Modern neural networks are often augmented with an attention mechanism, which tells the network where to focus within the input. We propose in this paper a new framework for sparse and structured attention, building upon a smoothed max operator. We show that the gradient of this operator defines a mapping from real val…
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 “focus of attention”
Model improves information transfer from visual streams.
problem Challenges in unsupervised learning from continuous visual data.
method Inspired by physics, maximizes mutual information through temporal process.
result Focus of attention enhances information transfer from input stream.
New interpretation of attention in Transformers and Graph Attention Networks.
problem Understanding and improving attention mechanisms in deep learning models.
method Decomposed attention into a kernel and a normalization term; generalized the kernel function and norm.
result Generalized attention leads to better performance on various tasks.
Without relevant human priors, neural networks may learn uninterpretable features. We propose Dynamics of Attention for Focus Transition (DAFT) as a human prior for machine reasoning. DAFT is a novel method that regularizes attention-based reasoning by modelling it as a continuous dynamical system using neural ordinary…
Self-attention prefers sparse functions of input sequences, reducing sample complexity.
problem Understanding the inductive biases of self-attention in modeling long-range dependencies.
method Theoretical analysis and synthetic experiments to probe sample complexity of learning sparse functions with Transformers.
result Bounded-norm Transformer networks can represent sparse functions of the input sequence with logarithmic sample complexity.
Deep reinforcement learning (DRL) has shown incredible performance in learning various tasks to the human level. However, unlike human perception, current DRL models connect the entire low-level sensory input to the state-action values rather than exploiting the relationship between and among entities that constitute t…
Investigates the benefits of multi-head attention in Transformers, deriving convergence and generalization guarantees.
problem Underexplored dynamics of multi-head attention in Transformer training and generalization.
method Derives convergence and generalization guarantees for gradient-descent training of a multi-head self-attention model.
result Establishes conditions for initialization that ensure multi-head attention's realizability.
Gaussian Attention Model and Its Application to Knowledge Base Embedding and Question Answeringstat.ML
We propose the Gaussian attention model for content-based neural memory access. With the proposed attention model, a neural network has the additional degree of freedom to control the focus of its attention from a laser sharp attention to a broad attention. It is applicable whenever we can assume that the distance in t…
Proposes a model combining difference-attention and error-correction LSTMs for improved time series prediction.
problem Improving accuracy in time series prediction.
method Combines difference-attention LSTM and error-correction LSTM in a cascade approach.
result Improves prediction accuracy in time series.
This is a survey article for the forthcoming `A Concise Encyclopedia of Knot Theory.' We focus on the topology of spatial graphs with few vertices and edges, paying particular attention to Brunnian -graphs.
Attention is an increasingly popular mechanism used in a wide range of neural architectures. The mechanism itself has been realized in a variety of formats. However, because of the fast-paced advances in this domain, a systematic overview of attention is still missing. In this article, we define a unified model for att…
Bayesian theory explains abrupt emergence of copy subcircuit in attention.
problem Understanding the abrupt emergence of the copy subcircuit in attention during training.
method Deriving a closed-form posterior over the attention matrix and reducing it to a low-dimensional order parameter space.
result Derive a phase transition in the amount of training data.
We aim to better understand attention over nodes in graph neural networks (GNNs) and identify factors influencing its effectiveness. We particularly focus on the ability of attention GNNs to generalize to larger, more complex or noisy graphs. Motivated by insights from the work on Graph Isomorphism Networks, we design …
Paper introduces kernel deformed exponential families for sparse continuous attention.
problem Creating efficient attention mechanisms for sparse data.
method Developed kernel deformed exponential families, theoretically and experimentally.
result Kernel deformed exponential families can attend to multiple compact regions of data.
Deep neural networks, including recurrent networks, have been successfully applied to human activity recognition. Unfortunately, the final representation learned by recurrent networks might encode some noise (irrelevant signal components, unimportant sensor modalities, etc.). Besides, it is difficult to interpret the r…
Study shows perceptual boost of visual attention varies with task difficulty and size.
problem Understanding how task-dependent the perceptual boost of visual attention is in natural settings.
method Designed and trained neural networks on various visual tasks, comparing results to baseline.
result Perceptual boost of attention is stronger with more difficult tasks and weaker with larger task sets.
SpGAT learns graph representations using spectral attention for efficiency.
problem Efficiently capturing global graph patterns with minimal parameters.
method Introduces Spectral Graph Attention Network (SpGAT) using spectral domain attention mechanisms and a fast Chebychev approximation.
result SpGAT achieves better global pattern recognition with fewer parameters compared to GAT.
Autonomous driving is getting a lot of attention in the last decade and will be the hot topic at least until the first successful certification of a car with Level 5 autonomy. There are many public datasets in the academic community. However, they are far away from what a robust industrial production system needs. Ther…
Graph attention networks improve performance on heterogeneous graphs.
problem Complex performance of GNNs on heterogeneous graphs.
method Integrating positional encodings into graph attention networks.
result Graph attention networks excel in node classification and link prediction.
Inspired by recent work in attention models for image captioning and question answering, we present a soft attention model for the reinforcement learning domain. This model uses a soft, top-down attention mechanism to create a bottleneck in the agent, forcing it to focus on task-relevant information by sequentially que…
Interprets how intrinsic motivation shapes behavior in RL agents.
problem Understanding how intrinsic motivation influences behavior in reinforcement learning agents.
method Analyzed five RL agents in procedurally generated environments using various interpretability techniques.
result Curiosity-driven agents exhibit broader and more dynamic attention than extrinsically motivated agents.
The amount of available Earth observation data has increased dramatically in the recent years. Efficiently making use of the entire body information is a current challenge in remote sensing and demands for light-weight problem-agnostic models that do not require region- or problem-specific expert knowledge. End-to-end …
Modeling Bitcoin prices and media attention using jump-type processes.
problem Capturing the dynamics of Bitcoin prices and media attention.
method Lévy processes and semiparametric estimation.
result Effective modeling of Bitcoin prices and media attention using Lévy processes.
Most previous studies on multi-agent reinforcement learning focus on deriving decentralized and cooperative policies to maximize a common reward and rarely consider the transferability of trained policies to new tasks. This prevents such policies from being applied to more complex multi-agent tasks. To resolve these li…
ATS2S model predicts RUL of industrial equipment using attention mechanism.
problem Accurate estimation of RUL for industrial equipment to improve maintenance schedules and reduce costs.
method ATS2S model that optimizes reconstruction and RUL prediction losses, uses attention mechanism, and integrates encoder and decoder features.
result ATS2S model achieves superior performance over 13 state-of-the-art methods on four real datasets.
New framework shows cross-attention improves multi-modal in-context learning.
problem Understanding multi-modal in-context learning in neural networks.
method Mathematical framework and linearized cross-attention mechanism.
result Cross-attention mechanism is provably optimal for multi-modal in-context learning.
Unlike images or videos data which can be easily labeled by human being, sensor data annotation is a time-consuming process. However, traditional methods of human activity recognition require a large amount of such strictly labeled data for training classifiers. In this paper, we present an attention-based convolutiona…
We propose sparsemax, a new activation function similar to the traditional softmax, but able to output sparse probabilities. After deriving its properties, we show how its Jacobian can be efficiently computed, enabling its use in a network trained with backpropagation. Then, we propose a new smooth and convex loss func…
We study a family of spheres with constant mean curvature (CMC) in the Riemannian Heisenberg group . These spheres are conjectured to be the isoperimetric sets of . We prove several results supporting this conjecture. We also focus our attention on the sub-Riemannian limit.
BERT-based architectures currently give state-of-the-art performance on many NLP tasks, but little is known about the exact mechanisms that contribute to its success. In the current work, we focus on the interpretation of self-attention, which is one of the fundamental underlying components of BERT. Using a subset of G…
Inspired by the observation that humans are able to process videos efficiently by only paying attention where and when it is needed, we propose an interpretable and easy plug-in spatial-temporal attention mechanism for video action recognition. For spatial attention, we learn a saliency mask to allow the model to focus…
Efficiently accelerates attention calculation for Transformers with relative positional encoding.
problem Quadratic complexity of attention in long sequences.
method Kernelized attention with Fast Fourier Transform (FFT) for RPE.
result Achieves O(n log n) time complexity, mitigates training instability, and outperforms other models.
New method uses shared attention for multi-task time series forecasting.
problem Insufficient training instances in single-task forecasting.
method Self-attention based sharing schemes across multiple tasks.
result Outperforms state-of-the-art single-task forecasting baselines and RNN-based multi-task forecasting method.
OTSeg uses multi-prompt Sinkhorn attention to improve zero-shot semantic segmentation.
problem Leveraging pre-trained CLIP knowledge to align text embeddings with pixel embeddings.
method OTSeg employs Multi-Prompts Sinkhorn (MPS) and Multi-Prompts Sinkhorn Attention (MPSA) to enhance semantic feature matching.
result OTSeg achieves state-of-the-art performance in zero-shot semantic segmentation tasks.
We focus our attention on the notion of intrinsic Lipschitz graphs, inside a special class of metric spaces i.e. the Carnot groups. More precisely, we provide a characterization of locally intrinsic Lipschitz functions in Carnot groups of step 2 in terms of their intrinsic distributional gradients.
LatFormer improves geometric reasoning by incorporating lattice symmetry priors in attention mechanisms.
problem State-of-the-art models struggle with geometric reasoning tasks in the ARC and LARC datasets.
method Introduced LatFormer, a model that uses lattice symmetry priors in attention masks.
result LatFormer requires 2 orders of magnitude fewer data than standard attention mechanisms.
This paper predicts stock prices using LLMs and news embeddings.
problem Predicting stock prices with high accuracy and relevance.
method Integrates LLMs with stock name embeddings and attention mechanisms for news filtering.
result Reduces MAE by 7.11% compared to baseline.
Distributional Associations vs In-Context Reasoning: A Study of Feed-forward and Attention Layerscs.LG
The study compares feed-forward and attention layers in language models.
problem Understanding the role of feed-forward and attention layers in language models.
method Empirical and theoretical analysis in a synthetic setting.
result Feed-forward layers learn simple distributional associations, while attention layers focus on in-context reasoning.
New NAM model improves image processing speed and accuracy.
problem Time-consuming pixel-by-pixel analysis of large images.
method Integrates Neuronal Attention model (NAM) to focus on small regions.
result Efficiently processes large images with improved speed and accuracy.
We present a method to stop the evaluation of a decision making process when the result of the full evaluation is obvious. This trait is highly desirable for online margin-based machine learning algorithms where a classifier traditionally evaluates all the features for every example. We observe that some examples are e…
Paper tackles noisy annotations by considering workers' attention levels.
problem Noisy annotations from workers with varying expertise.
method Proposes a probabilistic model that incorporates workers' attention for accurate label quality estimation.
result Improves aggregated labels by quantifying the relationship between workers' attention and label quality.
The paper explores how to make neural networks extrapolate longer sequences.
problem Neural networks struggle to extrapolate beyond seen data, especially for longer sequences.
method The authors propose a model with separate content- and location-based attention mechanisms.
result Models with the proposed attention mechanisms are better at extrapolating longer sequences.
Attention mechanism learns to focus on sparse tokens efficiently.
problem Detecting weak, rare, and sparsely located features in long sequences.
method Theoretical analysis and training of a single-layer attention classifier in a sparse-token classification model.
result A single-layer attention classifier can achieve vanishing test error with logarithmic signal strength growth, unlike linear classifiers requiring linear growth.
Financial time series prediction, especially with machine learning techniques, is an extensive field of study. In recent times, deep learning methods (especially time series analysis) have performed outstandingly for various industrial problems, with better prediction than machine learning methods. Moreover, many resea…
Learning latent representations of nodes in graphs is an important and ubiquitous task with widespread applications such as link prediction, node classification, and graph visualization. Previous methods on graph representation learning mainly focus on static graphs, however, many real-world graphs are dynamic and evol…
In this paper we present our scientific discovery that good representation can be learned via continuous attention during the interaction between Unsupervised Learning(UL) and Reinforcement Learning(RL) modules driven by intrinsic motivation. Specifically, we designed intrinsic rewards generated from UL modules for dri…
Extreme times in financial marketscond-mat.other
We apply the theory of continuous time random walks to study some aspects of the extreme value problem applied to financial time series. We focus our attention on extreme times, specifically the mean exit time and the mean first-passage time. We set the general equations for these extremes and evaluate the mean exit ti…
Derives an empirical capacity model for self-attention neural networks.
problem Theoretical capacity of large transformer models is not fully utilized by current optimization algorithms.
method Analyzes memory capacity of transformers using synthetic training data and common training algorithms.
result Derives an empirical capacity model (ECM) for a generic transformer.