Gated attention improves performance by using a hierarchical mixture of experts.
problem Improving performance of self-attention mechanisms in Transformers.
method Rigorously show that gated attention can be modeled as a hierarchical mixture of experts, providing a theoretical justification for its benefits.
result Gated attention is more sample-efficient than multi-head self-attention, requiring fewer data points to achieve the same estimation error.
Gated attention improves model curvature, enhancing performance on nonlinear tasks.
problem Understanding the geometric implications of gating in attention mechanisms.
method Modeling attention outputs as Gaussian distributions and analyzing Fisher--Rao geometry.
result Gated attention enables non-flat geometries, including positively curved manifolds.
Paper connects MoE and self-attention, proposing active-attention.
problem Improving efficiency and performance of self-attention mechanisms.
method Established connection between MoE and self-attention, analyzed quadratic gating functions, proposed active-attention mechanism.
result Active-attention outperforms standard self-attention in various tasks.
Investigates the fundamental components of attention mechanisms.
problem Understanding the building blocks of attention in deep learning.
method Classified and studied three key mechanisms: additive, multiplicative output, and synaptic attention.
result Additive activation attention is central in proofs of lower bounds.
A new method for feature fusion in U-Net decoders using difference-based gating.
problem Precise fusion of high-level semantics and low-level details in U-Net decoder reconstruction.
method Proposes two difference-based gating approaches: Feature-difference gating (FDG) and Entropy-difference gating (EDG).
result Both FDG and EDG methods outperform existing attention-based fusion methods, with EDG showing superior performance.
Perceptual capabilities of artificial systems have come a long way since the advent of deep learning. These methods have proven to be effective, however they are not as efficient as their biological counterparts. Visual attention is a set of mechanisms that are employed in biological visual systems to ease computationa…
Recurrent Neural Network (RNN) has been successfully applied in many sequence learning problems. Such as handwriting recognition, image description, natural language processing and video motion analysis. After years of development, researchers have improved the internal structure of the RNN and introduced many variants…
In this paper, we present a novel approach for incorporating external knowledge in Recurrent Neural Networks (RNNs). We propose the integration of lexicon features into the self-attention mechanism of RNN-based architectures. This form of conditioning on the attention distribution, enforces the contribution of the most…
Molecular structure-property relationships are key to molecular engineering for materials and drug discovery. The rise of deep learning offers a new viable solution to elucidate the structure-property relationships directly from chemical data. Here we show that the performance of graph convolutional networks (GCNs) for…
New model optimizes portfolios with realistic transaction costs.
problem Real-world transaction costs impact portfolio profitability.
method DPGRGT model with 2D relative-attentional Gated Transformer.
result Model outperforms baseline models in U.S. stock market data.
DAGR improves navigation by refining goal representations conditioned on the current state.
problem Goal-conditioned reinforcement learning lacks state awareness, leading to inefficient policy recovery.
method DAGR refines static goal embeddings into state-conditioned ones using gated cross-attention with a state-goal discrepancy map.
result DAGR improves navigation tasks on OGBench, matching or outperforming base methods.
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.
Partially observable environments present an important open challenge in the domain of sequential control learning with delayed rewards. Despite numerous attempts during the two last decades, the majority of reinforcement learning algorithms and associated approximate models, applied to this context, still assume Marko…
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.
KATA improves associative recall by optimizing feature maps derived from nonnegative attention weights.
problem Linear attention's poor performance on associative recall tasks.
method Formulates attention recall as a spherical-packing problem and introduces Kernelized Linear Attention Activations (KATA).
result KATA features offer a favorable capacity-interference tradeoff, enabling efficient associative recall.
WAVE improves time series forecasting by integrating AR and MA components.
problem Time series forecasting challenges.
method WAVE attention mechanism with AR and MA components.
result WAVE attention consistently improves TSF performance.
Study combines CNNs and LSTMs for ECG classification, improving performance with attention mechanisms.
problem Improving ECG classification accuracy for weakly supervised tasks.
method Investigates ConvLSTM networks and various attention mechanisms to capture both morphological and temporal features.
result Attention mechanisms improve classification performance and provide interpretable saliency maps.
Introduces Causal Energy Minimization to understand Transformer layers.
problem Empirical parameterization of Transformer blocks remains largely unexplored.
method Causal Energy Minimization framework that recasts Transformer layers as optimization steps on conditional energy functions.
result Identifies design space for Transformer layers including weight sharing and energy-based interpretations.
Study improves fraud detection in e-commerce with a stacked model combining CNNs, GNNs, and confidence gating.
problem Detecting credit card fraud in online transactions.
method Stacking approach with attention and confidence-driven layers, using DOWA and IOWA operators.
result The method achieves high accuracy and robust generalization in CCF detection.
Deep Sets improve reinforcement learning agent's object-centered navigation and generalization.
problem Improving reinforcement learning agents' ability to generalize to unseen objects and goals.
method Combining object-wise permutation invariant networks (Deep Sets) and gated-attention mechanisms.
result Agent demonstrates strong generalization to out-of-distribution goals in a procedurally-generated 2D world.
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…
Learning and memory are intertwined in our brain and their relationship is at the core of several recent neural network models. In particular, the Attention-Gated MEmory Tagging model (AuGMEnT) is a reinforcement learning network with an emphasis on biological plausibility of memory dynamics and learning. We find that …
Hierarchical pretraining with slow-fast ODEs
problem Causal self-attention vs. slow-fast ODEs
method Instantiating fast-slow ODE formalism as a concrete neural network
result Equilibrium manifold x=φ(y) is exactly the master-equation (ME) stationary distribution Toward enabling next-generation robots capable of socially intelligent interaction with humans, we present a computationalmodel of interactions in a social environment of multiple agents and multiple groups. The Multiagent Group Perception and Interaction (MGpi) network is a deep neural network that predi…
ConViT combines CNN and ViT strengths, improving image classification.
problem Combining the strengths of CNNs and ViTs while avoiding their limitations.
method Introducing GPSA, a form of positional self-attention with a soft convolutional inductive bias.
result ConViT outperforms DeiT on ImageNet while offering improved sample efficiency.
This paper introduces new attention-based convolutional neural networks for selecting bands from hyperspectral images. The proposed approach re-uses convolutional activations at different depths, identifying the most informative regions of the spectrum with the help of gating mechanisms. Our attention techniques are mo…
FleXOR trains fractional quantization for neural networks, improving accuracy and size.
problem Quantization limits to integer bits restricts compression and accuracy.
method Encryption algorithm with XOR gates for fractional bits during inference.
result FleXOR achieves high accuracy with fractional sub-1-bit weights.
LSTM improves cross-network recommendations by capturing user preference changes and irregular time intervals.
problem Offline cross-network recommender solutions fail to capture user preference changes and dynamic environments.
method Proposes a multi-layered LSTM network with attention mechanisms, higher order interactions, and time-aware gates.
result The model consistently outperforms state-of-the-art in accuracy, diversity, and novelty.
Methods from convex optimization are widely used as building blocks for deep learning algorithms. However, the reasons for their empirical success are unclear, since modern convolutional networks (convnets), incorporating rectifier units and max-pooling, are neither smooth nor convex. Standard guarantees therefore do n…
Temporal Functional Circuits explain KAN forecasts with interpretable edge functions.
problem Lack of mechanistic explanations in KAN forecasting.
method Transform KAN edge functions into faithful, temporally grounded explanations using a gated residual KAN.
result Gated KAN achieves lower MSE than linear-only models on regime-switching signals.
Language Models (LMs) are important components in several Natural Language Processing systems. Recurrent Neural Network LMs composed of LSTM units, especially those augmented with an external memory, have achieved state-of-the-art results. However, these models still struggle to process long sequences which are more li…
This paper describes the participation of Amobee in the shared sentiment analysis task at SemEval 2018. We participated in all the English sub-tasks and the Spanish valence tasks. Our system consists of three parts: training task-specific word embeddings, training a model consisting of gated-recurrent-units (GRU) with …
Extended LSTM improves language modeling performance.
problem Improving LSTM for large-scale language modeling.
method Exponential gating, modified memory structure, and residual stacking.
result xLSTM outperforms state-of-the-art models in performance and scaling.
Study improves stock price prediction using advanced ML models.
problem Improving financial forecasting accuracy in stock markets.
method Evaluation of RNN architectures including LSTM, GRU, and attention-based models.
result Attention-based models outperform others in capturing complex dependencies.
FEM improves attention mechanisms by applying value-driven log-linear tilts.
problem Standard attention mechanisms read via convex average, limiting channel-wise selection.
method Free Energy Mixer (FEM) applies a value-driven, per-channel log-linear tilt to a fast prior over indices.
result FEM outperforms strong baselines on NLP, vision, and time-series tasks.
Paper uses AI to predict option volatility surfaces with improved accuracy.
problem Difficult to predict dynamic evolution of option volatility smile surface.
method Combines deep learning (LSTM) with attention mechanism.
result Predicted volatility surfaces lead to higher returns and Sharpe ratios.
Predicting highrisk vascular diseases is a significant issue in the medical domain. Most predicting methods predict the prognosis of patients from pathological and radiological measurements, which are expensive and require much time to be analyzed. Here we propose deep attention models that predict the onset of the hig…
Determining whether hypotensive patients in intensive care units (ICUs) should receive fluid bolus therapy (FBT) has been an extremely challenging task for intensive care physicians as the corresponding increase in blood pressure has been hard to predict. Our study utilized regression models and attention-based recurre…
Deep learning model classifies concurrent human interactions from WiFi data with high accuracy.
problem Classifying concurrent human interactions from WiFi data with high accuracy.
method Attention-BiGRU deep learning model using Multiple Input Multiple Output radio link.
result Maximum benchmark accuracy of 94% for a single subject-pair, 88% for ten subject pairs.
Disease progression models are instrumental in predicting individual-level health trajectories and understanding disease dynamics. Existing models are capable of providing either accurate predictions of patients prognoses or clinically interpretable representations of disease pathophysiology, but not both. In this pape…
Recurrent Neural Networks (RNNs) with attention mechanisms have obtained state-of-the-art results for many sequence processing tasks. Most of these models use a simple form of encoder with attention that looks over the entire sequence and assigns a weight to each token independently. We present a mechanism for focusing…
Axial-LOB predicts stock prices from LOB data using attention layers.
problem Predicting stock price from LOB data with long-range dependencies.
method Axial-LOB uses gated position-sensitive axial attention layers to incorporate global interactions.
result Axial-LOB achieves state-of-the-art performance in stock price prediction.
The paper studies 4-qubit Clifford states and their properties.
problem Understanding the set and properties of 4-qubit Clifford states.
method Analyzing the 293760 4-qubit Clifford states, splitting them into 18 groups, and studying the action of CNOT gates and local gates.
result There are 293760 4-qubit Clifford states with specific entanglement entropies, and any pair can be connected with local gates and at most 3 CNOT gates.
Flexible priors improve VAE-based CF models for better user preference modeling.
problem Simplistic priors in VAEs limit user preference modeling and deeper representation learning.
method Incorporated flexible priors and gating mechanisms into VAEs for collaborative filtering.
result Flexible priors and gating mechanisms significantly improve recommendation performance.
Improved logistic MoE with sigmoid gate shows better sample efficiency.
problem Improving sample efficiency in logistic MoE models.
method Comprehensive analysis of multinomial logistic MoE with modified sigmoid gate, incorporating temperature parameter and using Euclidean score.
result The sigmoid gate leads to lower sample complexity than softmax gate for both parameter and expert estimation.
New method prepares 3-qubit states using local gates and controlled-Z gates.
problem Preparation of 3-qubit states using quantum gates.
method Uses Ry(θ) gates and controlled-Z gates, with an optimal number of controlled-Z gates. result Optimal number of controlled-Z gates for preparing 3-qubit states is four. Cross-domain sentiment classification (CDSC) is an importance task in domain adaptation and sentiment classification. Due to the domain discrepancy, a sentiment classifier trained on source domain data may not works well on target domain data. In recent years, many researchers have used deep neural network models for c…
Sigmoid gating is more sample efficient than softmax in mixture of experts.
problem Softmax gating leads to unnecessary competition among experts, causing representation collapse.
method Theoretical analysis of a regression framework with mixture of experts, identifying identifiability conditions and convergence rates.
result Sigmoid gating requires fewer samples to achieve the same expert estimation error as softmax gating.