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.
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.
GSA-Nets apply group equivariance to self-attention for vision tasks.
problem Improving self-attention networks for vision tasks.
method Define group-equivariant positional encodings.
result GSA-Nets outperform non-equivariant self-attention networks on vision 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.
SANST uses self-attentive networks with spatial and temporal embeddings for better POI recommendations.
problem Next point-of-interest (POI) recommendation for users based on their history.
method SANST incorporates spatio-temporal patterns into self-attentive networks.
result SANST outperforms state-of-the-art models by up to 13.65% in nDCG@10.
TSAM predicts directed temporal links using GCN and self-attention.
problem Predicting links in directed temporal networks.
method GCN, self-attention mechanism, autoencoder architecture, graph attentional layers, graph convolutional layers, graph recurrent unit layer.
result TSAM outperforms benchmarks on four realistic networks.
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.
A new neural network separates vocals from music accompaniment.
problem Separating vocals from music accompaniment in recordings.
method Self-attention convolutional neural network (CNN) with densely-connected blocks.
result 19.5% relative improvement in vocals separation.
New model adds persistent memory to self-attention layers for improved performance.
problem Improving transformer performance by removing feed-forward layers.
method Augmenting self-attention layers with persistent memory vectors.
result The model outperforms standard transformers on language modeling benchmarks.
Transformers' self-attention mechanism is mapped to a generalized Potts model.
problem Uncertainty in what type of data distribution self-attention can efficiently learn.
method Decouple word positions and embeddings, then show self-attention learns a generalized Potts model.
result Training self-attention is equivalent to solving the inverse Potts problem.
Self-attentive network improves emotion recognition in conversations.
problem Emotion recognition in dyadic conversations using deep learning.
method Introduces a novel self-attention mechanism for capturing temporal dynamics without a decoder.
result Outperforms state-of-the-art alternatives on the IEMOCAP benchmark.
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 investigates how Global Self-attention improves GCNs.
problem Improving expressive power and addressing overfitting in GCNs.
method Applying Global Self-attention mechanism over graph features.
result GSA mechanism enhances expressive power and mitigates overfitting and over-smoothing in GCNs.
Self-attention improves satellite time series classification without preprocessing.
problem Efficiently classifying raw satellite time series data.
method Comparison of deep learning models including self-attention, 1D-convolutions, recurrence, and random forest.
result Self-attention and recurrent neural networks outperform convolutional neural networks on raw satellite time series.
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.
LieTransformer extends self-attention to Lie groups for improved deep learning tasks.
problem Improving deep learning performance through group equivariant self-attention.
method LieSelfAttention layers that are equivariant to arbitrary Lie groups and their discrete subgroups.
result Competitive experimental results on various tasks.
A new graph pooling method using self-attention improves graph classification performance.
problem Challenges in applying downsampling to graphs in graph neural networks.
method Proposes a self-attention-based graph pooling method.
result Our method achieves superior graph classification performance on benchmark datasets.
Study reveals self-attention's role in learning and generalizing interactions.
problem Understanding self-attention's theoretical role in neural architectures.
method Interacting entities analysis, including multi-agent RL and genetic sequences.
result Self-attention efficiently represents, learns, and generalizes pairwise interactions.
Self-attention networks localize when eigenspectrum variance is small.
problem Self-attention mechanisms can lead to rank and entropy collapses, reducing model expressivity and trainability.
method Characterized attention localization using query-key eigenspectrum variance.
result Small eigenspectrum variance prevents both rank and entropy collapses, improving model performance.
CDSA uses self-attention to impute missing values in multivariate, geo-tagged time series data.
problem Missing values in multivariate, geo-tagged time series data.
method Cross-Dimensional Self-Attention (CDSA) for sequence modeling across time, location, and sensor measurements.
result CDSA outperforms state-of-the-art methods in imputation and forecasting on real-world datasets.
Model detects electricity theft with high accuracy.
problem Detecting electricity theft on imbalanced datasets.
method Multi-head self-attention mechanism with dilated convolutions and binary mask.
result Achieved AUC of 0.926, improving previous work by 17%.
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 propose Dynamic Self-Attention (DSA), a new self-attention mechanism for sentence embedding. We design DSA by modifying dynamic routing in capsule network (Sabouretal.,2017) for natural language processing. DSA attends to informative words with a dynamic weight vector. We achieve new state-of-the-art …
Aligns attention distributions for improved accuracy and robustness.
problem Improving the accuracy and robustness of neural networks using attention mechanisms.
method Alignment attention that encourages key and query distributions to match within each head.
result Alignment attention leads to better accuracy, uncertainty estimation, and robustness across various tasks.
SANNE model generates embeddings for unseen nodes in graph networks.
problem Lack of embeddings for unseen nodes in graph networks.
method SANNE uses a transformer self-attention network to generate embeddings.
result SANNE achieves state-of-the-art results for node classification.
New method embeds time span into self-attention for better temporal pattern recognition.
problem Capturing temporal patterns in event sequences without recurrent networks.
method Functional time representation learning with Bochner's and Mercer's Theorems.
result Proposed methods outperform baseline models in various continuous-time event sequence prediction tasks.
Quaternion self-attention reduces computational cost and improves performance.
problem Existing quaternion self-attention increases computational cost and diverges attention distributions.
method Proposes a shared-score quaternion self-attention mechanism.
result Reduces score-computation multiplications by 75% and softmax operations from four to one.
Insurance companies must manage millions of claims per year. While most of these claims are non-fraudulent, fraud detection is core for insurance companies. The ultimate goal is a predictive model to single out the fraudulent claims and pay out the non-fraudulent ones immediately. Modern machine learning methods are we…
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.
Transformers predict price movements from limit order books.
problem Predicting price movements from limit order books.
method Causal convolutional network with masked self-attention.
result Significantly outperforms existing architectures on FI-2010 dataset.
Proposes SAHP for better Hawkes process modeling.
problem Predicting occurrence patterns of event sequences.
method Leverages self-attention to modify Hawkes process intensity function.
result Demonstrates effectiveness on real-world datasets.
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.
Self-attention model improves HAR from wearable sensors.
problem Capturing spatio-temporal context from sensor data.
method Proposes a self-attention based neural network model.
result Significant performance improvement over state-of-the-art models.
ST-SAN predicts flow with spatial-temporal dependencies using self-attention.
problem Challenges in predicting flow due to spatial-temporal dependencies.
method Spatial-Temporal Self-Attention Network (ST-SAN) that addresses temporal and spatial dependencies.
result Significant improvement in flow prediction accuracy (9% in inflow, 4% in outflow) compared to state-of-the-art methods.
Hyper-SAGNN learns patterns in hypergraphs for complex interactions.
problem Learning patterns in hypergraphs with variable-sized heterogeneous hyperedges.
method Self-attention based graph neural network for homogeneous and heterogeneous hypergraphs.
result Significantly outperforms state-of-the-art methods on various tasks.
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.
EFA extends self-attention to handle mixed data types and dynamic relevance.
problem Handling high-dimensional, mixed data types with dynamic relevance.
method Probabilistic generative model using self-attention and latent factor model.
result EFA consistently outperforms existing models in complex latent structure capture and reconstruction.
This paper offers an overview of neural network compression techniques.
problem Overparameterized neural networks are large and resource-intensive.
method Pruning, quantization, tensor decomposition, knowledge distillation.
result A comprehensive review of compression techniques for deep neural networks.
Improved electrical load forecasting model using Fourier-enhanced RNN.
problem Electrical load time series downscaling with high accuracy and low error.
method Combines recurrent neural network with Fourier seasonal embeddings and self-attention.
result Significantly reduces RMSE across different time horizons compared to existing methods.
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.
Paper proposes multiscale self-attentive convolutions for vision and language.
problem Improving language and vision understanding models using self-attention.
method Developed 1D and 2D Self Attentive Convolutions (SAC), multiscale SAC (MSAC).
result MSAC enhances model performance for vision and language tasks.
Efficient neural network optimization reduces costs and improves model performance.
problem High computational costs in optimizing neural networks, especially at scale.
method Introduces self-attentive feed-forward neural units (SAFFU) for efficient optimization.
result Explicit solutions outperform models optimized by backpropagation alone, and further training with backpropagation leads to better optima from smaller data sets.
Active-memory mechanisms can replace self-attention in Transformers, but optimal results often require both.
problem Replacing self-attention with active-memory mechanisms in Transformers.
method Evaluation of various active-memory mechanisms in a Transformer model.
result Active-memory mechanisms can achieve comparable results to self-attention for language modeling, but optimal results are often achieved by combining both mechanisms.
SAIN integrates user-item feedback with content attributes for better recommendation.
problem Cold start problems in recommendation models due to sparse user-item interactions.
method SAIN uses a self-attention mechanism to capture feature interactions and an information integration layer to combine feedback and content information.
result SAIN outperforms state-of-the-art models by 2.13% on public datasets.
SAKT improves knowledge tracing by focusing on relevant past activities.
problem Handling sparse data in knowledge tracing models.
method Self-attention based approach to identify relevant past activities.
result SAKT outperforms state-of-the-art models, improving AUC by 4.43%.
Improves sequential recommendation with relation-aware self-attention.
problem Improving accuracy in sequential recommendation.
method Integrates Transformer's self-attention mechanism with a probabilistic model of recommendation context.
result Significant improvements over recent baseline models.
Study algebraic invariants from lightning self-attention models.
problem Understanding polynomial coefficients of self-attention mechanisms.
method Identify algebraic invariants using polynomial coefficients and coordinate geometry.
result Found linear and nonlinear families of algebraic invariants.
Random forests with attention and self-attention improve regression performance.
problem Improving regression model performance on various datasets.
method Proposes new models using attention and self-attention mechanisms to solve regression problems.
result The models improve model performance on many datasets.