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.
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.
Study reveals attention mechanism's similarity computation parallels traditional machine learning.
problem Understanding the essence and principles of attention mechanism in deep learning.
method Examined classic metrics and vector space properties in manifold learning, clustering, and supervised learning to identify key characteristics of similarity computation and information propagation.
result Self-attention mechanism in deep learning adheres to the same principles but operates more flexibly and adaptively.
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…
GOAT improves attention mechanisms by learning better priors.
problem Standard attention mechanisms use a naive uniform prior, limiting flexibility and generalization.
method GOAT introduces a trainable, continuous prior that replaces the uniform assumption, maintaining compatibility with optimized kernels.
result GOAT avoids representational trade-offs and learns an extrapolatable prior that combines positional flexibility with length generalization.
CoulGAT interprets GAT models by analyzing node interactions.
problem Understanding and interpreting the complex interactions within graph attention networks.
method Developed a CoulGAT framework to analyze and interpret GAT model layers and datasets.
result Extracted node-node and node-feature interactions to define a standard model for graph structure.
Attention mechanisms in deep neural networks have achieved excellent performance on sequence-prediction tasks. Here, we show that these recently-proposed attention-based mechanisms---in particular, the Transformer with its parallelizable self-attention layers, and the Memory Fusion Network with attention across modalit…
The softmax content-based attention mechanism has proven to be very beneficial in many applications of recurrent neural networks. Nevertheless it suffers from two major computational limitations. First, its computations for an attention lookup scale linearly in the size of the attended sequence. Second, it does not enc…
Single-head attention approximates any function under various norms.
problem Universal approximation of functions using attention mechanisms.
method Interpreting attention as partitioning and summing linear transformations.
result Single-head attention can approximate any continuous function under L∞-norm and Lebesgue integrable functions under Lp-norm. Paper proposes a new hierarchical attention mechanism for multi-scale data.
problem Challenges in applying neural attention to multi-scale, multi-modal data.
method Developed a mathematical framework for multi-modal, multi-scale data and derived optimal neural attention mechanics.
result Proposed hierarchical attention mechanism improves transformer performance in multi-scale, multi-modal settings.
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.
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.
New insights into attention mechanisms reveal dramatic trade-offs between rank and heads.
problem Dramatic trade-offs between rank and number of heads in attention mechanisms.
method Presented a simple target function and proved theoretical limits.
result Full-rank attention is necessary for long contexts, while low-rank is sufficient for short ones.
As an important part of speech recognition technology, automatic speech keyword recognition has been intensively studied in recent years. Such technology becomes especially pivotal under situations with limited infrastructures and computational resources, such as voice command recognition in vehicles and robot interact…
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.
Graph Neural Networks (GNNs) are powerful to learn the representation of graph-structured data. Most of the GNNs use the message-passing scheme, where the embedding of a node is iteratively updated by aggregating the information of its neighbors. To achieve a better expressive capability of node influences, attention m…
Graph attention is not always beneficial; conditions for perfect node classification are identified.
problem Understanding when graph attention mechanisms improve node classification performance.
method Theoretical analysis using Contextual Stochastic Block Models (CSBMs).
result Graph attention mechanisms are more effective when structure noise exceeds feature noise, and simpler graph convolution operations are better when feature noise predominates.
Visual Question Answering (VQA) requires AI models to comprehend data in two domains, vision and text. Current state-of-the-art models use learned attention mechanisms to extract relevant information from the input domains to answer a certain question. Thus, robust attention mechanisms are essential for powerful VQA mo…
Attention mechanism is effective in both focusing the deep learning models on relevant features and interpreting them. However, attentions may be unreliable since the networks that generate them are often trained in a weakly-supervised manner. To overcome this limitation, we introduce the notion of input-dependent unce…
Extracts important peaks from XRD spectra using Attention mechanism.
problem Identifying significant peaks in XRD patterns for material properties.
method Convolutional neural network with Attention mechanism to analyze deep features.
result Selected lattice constant predicts cathodic material cell voltage.
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.
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.
ABIForest improves anomaly detection using attention weights.
problem Anomaly detection in datasets.
method Attention mechanism integrated into Isolation Forest.
result ABIForest outperforms standard Isolation Forest on synthetic and real datasets.
The study reveals how attention paths in Transformers influence learning outcomes.
problem Understanding the theoretical basis of Transformers' performance.
method Developed a statistical mechanics theory for a simplified attention network.
result The predictor statistics are influenced by the combination of attention paths.
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.
MAT uses attention mechanism for molecule property prediction.
problem Designing a competitive neural network for molecule property prediction.
method Augmented attention mechanism using inter-atomic distances and molecular graph structure.
result MAT achieves state-of-the-art performance on diverse molecular prediction tasks.
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.
OLS predictions are shown to be similar to attention mechanisms in models.
problem OLS in traditional statistics and econometrics.
method Rewriting OLS as an attention mechanism in a transformed space.
result OLS can be understood as minimizing squared prediction errors via optimal embedding and decoding.
Linformer reduces transformer complexity to linear, improving efficiency.
problem High cost of training and deploying large transformer models for long sequences.
method Approximates self-attention with low-rank matrix, proposing Linformer with O(n) complexity. result Linformer performs similarly to standard transformers but is more memory- and time-efficient.
Neural networks using transformer-based architectures have recently demonstrated great power and flexibility in modeling sequences of many types. One of the core components of transformer networks is the attention layer, which allows contextual information to be exchanged among sequence elements. While many of the prev…
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.
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.
Paper proposes an attention sampler for reducing attention mechanism computation.
problem Computational challenges in large-scale attention-based models.
method Importance sampling in streaming setting, attention sampler.
result Significantly reduces the computational burden of attention mechanisms.
Study proposes a statistical test for Vision Transformer's attention mechanisms.
problem ViT's attention mechanisms may focus on irrelevant regions, leading to unreliable evidence.
method Selective inference framework to quantify statistical significance of attentions as p-values.
result Proposed method enables reliable quantification of false positive detection probability of attentions.
New attention mechanism improves meta-transfer learning in dynamic tasks.
problem Underfitting in meta-transfer learning with dynamic tasks.
method Proposed Recurrent Memory Reconstruction (RMR) attention mechanism.
result ASNP-RMR significantly outperforms baselines in various tasks.
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.
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.
Paper proposes a novel stock forecasting method combining attention and EMD.
problem Challenges in forecasting stock movement due to noise and lack of stock market information.
method Uses attention mechanism to consider both stock market and individual stock information, and EMD for noise reduction.
result Proposed method significantly outperforms state-of-the-art baselines.
Visual attention serves as a means of feature selection mechanism in the perceptual system. Motivated by Broadbent's leaky filter model of selective attention, we evaluate how such mechanism could be implemented and affect the learning process of deep reinforcement learning. We visualize and analyze the feature maps of…
IAL uses interactive learning to improve model performance with minimal human feedback.
problem Overfitting and high human interaction cost in training neural networks.
method IAL framework with NAP attention generator and reranking algorithm.
result IAL significantly outperforms baselines with less retraining and human interaction.
KFAtt improves CTR prediction by modeling user behavior with Kalman filtering attention.
problem Improving CTR prediction in personalized e-commerce search engines.
method KFAtt combines Kalman filtering with attention mechanisms to model user behavior.
result KFAtt outperforms existing methods in CTR prediction, achieving better performance in both offline and online settings.
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.
Mathematical study shows post-hoc explanations are better than attention weights alone.
problem Understanding the internal behavior of attention-based models.
method Mathematical analysis of a simple attention-based architecture.
result Post-hoc explanations provide more useful insights than attention weights alone.
MEANTIME improves sequential recommendation by using multi-temporal embeddings and attention mechanisms.
problem Limited use of timestamp information and information bottleneck in sequential recommendation models.
method MEANTIME employs multiple types of temporal embeddings and attention mechanisms to capture diverse patterns from user behavior sequences.
result MEANTIME outperforms state-of-the-art sequential recommendation methods.
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.
AttViz offers online visualizations of neural language model attention mechanisms.
problem Limited interpretability of neural language models.
method Online toolkit for exploring self-attention mechanisms.
result Visualizations help understand model decision-making.
TNP-KR improves scalability of NPs with Transformer blocks and attention mechanisms.
problem Scalability bottleneck in NPs and GPs, especially for large datasets.
method Introduces TNP-KR with KRBlock, kernel-based attention, and two attention mechanisms.
result TNP-KR with DKA outperforms Performer and achieves state-of-the-art results.
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.