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.
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.
Minimum attention improves reinforcement learning performance in high-dimensional dynamics.
problem Improving reinforcement learning performance in high-dimensional nonlinear dynamics.
method Applying minimum attention as a regularization technique in reinforcement learning, including model-based and model-free approaches.
result Minimum attention outperforms state-of-the-art algorithms in few-shot adaptation and variance reduction.
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.
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.
Attention models have had a significant positive impact on deep learning across a range of tasks. However previous attempts at integrating attention with reinforcement learning have failed to produce significant improvements. We propose the first combination of self attention and reinforcement learning that is capable …
AReLU uses attention-based rectification to improve neural network performance.
problem Improving neural network performance through better activation functions.
method Integrates attention mechanism with rectified linear unit (ReLU) to learn and scale feature maps.
result AReLU significantly boosts performance of most network architectures with minimal changes.
Improved language models with talking-heads attention.
problem Language model perplexity and quality issues.
method Added linear projections in multi-head attention.
result Better perplexities and quality in language tasks.
Novel GNN model tackles few-shot learning with improved performance.
problem Few-shot learning with GNN suffers from over-fitting and over-smoothing.
method Proposes Attentive GNN with triple-attention mechanism.
result Improves GNN performance for few-shot learning tasks.
Kernel PCA explains self-attention mechanisms in deep learning models.
problem Understanding and explaining self-attention mechanisms in deep learning models.
method Deriving self-attention from kernel principal component analysis (kernel PCA).
result RPC-Attention, a robust attention mechanism, outperforms softmax attention in various tasks.
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.
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…
New model uses attention for in-context learning of categorical data.
problem Learning from categorical data in context.
method Attention-based network with self-attention and cross-attention layers, using functional gradient descent.
result Model can perform multi-step inference for categorical observations.
Improved graph attention model for noisy graphs.
problem Understanding and improving graph attention in noisy graphs.
method Proposes SuperGAT, a self-supervised graph attention network.
result SuperGAT learns more expressive attention by encoding edges.
Study integrates attentional and spacing factors to improve category learning models.
problem Understanding the impact of training sequences on category learning.
method Introduced a novel integration of attentional factors and spacing into logistic knowledge tracing models.
result Enhanced model predicts students' learning outcomes better than existing models.
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.
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.
AIM models explain deep learning in attention layers, offering solvable insights.
problem Understanding how deep learning models learn in attention layers.
method Statistical mechanics and random matrix theory.
result Closed-form predictions for Bayes-optimal generalization error and gradient descent performance.
Multi-head attention outperforms single-head in in-context linear regression tasks.
problem Comparing performance of transformer with single-/multi-head attention in in-context learning.
method Theoretical analysis of performance of transformers with different attention mechanisms in linear regression tasks.
result Multi-head attention with a substantial embedding dimension outperforms single-head attention in in-context linear regression tasks.
Adapts attention to supervised learning for personalized predictions.
problem Personalized predictions for each data point with model simplicity.
method Local model fitting with attention weighting for tabular data.
result Attention weighting improves predictive performance and preserves interpretability.
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.
ABC learns context-aware representations for clustering.
problem Learning latent representations that adapt to context in machine learning.
method Attention-based neural architecture that learns a similarity kernel.
result Competitive results for clustering Omniglot characters.
Although group convolutional networks are able to learn powerful representations based on symmetry patterns, they lack explicit means to learn meaningful relationships among them (e.g., relative positions and poses). In this paper, we present attentive group equivariant convolutions, a generalization of the group convo…
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.
This work proposes a collaborative multi-head attention layer to reduce model size without sacrificing accuracy.
problem Over-parameterization in transformer models trained with large datasets.
method Proposes a collaborative multi-head attention layer that shares key/query projections.
result Reduction in model size by 4 for same accuracy and speed.
Gated attention improves performance by using a hierarchical mixture of experts.
problem Improving performance of self-attention mechanisms in Transformers.
method Rigorously show that gated attention can be modeled as a hierarchical mixture of experts, providing a theoretical justification for its benefits.
result Gated attention is more sample-efficient than multi-head self-attention, requiring fewer data points to achieve the same estimation error.
We have successfully implemented the "Learn to Pay Attention" model of attention mechanism in convolutional neural networks, and have replicated the results of the original paper in the categories of image classification and fine-grained recognition.
GSAN learns adaptive node representations using geometric scattering and attention.
problem Oversmoothing in node representation learning.
method Attention-based architecture integrating geometric scattering and GCN channels.
result GSAN outperforms previous networks in semi-supervised node classification.
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.
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%.
Attention networks show promise for both vision and language tasks, by emphasizing relationships between constituent elements through weighting functions. Such elements could be regions in an image output by a region proposal network, or words in a sentence, represented by word embedding. Thus far the learning of atten…
CLEAR learns causal graphs from attention in recommender systems to explain user behavior.
problem Understanding why specific recommendations are made in recommender systems.
method CLEAR learns session-specific causal graphs from attention in pre-trained neural recommenders, addressing latent confounders.
result CLEAR provides counterfactual explanations that are shorter and more effective than naive methods.
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…
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.
Minimalist softmax attention learns constrained Boolean functions with supervision.
problem Learning k-bit Boolean functions, especially AND and OR. method Minimalist single-head softmax-attention mechanism with teacher forcing.
result Minimalist attention can solve Boolean tasks with supervision, but not without.
Bayesian attention modules improve model interpretability and performance.
problem Deterministic attention modules limit model interpretability and optimization.
method Proposes a scalable stochastic attention module using simplex-constrained distributions and Bayesian learning.
result Consistent improvements over baselines in various attention-based models.
Study on multi-head softmax attention dynamics for in-context learning.
problem Understanding and optimizing multi-head softmax attention models for multi-task linear regression.
method Gradient flow analysis and spectral mapping technique.
result Gradient flow converges to optimal multi-head softmax attention model, with task allocation emerging during training.
Slot Attention extracts object-centric representations from images.
problem Learning distributed representations that don't capture natural scene composition.
method Slot Attention module interfaces with CNN outputs to produce task-dependent abstract slots.
result Slot Attention enables generalization to unseen compositions.
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.
We demystify attention patterns in multi-head softmax models for linear data.
problem Understanding the training dynamics and emergent patterns in multi-head softmax attention models.
method Extensive empirical experiments and rigorous theoretical analysis.
result Multi-head softmax attention models approximate a debiased gradient descent predictor, outperforming single-head attention and achieving near-Bayesian optimality.
Attention learns PCA on Gaussian data, proving its connection to principal component analysis.
problem Principal component analysis on Gaussian data.
method Analysis of attention mechanisms through PCA, covering finite and infinite prompt regimes.
result Attention aligns with principal eigenvectors of covariance matrices, converging to optimal solutions in the infinite-prompt limit.
New approach improves multi-head attention by making heads less similar.
problem Multi-head attention can lead to similar features, reducing model expressiveness.
method Proposes a non-parametric approach using Bayesian techniques to make heads repel each other.
result Improves feature diversity, leading to better representations and performance.
Recent trends of incorporating attention mechanisms in vision have led researchers to reconsider the supremacy of convolutional layers as a primary building block. Beyond helping CNNs to handle long-range dependencies, Ramachandran et al. (2019) showed that attention can completely replace convolution and achieve state…
Bayesian Attention Networks compress data by focusing on key training samples.
problem Lossless data compression for efficiency.
method Bayesian Attention Networks with attention factors and latent space.
result Efficient prediction using a few correlated training samples.
Study compares deep learning models for traffic forecasting, highlighting graph elements' impact.
problem Challenges in forecasting spatial-temporal traffic patterns.
method In-depth comparative study of four deep neural network models with different basic elements.
result Graph attention improves long-term predictions in traffic forecasting models.
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.
Orion-Bix combines biaxial attention and meta-learning for tabular few-shot learning.
problem Scaling and generalizing tabular models with mixed numeric and categorical fields, weak feature structure, and limited labeled data.
method Orion-Bix uses biaxial attention and meta-learned in-context reasoning to efficiently capture local and global dependencies.
result Orion-Bix outperforms gradient-boosting baselines and state-of-the-art tabular models on public benchmarks.