Graph convolutional networks (GCNs) have shown the powerful ability in text structure representation and effectively facilitate the task of text classification. However, challenges still exist in adapting GCN on learning discriminative features from texts due to the main issue of graph variants incurred by the textual …
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 “dual attention networks”
A framework for transformer attention layers derived from SVR.
problem Developing principled attention mechanisms for transformers.
method Mapping self-attention to SVR, deriving new attention types.
result Improved transformer performance and efficiency.
DanSmp predicts stock movement using a hybrid-relational MKG and dual attention networks.
problem Predicting stock price trends in volatile financial markets.
method Constructs a bi-typed MKG with hybrid-relations and uses DanSmp, a dual attention network, to learn momentum spillover signals.
result DanSmp improves stock prediction accuracy using the MKG.
Graph convolutional networks (GCNs) have recently become one of the most powerful tools for graph analytics tasks in numerous applications, ranging from social networks and natural language processing to bioinformatics and chemoinformatics, thanks to their ability to capture the complex relationships between concepts. …
Improves dialogue response model interpretability using attention and regularization.
problem Improving interpretability of dual encoder models for dialogue response suggestions.
method Integrates attention mechanism and novel regularization loss to emphasize important words.
result Improves model accuracy and interpretability compared to existing methods.
The Nonlinear autoregressive exogenous (NARX) model, which predicts the current value of a time series based upon its previous values as well as the current and past values of multiple driving (exogenous) series, has been studied for decades. Despite the fact that various NARX models have been developed, few of them ca…
Improved speech enhancement with MNTFA using time-frequency attention.
problem Speech enhancement with limited model size and memory.
method Designing MNTFA with self-attention modules for long sequences and joint training.
result MNTFA achieves better performance with fewer parameters than DPCRN.
Hybrid model predicts flow and pressure in water systems.
problem Predicting flow and pressure in water distribution systems with complex spatial-temporal correlations.
method Hybrid dual-stage spatial-temporal attention-based recurrent neural networks (hDS-RNN).
result Our model outperformed 9 baseline models in flow and pressure series prediction.
In recent years, there has been a surge of interest in developing deep learning methods for non-Euclidean structured data such as graphs. In this paper, we propose Dual-Primal Graph CNN, a graph convolutional architecture that alternates convolution-like operations on the graph and its dual. Our approach allows to lear…
Long-term prediction of multivariate time series is still an important but challenging problem. The key to solve this problem is to capture the spatial correlations at the same time, the spatio-temporal relationships at different times and the long-term dependence of the temporal relationships between different series.…
Visual Question Answering (VQA) requires AI models to comprehend data in two domains, vision and text. Current state-of-the-art models use learned attention mechanisms to extract relevant information from the input domains to answer a certain question. Thus, robust attention mechanisms are essential for powerful VQA mo…
PDNAS optimizes GNN architectures for diverse datasets.
problem Inadequate adaptability and combinatorial search space in GNNs.
method Dual architecture search (micro- and macro-architectures) with gradient-based optimization.
result PDNAS finds deeper GNNs with better performance on diverse datasets.
AnomalyDAE detects anomalies in networks by learning cross-modality interactions.
problem Detecting anomalies in attributed networks where structure and attributes interact.
method Dual autoencoder framework with attention mechanism for joint learning of structure and attribute embeddings.
result AnomalyDAE effectively detects anomalies by reconstructing node attributes and structures.
A new method for multi-criteria recommender systems using graph attention networks.
problem Lack of nuanced relationships between users and items based on specific criteria.
method MDGAT, a multi-edge bipartite graph with dual attention networks and contrastive learning.
result MDGAT achieves higher accuracy in predicting item ratings compared to baseline methods.
Attentive Neural Controlled Differential Equations for Time-series Classification and Forecastingcs.LG
ANCDEs improve time-series forecasting and classification using attention in NCDEs.
problem Improving time-series forecasting and classification using neural controlled differential equations.
method Integrating attention into neural controlled differential equations (ANCDEs).
result ANCDEs consistently show the best accuracy in time-series classification and forecasting.
End-to-End Models for the Analysis of System 1 and System 2 Interactions based on Eye-Tracking Dataq-bio.NC
Method identifies dual cognitive system interactions using eye-tracking data.
problem Quantify interactions between System 1 and System 2 cognitive processes.
method Modified Stroop test, machine learning, eye-tracking data.
result Machine learning can distinguish between different tasks and characterize attentional load.
CATA++ improves scientific article recommendations by learning latent spaces with attention.
problem Natural data sparsity limits MF performance in recommender systems.
method CATA++ uses a dual autoencoder with attention to learn latent spaces from content and contextual information.
result CATA++ significantly improves MF performance on real-world datasets.
Survey on biharmonic Riemannian submersions, a dual concept of biharmonic submanifolds.
problem Understanding biharmonic Riemannian submersions as a dual concept.
method Short survey focusing on biharmonic Riemannian submersions.
result Survey provides insights into the dual concept of biharmonic submanifolds.
Optimal transport simplifies machine learning by comparing probability measures.
problem Comparing and manipulating probability distributions in machine learning.
method Uses optimal transport to compare and manipulate probability distributions, combining statistical and geometric perspectives.
result Optimal transport provides a unified framework for various machine learning tasks.
The clustering methods have recently absorbed even-increasing attention in learning and vision. Deep clustering combines embedding and clustering together to obtain optimal embedding subspace for clustering, which can be more effective compared with conventional clustering methods. In this paper, we propose a joint lea…
Hydra boosts efficiency for long-context reasoning in resource-constrained settings.
problem Quadratic complexity of transformers limits long-context reasoning in resource-constrained systems.
method Hydra uses a modular architecture with adaptive routing between sparse global attention, mixture-of-experts, and dual memories.
result Hydra achieves significant throughput and accuracy improvements for long-context reasoning.
Linearized attention fails to converge to NTK limit even at large widths.
problem Understanding the convergence of attention mechanisms to the kernel regime.
method Analyzes linearized attention and its relationship to the NTK limit, considering practical widths and conditions.
result Linearized attention does not converge to its NTK limit at any practical width, revealing a fundamental trade-off.
Singular dual pairsmath.SG
We generalize the notions of dual pair and polarity introduced by S. Lie and A. Weinstein in order to accommodate very relevant situations where the application of these ideas is desirable. The new notion of polarity is designed to deal with the loss of smoothness caused by the presence of singularities that are encoun…
The financial crisis showed the importance of measuring, allocating and regulating systemic risk. Recently, the systemic risk measures that can be decomposed into an aggregation function and a scalar measure of risk, received a lot of attention. In this framework, capital allocations are added after aggregation and can…
ADAVI tackles variational inference for large HBM models in neuroimaging.
problem Large, pyramidally-organized HBM models in neuroimaging studies.
method Automatic dual amortized variational inference using neural networks and attention-based hierarchical encoding.
result Significantly reduced parameterization of the variational family, maintaining expressivity.
FAL improves formation resistivity prediction from cased boreholes with noise resistance.
problem Noise and high-frequency disaster in predicting formation resistivity from cased boreholes.
method Frequency-aware framework and temporal anti-noise block for LSTM.
result FAL achieves a 24.3% improvement in R2 over LSTM, reaching R2=0.91.
DualVDT improves time-series forecasting with a novel dual reparametrized structure.
problem Time-series forecasting with improved performance and analytical rigor.
method Dual reparametrized variational mechanisms on VAE, latent score based generative model, reverse time stochastic differential equation, variational ancestral sampling, KL divergence reduction.
result Advanced performance in time-series forecasting with reduced KL divergence.
CADE learns dual node representations for better generalization.
problem Transductive graph embeddings cannot generalize to unseen nodes or across different graphs.
method CADE combines real-time neighborhoods with neighbor-attentioned representation, preserving known node memory.
result CADE outperforms state-of-the-art methods in generalization and context-awareness.
Bayesian attention improves model performance and robustness.
problem Limited exploration of stochastic attention in neural networks.
method Introduces Bayesian attention belief networks using gamma and Weibull distributions.
result Outperforms deterministic and stochastic attention methods in accuracy and robustness.
A new deep learning framework selects representative samples for unsupervised learning.
problem Selecting representative samples for unsupervised learning in non-linear data.
method DUAL framework using an encoder-decoder architecture to learn nonlinear embeddings and a selection block to choose representative samples.
result DUAL outperforms state-of-the-art methods in selecting representative samples for unsupervised learning.
GA-Net selectively attends to parts of a sequence for text classification.
problem Inefficient global attention mechanisms on long sequences.
method Gated Attention Network (GA-Net) using an auxiliary network to dynamically select and attend to important parts of the sequence.
result GA-Net achieves better performance with less computation and interpretability.
Neural networks using transformer-based architectures have recently demonstrated great power and flexibility in modeling sequences of many types. One of the core components of transformer networks is the attention layer, which allows contextual information to be exchanged among sequence elements. While many of the prev…
Enhances group convolutional networks with attention to learn meaningful relationships.
problem Lack of explicit means to learn meaningful relationships among symmetry patterns.
method Introduces attentive group equivariant convolutions, applying attention during convolution.
result Consistently outperforms conventional group convolutional networks on benchmark datasets.
Graph neural network (GNN), as a powerful representation learning model on graph data, attracts much attention across various disciplines. However, recent studies show that GNN is vulnerable to adversarial attacks. How to make GNN more robust? What are the key vulnerabilities in GNN? How to address the vulnerabilities …
Transformer models align words through attention weights, closely approximating Optimal Transport.
problem Understanding the internal mechanism of transformer models in language processing.
method Empirical evidence and theoretical analysis of attention weights and their relation to Optimal Transport.
result Transformer models can simulate gradient descent on the dual of entropy-regularized OT problem, providing a theoretical foundation for token alignment.
Two algorithms solve nonconvex minimax problems with linear constraints, achieving complexity guarantees.
problem Nonconvex minimax problems with coupled linear constraints.
method Zeroth-order primal-dual alternating projected gradient (ZO-PDAPG) and zeroth-order regularized momentum primal-dual projected gradient (ZO-RMPDPG) algorithms.
result Iteration complexity guarantees for solving nonconvex-(strongly) concave minimax problems with coupled linear constraints.
TLOB predicts stock prices better than existing models by adapting a simple MLP to LOB data.
problem Predicting stock prices from LOB data is challenging and complex.
method TLOB uses a transformer model with dual attention to capture spatial and temporal dependencies.
result TLOB outperforms state-of-the-art models across multiple datasets and horizons.
We consider the diffeological pseudo-bundles of exterior algebras, and the Clifford action of the corresponding Clifford algebras, associated to a given finite-dimensional and locally trivial diffeological vector pseudo-bundle, as well as the behavior of the former three constructions (exterior algebra, Clifford action…
Mathematical framework for understanding attention in neural networks.
problem Lack of theoretical understanding of attention in neural networks.
method Proposes a measure-theoretic model of attention and interprets self-attention as a system of self-interacting particles.
result Shows that attention is Lipschitz-continuous under suitable assumptions.
Dual Variable Learning Rates improve neural network training efficiency.
problem Training neural networks efficiently and effectively.
method DVLR uses different learning rates for correct and incorrect responses, and adjusts rates based on network performance.
result DVLR consistently improves neural network accuracy across different types and domains.
The ability to look multiple times through a series of pose-adjusted glimpses is fundamental to human vision. This critical faculty allows us to understand highly complex visual scenes. Short term memory plays an integral role in aggregating the information obtained from these glimpses and informing our interpretation …
The Dual PC Algorithm and the Role of Gaussianity for Structure Learning of Bayesian Networksstat.ML
Dual PC algorithm improves structure learning of Bayesian networks.
problem Learning the structure of Bayesian networks from observational data.
method Dual PC algorithm, leveraging covariance and precision matrices, and partial correlations.
result The dual PC algorithm outperforms the classic PC algorithm in structure recovery, even with non-Gaussian data.
BiSHop tackles tabular data challenges with sparse Hopfield layers.
problem Non-rotationally invariant data structure and feature sparsity in tabular data.
method Sequential column-wise and row-wise processing through interconnected directional learning modules with generalized sparse modern Hopfield layers.
result BiSHop surpasses current SOTA methods with significantly less hyperparameter tuning.
Kernelised Normalising Flowsstat.ML
Kernelised flows improve density estimation and generation with fewer parameters.
problem Limited expressiveness of flow-based models due to invertibility constraints.
method Integrates kernels into normalising flows to enhance expressiveness and efficiency.
result Kernelised flows outperform neural network-based flows in parameter efficiency and low-data scenarios.
Self-attention models benefit equally from width and depth, but beyond a certain point, depth becomes less efficient.
problem Understanding the optimal balance between depth and width in self-attention models.
method Theoretical predictions and empirical ablations on networks of varying depths and widths.
result An optimal width of 30K is recommended for a 1-Trillion parameter network, marking a significant width for self-attention models.
Analyzes self-attention in recurrent networks, proving it mitigates vanishing gradients.
problem Vanishing gradients in recurrent networks when capturing long-term dependencies.
method Formal analysis of self-attention's effect on gradient propagation, proposing a relevancy screening mechanism.
result Self-attention mitigates vanishing gradients in recurrent networks, providing guarantees.
AReLU uses attention-based rectification to improve neural network performance.
problem Improving neural network performance through better activation functions.
method Integrates attention mechanism with rectified linear unit (ReLU) to learn and scale feature maps.
result AReLU significantly boosts performance of most network architectures with minimal changes.
Paper investigates Lipschitz constants of self-attention modules in neural networks.
problem Lipschitz constants of self-attention modules in neural networks.
method Proved standard dot-product self-attention is not Lipschitz for unbounded input domain. Proposed L2 self-attention that is Lipschitz. Derived upper bound on L2 self-attention's Lipschitz constant.
result Proved standard self-attention is not Lipschitz for unbounded input domain and proposed an alternative L2 self-attention that is Lipschitz.