Spark Transformer achieves high sparsity in FFN and attention without sacrificing model quality.
problem Inactivity of most neurons in FFN of Transformers, leading to inefficiency.
method Top-k masking, statistical top-k algorithm, and predictor for activated entries.
result Only 8% of FFN neurons are activated, achieving up to 2.5x wall-time speedup.
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…
Network pruning is aimed at imposing sparsity in a neural network architecture by increasing the portion of zero-valued weights for reducing its size regarding energy-efficiency consideration and increasing evaluation speed. In most of the conducted research efforts, the sparsity is enforced for network pruning without…
ResGCN detects anomalies in attributed networks by capturing sparsity and nonlinearity.
problem Detecting anomalous nodes in attributed networks.
method Attention-based deep residual modeling using Graph Convolutional Networks.
result ResGCN effectively detects anomalies in attributed networks.
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.
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.
The p-Laplacian Transformer improves transformer models by assigning higher attention weights to tokens in close proximity.
problem The self-attention mechanism in transformers does not effectively distinguish attention weights between tokens in close and non-close proximity.
method Proposes a novel class of transformers, p-Laplacian Transformers, that use p-Laplacian regularization to assign higher attention weights to tokens in close proximity. result Empirically demonstrates that p-Laplacian Transformers outperform baseline transformers on various benchmark datasets.
Novel regularization for Vision Transformers improves model generalization and sparsity.
problem Improving generalization and sparsity in Vision Transformers.
method Likelihood-guided variational Ising-based regularization.
result Improved generalization and sparsity in Vision Transformers.
New Performer model tackles long-sequence protein modeling.
problem Challenges of training complex Transformer models for long sequences.
method Linearly scalable long-context Transformer architecture, Performer.
result Performer provides strong theoretical guarantees and is effective for protein sequence modeling.
Researchers improve transformer networks' optimization and understanding.
problem Improving the understanding and optimization of transformer networks.
method Introducing a convex alternative to the self-attention mechanism and reformulating the training problem as a convex optimization problem.
result Revealed an implicit regularization mechanism that promotes sparsity across tokens.
Recent studies in the literature have paid much attention to the sparsity in linear classification tasks. One motivation of imposing sparsity assumption on the linear discriminant direction is to rule out the noninformative features, making hardly contribution to the classification problem. Most of those work were focu…
Scales attention for long contexts in LLMs.
problem Development of attention mechanisms for long context inference.
method Scale-invariant total attention and sparsity conditions, with a position-dependent transformation of logits.
result Scale-invariant attention scheme improves validation loss and long-context retrieval.
GISST interprets GNNs by combining attention and sparsity for graph structure and node feature importance.
problem Lack of joint consideration of graph structure and node features in GNN interpretation.
method Model-agnostic framework using attention mechanism and sparsity regularization.
result GISST achieves superior node feature and edge explanation precision in synthetic and real-world datasets.
The paper investigates polynomial alternatives to softmax in transformer models.
problem The effectiveness of softmax attention in transformers is questioned.
method The authors explore polynomial activations as alternatives to softmax, focusing on their ability to regularize the attention matrix.
result Certain polynomials can serve as effective substitutes for softmax in transformer applications, achieving strong performance.
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.
Regularizes attention scores in vision transformers using bootstrapping.
problem Noisy and diffused attention maps in ViT limit interpretability.
method Statistical learning techniques, bootstrapping of attention scores.
result Improves shrinkage and sparsity of attention scores.
New method identifies causal order without sparsity assumptions.
problem Causal order discovery in observational data.
method Sequential procedure to directly identify causal order.
result Direct identification of causal order without sparsity assumptions.
A new method for fast and robust sparsity learning over networks.
problem Efficiently learning sparse models in decentralized networks.
method Decentralized surrogate median regression (deSMR) method.
result Linear convergence rate with a simple implementation.
Paper proposes a new sparsity scheme for high-dimensional VAR models.
problem Estimation of high-dimensional VAR models with sparsity assumptions.
method Regularized estimation procedures for sparse VAR models.
result Threholding extends consistency properties of regularized estimators.
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.
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.
Transformers can learn optimal variable selection in group-sparse classification.
problem Understanding how transformers leverage attention to select relevant variables in group-sparse classification.
method Training a one-layer transformer using gradient descent to select variables from one group of input variables.
result A one-layer transformer can correctly leverage the attention mechanism to select variables, disregarding irrelevant ones.
Sparse Hopfield model improves memory retrieval with fewer connections.
problem Memory retrieval efficiency with fewer connections.
method Sparse extension of Hopfield model, derived from sparse entropic regularizer.
result Sparse Hopfield model achieves tighter error bounds and better performance.
Sparsity learning with known grouping structure has received considerable attention due to wide modern applications in high-dimensional data analysis. Although advantages of using group information have been well-studied by shrinkage-based approaches, benefits of group sparsity have not been well-documented for greedy-…
Improved GRU model with multi-head cross-attention enhances stock prediction accuracy.
problem Inaccurate stock prediction due to complex market dynamics and data sparsity.
method Enhanced GRU with multi-head cross-attention for better historical information selection and latent market state learning.
result The proposed MCI-GRU model outperforms state-of-the-art techniques in multiple metrics.
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.
Improved text generation with discourse-aware soft prompts.
problem Efficient fine-tuning methods don't generalize across all generation tasks.
method Hierarchical blocking and attention sparsity on prefix parameters.
result Structured design of prefix parameters yields more coherent generations.
Transformer models waste resources on long-context tasks.
problem Redundant attention computations in Transformer models for long-context tasks.
method Reformulate sequence modeling as supervised learning, analyze attention sparsity, formulate attention optimization as linear coding problem, propose Dynamic Group Attention.
result DGA reduces computational costs while maintaining performance.
Social-based recommendation systems exploit the selections of friends to combat the data sparsity on user preferences, and improve the recommendation accuracy of the collaborative filtering strategy. The main challenge is to capture and weigh friends' preferences, as in practice they do necessarily match. In this paper…
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.
A new deep learning model for tabular data improves accuracy over GBDT.
problem Improving accuracy in tabular data classification.
method Differentiable forest with sparse attention mechanism.
result The differentiable forest achieves higher accuracy than GBDT on tabular datasets.
Converting an n-dimensional vector to a probability distribution over n objects is a commonly used component in many machine learning tasks like multiclass classification, multilabel classification, attention mechanisms etc. For this, several probability mapping functions have been proposed and employed in literature s…
The multi-label classification framework, where each observation can be associated with a set of labels, has generated a tremendous amount of attention over recent years. The modern multi-label problems are typically large-scale in terms of number of observations, features and labels, and the amount of labels can even …
A trend in compressed sensing (CS) is to exploit structure for improved reconstruction performance. In the basic CS model, exploiting the clustering structure among nonzero elements in the solution vector has drawn much attention, and many algorithms have been proposed. However, few algorithms explicitly consider corre…
Joint sparsity regularization in multi-task learning has attracted much attention in recent years. The traditional convex formulation employs the group Lasso relaxation to achieve joint sparsity across tasks. Although this approach leads to a simple convex formulation, it suffers from several issues due to the loosenes…
Multiple kernel learning (MKL), structured sparsity, and multi-task learning have recently received considerable attention. In this paper, we show how different MKL algorithms can be understood as applications of either regularization on the kernel weights or block-norm-based regularization, which is more common in str…
NFM improves deep learning by selectively processing hidden states.
problem Processing entire hidden states in each layer limits modularity and reusability.
method Introduces Neural Function Modules (NFM) with attention, sparsity, and feedback.
result Improves results in classification, generalization, generative modeling, and reinforcement learning.
Sparse data models, where data is assumed to be well represented as a linear combination of a few elements from a dictionary, have gained considerable attention in recent years, and their use has led to state-of-the-art results in many signal and image processing tasks. It is now well understood that the choice of the …
This paper analyzes privacy risks in neural network pruning and proposes a defense mechanism.
problem Privacy risks in neural network pruning due to membership inference attacks.
method Investigates the impact of pruning on prediction divergence and proposes a self-attention membership inference attack.
result Proposed defense mechanism mitigates privacy risks while maintaining sparsity and accuracy.
The paper studies the asymptotic behavior of adversarial training under ℓ∞-perturbation.
problem Theoretical guarantees for sparsity-recovery in adversarial training.
method Investigation of the asymptotic distribution of the adversarial training estimator in generalized linear models.
result The asymptotic distribution of the adversarial training estimator under ℓ∞-perturbation could have a positive probability mass at 0 when the true parameter is 0. In this paper, we consider voxel selection for functional Magnetic Resonance Imaging (fMRI) brain data with the aim of finding a more complete set of probably correlated discriminative voxels, thus improving interpretation of the discovered potential biomarkers. The main difficulty in doing this is an extremely high di…
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.
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 l0 norm. In this paper we develop a Momentumized Iterative Shrinkage Th…
Large-scale non-convex sparsity-constrained problems have recently gained extensive attention. Most existing deterministic optimization methods (e.g., GraSP) are not suitable for large-scale and high-dimensional problems, and thus stochastic optimization methods with hard thresholding (e.g., SVRGHT) become more attract…
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.
CATS enhances MTSF by generating ATS from OTS to improve forecasting accuracy.
problem Recent deep learning models often outperform multivariate ones in MTSF.
method CATS constructs ATS from OTS using a 2D temporal-contextual attention mechanism.
result CATS achieves state-of-the-art performance with reduced complexity.
Using a low-dimensional parametrization of signals is a generic and powerful way to enhance performance in signal processing and statistical inference. A very popular and widely explored type of dimensionality reduction is sparsity; another type is generative modelling of signal distributions. Generative models based o…
Modeling student behaviors and multiple predictions for early intervention.
problem Predicting student outcomes and interactions among multiple tasks.
method Proposes a variant of LSTM and soft-attention mechanism for heterogeneous behaviors, and co-attention mechanism for task interactions.
result Demonstrated effectiveness in predicting student outcomes and interactions.