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.
Survey categorizes attention models across various domains.
problem Understanding and improving attention models in neural networks.
method Taxonomy and review of existing techniques.
result Provides a structured overview of attention models.
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.
Improved Q&A model with LSTM and bi-directional attention.
problem Enhancing neural network models for effective question answering.
method Implemented a Bi-directional attention flow layer connected to a Multi-layer LSTM encoder, with a new end-index decoder layer conditioning on start-index output.
result Increased model performance by 15.16% on test set.
Elliptical Attention improves transformer performance by focusing on contextually relevant features.
problem Transformer models suffer from representation collapse and are vulnerable to contaminated samples.
method Uses Mahalanobis distance to define hyper-ellipsoidal neighborhoods for attention weights.
result Elliptical Attention reduces representation collapse and enhances model robustness.
Studying a softmax-attention model, we show that the learned query converges to the latent signal subspace spanned by the informative direction.
problem Understanding the theoretical principles of attention mechanisms in large-scale token collections.
method Deriving a population objective and analyzing the limiting ordinary differential equation of the learning dynamics.
result The learned query asymptotically recovers the latent signal up to the intrinsic sign ambiguity.
Bitcoin's attention is linked to Google Trends data, not general uncertainty.
problem Bitcoin's correlation with Google Trends data was previously misunderstood.
method Analyzed bidirectional relationships between Bitcoin returns and Google Trends attention over six days.
result Information flows from Bitcoin volatility to Google Trends attention, not the other way.
New model improves graph attention for relational data.
problem Improving graph attention models for relational data.
method Relational Graph Attention Networks (R-GAT) extending non-relational graph attention to relational data.
result R-GAT performs worse than expected, but some configurations marginally improve molecular property modeling.
Agent learns causal relationships from visual data to perform tasks.
problem Performing tasks in novel environments with latent causal structures.
method Learning-based approach to induce causal graphs from visual observations, using attention mechanisms.
result Effective generalization to new tasks with unseen causal structures.
Analyzing a comprehensive news dataset, we document that joint news coverage triggers attention contagion, causing temporarily inflated valuations for affected stocks. Tracing SEC EDGAR visits from unique IPs, we provide direct evidence of attention spillovers between stocks. Stocks with greater joint news coverage exh…
Bi-LSTM with attention generates jazz music with rich nuances.
problem Challenges in producing realistic music with structure and rationality.
method Deep learning, Bi-directional Long Short Term Memory (Bi-LSTM) Neural Network with Attention.
result Bi-LSTMs with attention preserve the richness and technical nuances of old style music.
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.
Unified framework for critical scaling of inverse temperature in self-attention.
problem Conflicting inverse-temperature laws for long-context self-attention.
method Counting gaps and defining an upper-tail accumulation scale.
result Critical inverse-temperature scale determined by gap-counting function.
Neural nets predict user attention from mouse movements.
problem Predicting user attention from mouse cursor movements.
method Investigated different mouse movement representations and trained neural networks.
result Neural networks outperform handcrafted features for predicting user attention.
Graph2Seq converts graph inputs to sequences with attention-based neural networks.
problem Converting graph inputs to sequences for machine learning tasks.
method Graph-to-sequence neural encoder-decoder model with attention-based LSTM.
result Achieves state-of-the-art performance on various tasks.
A reinforcement learning model uses attention to make actions interpretable.
problem Creating interpretable reinforcement learning models.
method Soft attention mechanism to focus on task-relevant information.
result The model achieves competitive performance on Atari tasks and is interpretable.
News attention to financial intermediaries and crises predicts excess bond premium and macroeconomic movements.
problem Drivers of the excess bond premium (EBP).
method News attention to 180 topics captures up to 80% of EBP variation and forecasts macroeconomic movements.
result News attention to financial intermediaries and crises drives up the EBP and predicts macroeconomic downturns.
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.
MOCA uses modular attention to estimate causal effects from complex data.
problem Estimating causal effects from observational data with complex, non-linear, and high-dimensional treatment and outcome mechanisms.
method MOCA is a transformer-based framework that separates treatment and outcome modeling through modular design and one-way attention mechanism, with cutting-feedback to prevent outcome influence on treatment representations.
result MOCA outperforms classical estimators and machine learning approaches across various simulated and real-world scenarios.
Study relaxes identification assumptions for natural direct effects in non-randomized settings.
problem Identifying causal direct effects under unmeasured confounding.
method Developed relaxed conditions for identifying natural direct effects in non-randomized settings.
result Identified natural direct effect under unmeasured confounding conditions.
Language models fail to process hallucinated responses, and this study diagnoses the failure.
problem Language models fail to process hallucinated responses, leading to over-concentration or diffuse attention.
method The study uses forced scoring of benchmark-labeled responses to compute attention shapes and analyze the symmetric component of the degree-normalized attention operator.
result The study proves that every transpose-invariant spectral diagnostic of the attention operator is orientation-blind and bounds the sensitivity of any Lipschitz diagnostic by the asymmetry coefficient \(G\).
Paper proposes a CNN-LSTM model for image denoising and reconstruction.
problem Challenging task of image denoising and reconstruction in computer vision.
method Proposes an encoder-decoder model with direct attention, using CNN for encoding and LSTM for decoding.
result Model can reconstruct clean images from highly corrupted ones, even when human understanding is difficult.
This research integrates attention into XAI frameworks for better model explanations.
problem Improving the interpretability of transformer models.
method Developed two novel explanation methods: Shapley value decomposition and token-level directional derivatives.
result Attention weights can be meaningfully incorporated into XAI frameworks, enhancing transformer explainability.
I-BERT extends Transformer's self-attention to arbitrary input lengths.
problem Transformer models struggle with inductive generalization to unseen input lengths.
method Replaces positional encodings with a recurrent layer.
result I-BERT achieves state-of-the-art results on algorithmic tasks.
Improves GATs by adding margin-based constraints to prevent over-fitting and over-smoothing.
problem Over-fitting and over-smoothing in GATs.
method Margin-based constraints on attention weights and graph structure.
result Significant improvements over previous GATs on various datasets.
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.
This paper analyzes the interpolation error of nonlinear Attention compared to linear regression.
problem Understanding the interpolation error of nonlinear Attention in high-dimensional settings.
method Derives explicit expressions for mean-squared interpolation error using signal-plus-noise model and random matrix theory.
result Nonlinear Attention generally incurs a larger interpolation error than linear regression, but this gap can be reversed with structured signals.
Paper proposes a faster neural machine translation model using election methods and Q-learning.
problem Slower inference time in complex attention models.
method Modelled attention network using election methods and Q-learning.
result Inference time is less than a standard Bahdanau translator, results comparable.
We replace the Hidden Markov Model (HMM) which is traditionally used in in continuous speech recognition with a bi-directional recurrent neural network encoder coupled to a recurrent neural network decoder that directly emits a stream of phonemes. The alignment between the input and output sequences is established usin…
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.
A new multi-layer attention mechanism improves speech keyword recognition accuracy.
problem Inaccurate attention weights in LSTM networks for speech keyword recognition.
method Introducing information from layers prior to feature extraction into attention weights calculations.
result The proposed multi-layer attention mechanism leads to more accurate attention weights and improved keyword spotting performance.
Recent links between Finsler Geometry and the geometry of spacetimes are briefly revisited, and prospective ideas and results are explained. Special attention is paid to geometric problems with a direct motivation in Relativity and other parts of Physics.
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.
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.
Randomly initialized transformers show extreme token preferences.
problem Structural biases in randomly initialized transformers.
method Dissection of transformer architecture at initialization.
result Initialization-induced biases persist throughout training.
Proposes a deep learning approach for attributed graph clustering.
problem Suboptimal performance in graph clustering due to two-step frameworks.
method Goal-directed deep learning approach using attention networks and inner product decoders.
result Superior performance compared to state-of-the-art algorithms.
HKT improves sequence processing with multi-scale attention and kernel analysis.
problem Processing sequences at multiple scales with efficient attention mechanisms.
method Trainable causal downsampling and convex weights for level-specific score matrices.
result HKT achieves consistent gains over standard attention across various tasks.
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.
Transformer models align words through attention weights, closely approximating Optimal Transport.
problem Understanding the internal mechanism of transformer models in language processing.
method Empirical evidence and theoretical analysis of attention weights and their relation to Optimal Transport.
result Transformer models can simulate gradient descent on the dual of entropy-regularized OT problem, providing a theoretical foundation for token alignment.
Softmax is found ineffective for NL block, leading to improved performance.
problem Inefficiency of softmax in NL block for global context modeling.
method Empirical analysis and replacement of softmax with scaling factor.
result Improved performance on various datasets with reduced computational cost.
Transformers without skip connections collapse token representations to a single direction.
problem Rapid convergence of token representations to a single direction in self-attention-only Transformers.
method Analysis of layer normalization, residual connections, and multi-head attention mechanisms.
result Residual connections prevent rank collapse in real Transformers, while MLPs generate new feature directions.
New stochastic gradient descent with random search directions improves efficiency and convergence.
problem Efficiency and convergence of stochastic gradient descent methods.
method Developed a new class of stochastic gradient descent algorithms with random search directions.
result Established almost sure convergence and provided Lp rates of convergence. AutoAnchor uses cross-attention to improve text-to-image model unlearning.
problem Mitigating harmful or copyrighted content in text-to-image models.
method Two-stage framework that automatically synthesizes manifold-proximal anchors using cross-attention consistency loss.
result Effective robust and unbiased unlearning across various baselines.
Gradient flow in softmax models tends to produce low-entropy outputs.
problem Understanding the training dynamics of softmax-based models.
method Analysis of gradient flow dynamics in the value-softmax model.
result Gradient flow drives optimization towards low-entropy solutions.
Self-attention optimizers converge to optimal weights, revealing bias patterns.
problem Understanding the implicit bias in self-attention mechanisms.
method Analysis of gradient-based optimization in self-attention layers.
result Adaptive step-size strategies can accelerate convergence to optimal weights.
Linearized attention fails to converge to NTK limit even at large widths.
problem Understanding the convergence of attention mechanisms to the kernel regime.
method Analyzes linearized attention and its relationship to the NTK limit, considering practical widths and conditions.
result Linearized attention does not converge to its NTK limit at any practical width, revealing a fundamental trade-off.
Axial-LOB predicts stock prices from LOB data using attention layers.
problem Predicting stock price from LOB data with long-range dependencies.
method Axial-LOB uses gated position-sensitive axial attention layers to incorporate global interactions.
result Axial-LOB achieves state-of-the-art performance in stock price prediction.
Improves point-cloud reconstruction by optimizing projections with self-attention.
problem Inefficient and non-metric projection methods for sliced Wasserstein distances.
method Proposes distributional sliced Wasserstein distance with self-attention for permutation-invariant and metric optimization.
result Self-attention amortized distributional projection optimization achieves better performance in point-cloud reconstruction.