Research
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.

168,657 papers · 148 categories

Trend · papers per month

75150224299 · Jun 202019922001200920172026
48 results for Sparse Attention

Efficient sparse attention reduces self-attention complexity and improves model performance.

problem Quadratic compute and memory requirements of self-attention for long sequences.
method Content-based sparse attention with dynamic routing module.
result Routing Transformer achieves state-of-the-art performance on various benchmarks.

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.

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.

Study examines asset pricing using various attention models, finding global self-attention and sliding window sparse attention models perform well.

problem Traditional asset pricing models miss temporal dependency and short memory issues.
method Investigates RNN attention models with various attention mechanisms for large-cap US stocks.
result Global self-attention and sliding window sparse attention models outperform in deriving returns and hedging risks, especially during the pandemic.

Sparse Transformers can approximate dense Transformers with only O(n) connections.

problem Can sparse Transformers approximate arbitrary sequence-to-sequence functions?
method Proposed sufficient conditions for universal approximation and proved that sparse Transformers with O(n) connections can approximate dense models.
result Sparse Transformers with O(n) connections can approximate the same function class as dense models with n^2 connections.

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.

HopGAT improves node classification in sparsely labeled graphs by learning from distant neighbors.

problem Classifying nodes in sparsely labeled graphs with limited labeled data.
method Hop-aware supervision mechanism and simulated annealing learning strategy.
result The model achieves high accuracy even with 40% labeled data, reducing performance loss to 3.9%.

Sparse attention model reduces long-context inference time with exponential accuracy guarantees.

problem Efficiently processing long-context queries in large language models.
method Formalizes attention as a projection onto key vectors, analyzes entropic relaxation, and introduces Vashista Sparse Attention.
result Sparse attention concentrates on a constant-size active face, leading to exponential decay of inactive tokens' mass and linear scaling of active face error.

Paper extends sparse alternatives to softmax for continuous domains, enabling efficient attention mechanisms.

problem Efficiently assigning zero probability to irrelevant categories in continuous domains.
method Extend alpha-entmax to continuous domains, introducing continuous-domain attention mechanisms.
result Continuous attention allows attending to time intervals and compact regions, improving text classification, machine translation, and visual question answering.

Attention mechanisms and non-local mean operations in general are key ingredients in many state-of-the-art deep learning techniques. In particular, the Transformer model based on multi-head self-attention has recently achieved great success in natural language processing and computer vision. However, the vanilla algori…

2019-05-24abs ↗pdf ↗

We present a general architecture of deep differentiable forest and its sparse attention mechanism. The differentiable forest has the advantages of both trees and neural networks. Its structure is a simple binary tree, easy to use and understand. It has full differentiability and all variables are learnable parameters.…

2020-02-29abs ↗pdf ↗

CoT improves transformer sample efficiency by reducing input token dependencies and attention sparsity.

problem Transformer sample inefficiency in simple tasks.
method Demonstrated through parity-learning setup, showing CoT reduces required samples from exponential to polynomial.
result Transformer learns function within polynomial samples with CoT, requiring exponential samples without CoT.

Attention mechanisms have become ubiquitous in NLP. Recent architectures, notably the Transformer, learn powerful context-aware word representations through layered, multi-headed attention. The multiple heads learn diverse types of word relationships. However, with standard softmax attention, all attention heads are de…

2019-08-30abs ↗pdf ↗

Transformers are powerful sequence models, but require time and memory that grows quadratically with the sequence length. In this paper we introduce sparse factorizations of the attention matrix which reduce this to O(nn)O(n \sqrt{n}). We also introduce a) a variation on architecture and initialization to train deeper net…

2019-04-23abs ↗pdf ↗

Sparse Transformers degrade semantic information first, with early layers encoding more.

problem Understanding how sparse Transformers affect learned representations and semantic information.
method Probed Transformers with progressively pruned weights to observe changes in semantic information and model behavior.
result Complex semantic information is first to degrade in sparse Transformers, with early layers encoding more.

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…

2017-05-22abs ↗pdf ↗

Improves key instance detection in MIL models by using neural network inversion with sparseness constraint.

problem Limited key instance detection performance in attention-based deep MIL models due to skewed attention scores.
method Sparse network inversion with a sparseness constraint incorporated into neural network inversion, solved by proximal gradient method.
result Significantly improved key instance detection performance while maintaining bag-level prediction performance.

Transformers show strengths and weaknesses in complexity analysis.

problem Understanding the strengths and limitations of attention layers in transformers.
method Analysis of representation power through complexity parameters and task-specific constructions.
result Transformers can solve sparse averaging tasks with logarithmic complexity, but triple detection tasks require linear complexity.

MAESTRO improves multimodal learning for dynamic time series with adaptive attention and robustness.

problem Challenges in multimodal learning, especially in healthcare and daily living.
method Dynamic intra- and cross-modal interactions, symbolic tokenization, adaptive attention budgeting, sparse cross-modal attention, MoE mechanism.
result Average relative improvements of 4% and 8% over existing multimodal and multivariate approaches, respectively, under complete observations.

A new method reduces memory requirements for Graph Transformers by sparsely training a network.

problem Quadratic memory complexity in Graph Transformers limits their scalability to large graphs.
method Spexphormer: trains a narrow network on augmented graph, then uses only active connections in a wider network.
result Spexphormer achieves good performance with drastically reduced memory requirements.

Many transformations in deep learning architectures are sparsely connected. When such transformations cannot be designed by hand, they can be learned, even through plain backpropagation, for instance in attention mechanisms. However, during learning, such sparse structures are often represented in a dense form, as we d…

2018-10-22abs ↗pdf ↗

Global Memory Augmentation (GMAT) improves Transformer performance on long documents.

problem Large memory requirements of Transformer pairwise dot-product attention for long sequences.
method Integrates a dense global memory of length M into sparse Transformer blocks.
result Significant improvement on various tasks, including synthetic tasks, masked language modeling, and reading comprehension.

Graph Neural Networks (GNNs) have proved to be an effective representation learning framework for graph-structured data, and have achieved state-of-the-art performance on many practical predictive tasks, such as node classification, link prediction and graph classification. Among the variants of GNNs, Graph Attention N…

2019-12-02abs ↗pdf ↗

AGML model improves indoor localization with sparse fingerprints using meta-learning and graph neural networks.

problem Maintaining high localization accuracy with extremely sparse fingerprints.
method Attentional Graph Neural Network (AGNN) and meta-learning framework with data augmentation strategies.
result AGML model consistently outperforms baseline methods across various metrics.

This paper develops sparse alternatives to continuous distributions, including new types of Gaussians and attention mechanisms.

problem Creating flexible continuous distributions with varying support for machine learning applications.
method Defining ΩΩ-regularized prediction maps and Fenchel-Young losses for arbitrary domains, and deriving new types of Gaussians and attention mechanisms.
result Sparse alternatives to continuous distributions, including deformed exponential families and ββ-Gaussians, are introduced.

MINN-SA enhances cancer detection using TCR sequences with better interpretability.

problem Challenges in detecting cancers using TCR sequences due to one-to-many correspondence.
method Multiple Instance Neural Networks based on Sparse Attention (MINN-SA).
result MINN-SA achieves highest AUC scores on 10 cancer types compared to existing MIL approaches.

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.

SGPA calibrates transformer uncertainty for safety-critical tasks.

problem Uncertainty estimation in transformer models for safety-critical domains.
method Bayesian inference in transformer's output space using sparse Gaussian processes.
result SGPA-based Transformers improve in-distribution calibration and out-of-distribution robustness.

A new method for self-attention models that improves uncertainty estimation.

problem Overconfident predictions and lack of calibrated uncertainty in Transformers.
method Kernel-Eigen Pair Sparse Variational Gaussian Processes (KEP-SVGP) with Kernel SVD (KSVD) to handle asymmetry of attention kernels.
result Reduction in time complexity and improved performance on various benchmarks.

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.

Transformers learn to integrate information from past positions incrementally, specializing heads in distinct patterns.

problem How transformers learn to integrate information from multiple past positions with varying statistical significance.
method High-order Markov chain task, incremental learning, sparse attention patterns, simplified differential equations, stage-wise convergence, early stopping as regularizer.
result Transformers learn to specialize heads in distinct patterns, shifting from competitive to cooperative learning dynamics.

Transformers with linear space and time complexity for accurate attention estimation.

problem Efficiently estimating attention in large-scale tasks without relying on priors.
method Performers use Fast Attention Via positive Orthogonal Random features (FAVOR+) for linear approximation of softmax attention.
result Performers achieve competitive results on various tasks, demonstrating the effectiveness of their attention-learning approach.

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.

The paper explores how sinks and diagonal patterns prevent attention oversmoothing.

problem Preventing attention oversmoothing in neural networks.
method Analyzing geometric conditions and conditions for dense vs. sparse attention, proving equivalence between sinks and hard attention switch, and comparing the costs of sinks vs. diagonal patterns.
result Sinks and diagonal patterns effectively prevent attention oversmoothing, and diagonal patterns provide a more flexible approach.

Transformer attention layers solve single-location regression tasks.

problem Understanding token-wise sparsity and internal linear representations in attention-based models.
method Introduce single-location regression task and a simplified predictor based on self-attention layers.
result Transformer attention layers are asymptotically Bayes optimal and can learn underlying structures effectively.

Kriformer uses graph transformers to estimate data in sparse sensor areas.

problem Sparse sensor deployment and unreliable data in spatiotemporal kriging tasks.
method Graph transformer model with positional encoding and attention mechanisms.
result Kriformer excels in representing unobserved locations in spatiotemporal kriging tasks.

This work explains the structural origins of attention sinks in LLMs.

problem Initial tokens disproportionately monopolize attention scores in LLMs.
method Traced to self-attention's value aggregation process and FFN layer activations.
result Attention sinks form due to variance discrepancy and dimension disparity.

Significant attention has been given to minimizing a penalized least squares criterion for estimating sparse solutions to large linear systems of equations. The penalty is responsible for inducing sparsity and the natural choice is the so-called l0l_0 norm. In this paper we develop a Momentumized Iterative Shrinkage Th…

2014-09-25abs ↗pdf ↗

Study reveals Transformer's expressive power and mechanisms.

problem Understanding the approximation properties of Transformer for sequence modeling.
method Systematic study of Transformer's components and their combined effects, establishing approximation rates.
result Reveals roles of critical parameters in Transformer, such as number of layers and attention heads.