Attention weights may not accurately highlight important parts due to combinatorial shortcuts.
problem Inaccurate interpretation of attention weights in models.
method Theoretical analysis and design of experiments to show combinatorial shortcuts. Proposed two methods to mitigate this issue.
result Proposed methods improve the interpretability of attention mechanisms.
Linear attention in Transformers can be interpreted as dynamic VAR models.
problem Misalignment between Transformers and autoregressive forecasting objectives.
method Interpreting linear attention as VAR, rearranging MLP, attention, and flow.
result SAMoVAR improves performance, interpretability, and efficiency.
VALC provides concept-level interpretations of FLMs, overcoming word-level limitations.
problem Lack of higher-level structure interpretation in FLMs' attention weights.
method Formal definition of conceptual interpretation, variational Bayesian framework (VALC).
result VALC finds optimal language concepts for FLM predictions, providing concept-level interpretations.
Deep neural network models have recently draw lots of attention, as it consistently produce impressive results in many computer vision tasks such as image classification, object detection, etc. However, interpreting such model and show the reason why it performs quite well becomes a challenging question. In this paper,…
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…
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.
Improves dialogue response model interpretability using attention and regularization.
problem Improving interpretability of dual encoder models for dialogue response suggestions.
method Integrates attention mechanism and novel regularization loss to emphasize important words.
result Improves model accuracy and interpretability compared to existing methods.
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.
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.
Proposes new methods for interpreting document classification models.
problem Interpretation fragility of attention-based neural networks.
method Corpus-level and concept-based explanation methods using attention weights.
result Extracts semantically meaningful keywords and concepts for model predictions.
Transformers interpreted as probabilistic Laplacian Eigenmaps steps.
problem Improving transformer performance through probabilistic interpretation.
method Probabilistic Laplacian Eigenmaps model derivation and graph diffusion step.
result Subtracting identity from attention matrix improves transformer performance.
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.
New interpretation of attention in Transformers and Graph Attention Networks.
problem Understanding and improving attention mechanisms in deep learning models.
method Decomposed attention into a kernel and a normalization term; generalized the kernel function and norm.
result Generalized attention leads to better performance on various tasks.
Disease progression models are instrumental in predicting individual-level health trajectories and understanding disease dynamics. Existing models are capable of providing either accurate predictions of patients prognoses or clinically interpretable representations of disease pathophysiology, but not both. In this pape…
Federated learning interprets temporal dynamics across clients with graph attention.
problem Interpreting temporal patterns across decentralized, heterogeneous systems with nonlinear dynamics.
method Graph Attention Network for learning state transition models over latent states communicated between clients.
result First interpretable characterization of cross-client temporal interdependencies in decentralized nonlinear systems.
Inspired by recent work in attention models for image captioning and question answering, we present a soft attention model for the reinforcement learning domain. This model uses a soft, top-down attention mechanism to create a bottleneck in the agent, forcing it to focus on task-relevant information by sequentially que…
Enhances image captioning with novel context combination methods.
problem Improving machine learning for image captioning with structured learning and meaningful interpretation.
method Combines Feature Distribution Composition (FDC), Multiple Role Representation Crossover (MRRC) attention layers, and language decoder.
result Significantly improved image captioning performance (35.3%) and established new standards.
We present an attention mechanism inspired from definition of screened Coulomb potential. This attention mechanism was used to interpret the Graph Attention (GAT) model layers and training dataset by using a flexible and scalable framework (CoulGAT) developed for this purpose. Using CoulGAT, a forest of plain and resne…
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.
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.
Although deep convolutional neural networks achieve state-of-the-art performance across nearly all image classification tasks, their decisions are difficult to interpret. One approach that offers some level of interpretability by design is \textit{hard attention}, which uses only relevant portions of the image. However…
Inspired by the observation that humans are able to process videos efficiently by only paying attention where and when it is needed, we propose an interpretable and easy plug-in spatial-temporal attention mechanism for video action recognition. For spatial attention, we learn a saliency mask to allow the model to focus…
New approach improves linear-time attention for language models.
problem Challenges of quadratic attention in long-sequence modelling, especially for discrete data.
method Reinterpreting linear attention through latent probabilistic graphical models, introducing asymmetric structure and recurrent parameterisation.
result Our model achieves competitive performance and outperforms existing linear attention variants on language modelling benchmarks.
STAM learns important time steps and variables for multivariate time series prediction.
problem Accurate interpretation of multivariate time series predictions.
method Spatiotemporal attention mechanism (STAM) for multivariate time series modeling.
result STAM maintains state-of-the-art prediction accuracy with improved interpretability.
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.
SNI framework for mixed-type data imputation interprets and explains missing values.
problem Missing data in mixed-type databases skew analysis results.
method SNI couples statistical priors with neural attention to impute and explain missing values.
result SNI provides interpretable feature dependency diagnostics and soft regularization of attention.
Intelligent Momentum Transformer outperforms traditional trading strategies.
problem Improving time-series momentum and mean-reversion trading strategies.
method Attention-based deep-learning architecture (Momentum Transformer) combining attention and LSTM.
result Momentum Transformer outperforms benchmarks and adapts to new market regimes.
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…
Introduces a novel spatial attention module for convolutional networks.
problem Irregular boundaries in position-wise spatial attention maps hamper model generalization.
method Introduces a convolutional rectangular attention module with 5 parameters.
result Systematically outperforms position-wise counterparts in experiments.
SANs estimate feature importance in neural models, identifying interactions and high-ranked features.
problem Understanding and interpreting black-box neural network models.
method Self-Attention Network (SAN) architecture for feature importance estimation.
result SANs identify similar high-ranked features and feature interactions as other methods, improving predictive performance.
We propose a novel high-performance and interpretable canonical deep tabular data learning architecture, TabNet. TabNet uses sequential attention to choose which features to reason from at each decision step, enabling interpretability and more efficient learning as the learning capacity is used for the most salient fea…
Proposes a self-attention-based method for drug-target interaction prediction.
problem Interpreting machine learning models for drug-target interactions.
method Self-attention-based multi-view representation learning approach.
result Competitive prediction performance with biologically interpretable results.
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.
A brain-inspired spiking Transformer reduces energy consumption and enhances interpretability.
problem Energy inefficiency and lack of interpretability in Transformer models.
method Spiking STDP Transformer using spike-timing-dependent plasticity (STDP) for self-attention.
result Achieves 94.35% and 78.08% accuracy on CIFAR-10 and CIFAR-100 datasets respectively, with 88.47% energy reduction.
Attention Model has now become an important concept in neural networks that has been researched within diverse application domains. This survey provides a structured and comprehensive overview of the developments in modeling attention. In particular, we propose a taxonomy which groups existing techniques into coherent …
SpotV2Net forecasts intraday spot volatilities using graph attention networks.
problem Forecasting multivariate intraday spot volatilities accurately.
method Graph Attention Network architecture with Fourier estimates of spot and vol-of-vol volatilities.
result SpotV2Net outperforms other models in forecasting accuracy.
RETAIN model improves glucose forecasting for diabetics, offering both accuracy and interpretability.
problem Inability of deep learning models to interpret their predictions in healthcare.
method Two-level attention mechanism in a recurrent neural network (RETAIN) architecture.
result RETAIN model achieves comparable accuracy to LSTM and FCN models while being highly interpretable.
Paper introduces a neural framework for accurate energy forecasting.
problem Challenges of forecasting energy demand and supply due to variability of renewable sources and dynamic consumption patterns.
method Integrates Neural ODEs, graph attention, multi-resolution wavelet transformations, and adaptive learning of frequencies.
result Consistently outperforms state-of-the-art baselines in various forecasting metrics across diverse datasets.
Recent years have witnessed the successful marriage of finance innovations and AI techniques in various finance applications including quantitative trading (QT). Despite great research efforts devoted to leveraging deep learning (DL) methods for building better QT strategies, existing studies still face serious challen…
Attention-only transformers learn from context via two stages of inference.
problem Learning from corrupted token sequences in minimal transformers.
method Two-stage empirical Bayes interpretation: kernel-weighted posterior mean and particle dynamics.
result Effective denoising without explicit noise schedules, showing posterior-mean recovery under asymptotic conditions.
LATTE tackles heterogeneous network embedding challenges with layer-stacked attention.
problem Aggregating higher-order indirect relations in heterogeneous networks.
method Layer-stacked ATTention Embedding (LATTE) that decomposes meta relations at each layer.
result LATTE achieves state-of-the-art performance on benchmark 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.
Enhances group convolutional networks with attention to learn meaningful relationships.
problem Lack of explicit means to learn meaningful relationships among symmetry patterns.
method Introduces attentive group equivariant convolutions, applying attention during convolution.
result Consistently outperforms conventional group convolutional networks on benchmark datasets.
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.
Models use embeddings and attention for better claim severity prediction.
problem Improving predictive modeling of claim severity with categorical data.
method Developed neural networks and attention-based architectures with embeddings.
result Attention-based models enhance predictive performance with contextual augmentation.
We present an open-source tool for visualizing multi-head self-attention in Transformer-based language representation models. The tool extends earlier work by visualizing attention at three levels of granularity: the attention-head level, the model level, and the neuron level. We describe how each of these views can he…
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. 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.