated features.
Early recognition of abnormal rhythms in ECG signals is crucial for monitoring and diagnosing patients' cardiac conditions, increasing the success rate of the treatment. Classifying abnormal rhythms into exact categories is very challenging due to the broad taxonomy of rhythms, noises and lack of large-scale real-world…
Fusion of transformer networks using optimal transport for improved performance.
problem Improving performance of transformer-based models through fusion.
method Exploiting optimal transport for soft alignment of transformer components.
result Consistently outperforms vanilla fusion and individual parent models.
Our model predicts stock market intervals using chaotic fusion and graph convolutional networks.
problem Uncertainty in financial market predictions without quantified uncertainty.
method Bi-level chaotic fusion, graph convolutional networks, volatility-aware gating, temporal dependencies.
result Significant improvements in prediction intervals and coverage compared to existing methods.
With the increasing popularity of video sharing websites such as YouTube and Facebook, multimodal sentiment analysis has received increasing attention from the scientific community. Contrary to previous works in multimodal sentiment analysis which focus on holistic information in speech segments such as bag of words re…
Multi-view time series classification (MVTSC) aims to improve the performance by fusing the distinctive temporal information from multiple views. Existing methods mainly focus on fusing multi-view information at an early stage, e.g., by learning a common feature subspace among multiple views. However, these early fusio…
The multi-scale, mutli-physics nature of fusion plasmas makes predicting plasma events challenging. Recent advances in deep convolutional neural network architectures (CNN) utilizing dilated convolutions enable accurate predictions on sequences which have long-range, multi-scale characteristics, such as the time-series…
Computational modeling of human multimodal language is an emerging research area in natural language processing spanning the language, visual and acoustic modalities. Comprehending multimodal language requires modeling not only the interactions within each modality (intra-modal interactions) but more importantly the in…
MRIF models dynamic user interests at multiple temporal-ranges.
problem Capturing dynamic and multi-resolution user interests in recommendation.
method Multi-resolution Interest Fusion (MRIF) model that considers both temporal-ranges and drifts in user interests.
result MRIF outperforms state-of-the-art recommendation methods consistently.
New BNN method reduces training time and model size.
problem Overconfident predictions in deep learning models.
method Designing STF-BNN for efficient scaling of BNNs.
result Significantly reduces training time and model size compared to vanilla BNNs.
CityTFT models urban building energy using a data-driven approach.
problem Current UBEM methods are time-consuming and based on physics.
method CityTFT uses a TFT framework with an augmented loss function.
result CityTFT predicts energy demands with high accuracy.
Paper proposes a method for weather-informed probabilistic forecasting and scenario generation in power systems.
problem Challenges of integrating renewable energy sources into power grids due to their stochasticity and uncertainty.
method Combines probabilistic forecasting and Gaussian copula for day-ahead prediction and scenario generation of load, wind, and solar power.
result Demonstrates superior performance of the proposed weather-informed Temporal Fusion Transformer (WI-TFT) model.
A new memory-based fusion layer improves multi-modal deep learning performance.
problem Improving performance of multi-modal deep learning by addressing long-term dependencies.
method Introducing a Memory based Attentive Fusion (MBAF) layer that incorporates both current and long-term dependencies.
result The MBAF layer enhances fusion and improves performance across different modalities and networks.
A novel one-class classifier fusion method for robust anomaly detection.
problem Fundamental challenges in ensemble-based anomaly detection.
method Locally adaptive learning with dynamic ℓp-norm constraints and interior-point optimization.
result Significantly improved computational efficiency and superior performance across diverse anomaly types.
New 4-manifold invariant defined from trisection diagrams.
problem Defining a new 4-manifold invariant from trisection diagrams.
method Algebraic data from bimodule categories and spherical fusion categories, described diagrammatically.
result Includes Hopf algebraic invariants and modular fusion category invariants.
Characterizing the dynamic interactive patterns of complex systems helps gain in-depth understanding of how components interrelate with each other while performing certain functions as a whole. In this study, we present a novel multimodal data fusion approach to construct a complex network, which models the interaction…
Proposes a non-autoregressive Transformer for time series forecasting.
problem Autoregressive errors and spatial-temporal dependencies in time series forecasting.
method Introduces a Non-Autoregressive Transformer with a learned temporal influence map.
result Demonstrates state-of-the-art performance on time series forecasting datasets.
Proposes a framework to fuse heterogeneous data sources for better modeling.
problem Heterogeneous data sources with different input parameter spaces.
method Input mapping calibration (IMC) and latent variable Gaussian process (LVGP).
result Improved predictive accuracy over single source models.
This paper proposes a novel framework for fusing multi-temporal, multispectral satellite images and OpenStreetMap (OSM) data for the classification of local climate zones (LCZs). Feature stacking is the most commonly-used method of data fusion but does not consider the heterogeneity of multimodal optical images and OSM…
This paper improves model fusion by training-time neuron alignment, reducing barriers in multi-model fusion.
problem Diverse neuron permutations across different settings hinder model fusion performances.
method Training-time neuron alignment using fixed neuron anchors to reduce training-time permutations.
result Training-time neuron alignment improves fusion of pretrained models and federated learning performances.
Mantis improves time series classification using a transformer model trained on synthetic data.
problem Insufficient application of foundation models to time series classification.
method Pre-trained transformer model on synthetic data, enhanced test-time methodology.
result Mantis achieves state-of-the-art performance across diverse datasets.
Multimodal research is an emerging field of artificial intelligence, and one of the main research problems in this field is multimodal fusion. The fusion of multimodal data is the process of integrating multiple unimodal representations into one compact multimodal representation. Previous research in this field has exp…
Study improves stock movement prediction using multimodal data.
problem Inaccurate stock movement prediction due to incomplete multimodal data integration.
method Introduces MSGCA framework for robust multimodal fusion.
result MSGCA framework outperforms existing methods by 21.7% on multimodal datasets.
Diffusion Transformer captures spatial-temporal dependencies in sequential data.
problem Capturing rich spatial and temporal dependencies in sequential data.
method Established theoretical guarantees for diffusion transformers learning Gaussian process data.
result Spatial-temporal dependencies are captured within attention layers of diffusion transformers.
Layer fusion reduces deep neural network layers with minimal loss in accuracy.
problem Model compression to reduce neural network size and computation.
method Fusion of similar layers to reduce model size with minimal performance loss.
result Deep networks can be compressed up to 3.33x with minimal accuracy loss.
Multivariate time series prediction has applications in a wide variety of domains and is considered to be a very challenging task, especially when the variables have correlations and exhibit complex temporal patterns, such as seasonality and trend. Many existing methods suffer from strong statistical assumptions, numer…
The sharp and recent increase in the availability of data captured by different sensors combined with their considerably heterogeneous natures poses a serious challenge for the effective and efficient processing of remotely sensed data. Such an increase in remote sensing and ancillary datasets, however, opens up the po…
Multimodal fusion frameworks for Human Action Recognition (HAR) using depth and inertial sensor data have been proposed over the years. In most of the existing works, fusion is performed at a single level (feature level or decision level), missing the opportunity to fuse rich mid-level features necessary for better cla…
Sentinel improves time series forecasting by modeling both temporal and channel dependencies.
problem Limited effectiveness of existing transformer-based architectures in multivariate time-series forecasting.
method Proposes Sentinel, a full transformer-based architecture with multi-patch attention mechanism.
result Sentinel achieves better or comparable performance compared to state-of-the-art approaches.
LDF combines neural networks with probabilistic models for data fusion.
problem Combining limited primary data with readily available auxiliary data.
method Neural networks as conjugate mappings of auxiliary data for posterior analysis.
result Efficient inference and compact latent variable posterior distributions.
TCGPN improves stock forecasting by capturing temporal correlation patterns.
problem Stock forecasting with minimal periodicity and large node numbers.
method TCGPN uses Temporal-Correlation fusion encoder and pre-training methods to handle large datasets.
result TCGPN achieves state-of-the-art results on real stock market data.
Transformer-based method for causal discovery with prior knowledge integration.
problem Complex nonlinear dependencies and spurious correlations in time series data.
method Multi-layer Transformer forecaster with gradient-based causal structure extraction and attention masking for prior knowledge integration.
result Significant improvement in causal discovery and causal lag estimation compared to state-of-the-art methods.
A new method detects financial fraud using graph transformers.
problem Detecting fraudulent transactions in financial data.
method Spatial-Temporal-Aware Graph Transformer (STA-GT) integrating GNNs and transformers.
result STA-GT outperforms general GNN models on financial fraud detection.
Neural surrogates speed up 5D gyrokinetic simulations of plasma turbulence.
problem Expensive numerical simulations of plasma turbulence hinder fusion reactor design.
method Trained a hierarchical vision transformer in 5D to predict plasma quantities faster.
result Neural surrogates predict plasma quantities two orders of magnitude faster than numerical codes.
Defines state sum models with defects in 3-manifolds.
problem Detecting and characterizing defects in 3-manifolds.
method Turaev-Viro-Barrett-Westbury state sum models with defects labeled by bimodule categories and functors.
result State sums are triangulation-independent and can be computed using polygon diagrams.
Paper unifies propositionalization and embedding for relational learning.
problem Data fusion from diverse input formats into a single table.
method Unified framework combining propositionalization and embedding.
result New algorithms outperform existing relational learners.
Current high-throughput data acquisition technologies probe dynamical systems with different imaging modalities, generating massive data sets at different spatial and temporal resolutions posing challenging problems in multimodal data fusion. A case in point is the attempt to parse out the brain structures and networks…
A machine learning approach to record fusion with high accuracy.
problem Aggregating multiple records corresponding to the same entity.
method Constructing feature vectors from attribute-level, record-level, and database-level signals; using a stagewise additive model to learn a classifier.
result Average precision of ~98% with source information and ~94% without source information across diverse datasets.
Framework improves marine mammal monitoring in noisy underwater environments.
problem Underwater bioacoustic monitoring challenges due to overlapping calls and variable noise.
method Multi-step attention-guided framework with segmentation and mid-level fusion.
result Improved signal discrimination, reduced false positives, reliable representations.
ARM improves multivariate time series forecasting by better capturing series-wise relationships.
problem Challenges in handling complex temporal-contextual relationships in multivariate time series forecasting.
method ARM is an enhanced multivariate LTSF architecture that employs Adaptive Univariate Effect Learning, Random Dropping, and Multi-kernel Local Smoothing.
result ARM outperforms vanilla Transformers on multiple benchmarks without significantly increasing computational costs.
Tensor models improve joint EEG and fMRI analysis.
problem Jointly analyzing EEG and fMRI for brain function studies.
method Soft and flexible coupling of tensor decompositions for EEG and fMRI.
result Tensorial methods outperform ICA in multi-modal analysis.
Transformers learn to predict temporal logic solutions from classical solver outputs.
problem Training neural networks on logic problem solutions for verification.
method Training a Transformer on generated training data from classical solvers, focusing on one solution per formula.
result Transformers can predict correct solutions to temporal logic problems, even to unseen benchmarks.
Speaker verification (SV) systems using deep neural network embeddings, so-called the x-vector systems, are becoming popular due to its good performance superior to the i-vector systems. The fusion of these systems provides improved performance benefiting both from the discriminatively trained x-vectors and generative …