Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

60120180240 · Jun 202019922001200920172026
48 results for attention patterns

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.

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.

This work improves KG embeddings by integrating hyperbolic and attention mechanisms.

problem Preserving hierarchical and logical patterns in KGs with low-dimensional embeddings.
method Combines hyperbolic reflections/rotations with attention mechanisms to capture complex relational patterns.
result Improves MRR by up to 6.1% on standard benchmarks and new state-of-the-art results in high dimensions.

Acoustic Scene Classification (ASC) is a challenging task, as a single scene may involve multiple events that contain complex sound patterns. For example, a cooking scene may contain several sound sources including silverware clinking, chopping, frying, etc. What complicates ASC more is that classes of different activi…

2019-09-16abs ↗pdf ↗

LNUCB-TA improves MAB performance by dynamically adjusting exploration rates and recognizing spatiotemporal patterns.

problem Suboptimal performance in environments with rapidly changing reward structures and static exploration rates.
method Hybrid model combining linear and nonlinear estimation, with adaptive k-NN for temporal attention.
result Significantly outperforms state-of-the-art algorithms in cumulative and mean reward, convergence, and robustness.

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.

Transformers learn to integrate information from past positions incrementally, specializing heads in distinct patterns.

problem How transformers learn to integrate information from multiple past positions with varying statistical significance.
method High-order Markov chain task, incremental learning, sparse attention patterns, simplified differential equations, stage-wise convergence, early stopping as regularizer.
result Transformers learn to specialize heads in distinct patterns, shifting from competitive to cooperative learning dynamics.

Forecasting multivariate time series data, such as prediction of electricity consumption, solar power production, and polyphonic piano pieces, has numerous valuable applications. However, complex and non-linear interdependencies between time steps and series complicate the task. To obtain accurate prediction, it is cru…

2018-09-12abs ↗pdf ↗

New neural network improves audio classification accuracy.

problem Challenging audio classification problem in pattern recognition.
method Introduces a Classifier-Attention-Based Convolutional Neural Network (CAB-CNN) with an attention mechanism to reduce classifier complexity.
result Significantly improves audio classification performance, achieving more than 10% improvements.

Enhanced deep learning model forecasts household leverage series accurately.

problem Forecasting household leverage series due to complex temporal-spatial dynamics.
method TSEN model with multiple RNN-based layers and an attention layer.
result Captures temporal-spatial dynamics and provides more accurate predictions.

BERT-based architectures currently give state-of-the-art performance on many NLP tasks, but little is known about the exact mechanisms that contribute to its success. In the current work, we focus on the interpretation of self-attention, which is one of the fundamental underlying components of BERT. Using a subset of G…

2019-08-21abs ↗pdf ↗

Modern deep learning approaches have achieved groundbreaking performance in modeling and classifying sequential data. Specifically, attention networks constitute the state-of-the-art paradigm for capturing long temporal dynamics. This paper examines the efficacy of this paradigm in the challenging task of emotion recog…

2019-04-24abs ↗pdf ↗

Neural networks are surprisingly good at interpolating and perform remarkably well when the training set examples resemble those in the test set. However, they are often unable to extrapolate patterns beyond the seen data, even when the abstractions required for such patterns are simple. In this paper, we first review …

2019-11-10abs ↗pdf ↗

Sparse Transformers can approximate dense Transformers with only O(n) connections.

problem Can sparse Transformers approximate arbitrary sequence-to-sequence functions?
method Proposed sufficient conditions for universal approximation and proved that sparse Transformers with O(n) connections can approximate dense models.
result Sparse Transformers with O(n) connections can approximate the same function class as dense models with n^2 connections.

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.

The Transformer is a fully attention-based alternative to recurrent networks that has achieved state-of-the-art results across a range of NLP tasks. In this paper, we analyze the structure of attention in a Transformer language model, the GPT-2 small pretrained model. We visualize attention for individual instances and…

2019-06-07abs ↗pdf ↗

The paper identifies patterns in language model weights used for memorizing paragraphs.

problem Locating the specific mechanisms and weights used by language models to memorize paragraphs.
method Examined gradients and attention patterns in language models to identify memorized paragraphs.
result Gradients of memorized paragraphs have a distinguishable spatial pattern, and localized attention heads are involved in paragraph memorization.

DeepRC uses Hopfield networks and attention to classify immune repertoires.

problem Classifying the vast number of immunosequences of an individual.
method Integrates transformer-like attention into deep learning architectures.
result DeepRC outperforms other methods in predictive performance.

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…

2020-02-07abs ↗pdf ↗

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…

2019-11-08abs ↗pdf ↗

Asynchronous events on the continuous time domain, e.g., social media actions and stock transactions, occur frequently in the world. The ability to recognize occurrence patterns of event sequences is crucial to predict which typeof events will happen next and when. A de facto standard mathematical framework to do this …

2019-07-17abs ↗pdf ↗

DeepSupp detects financial support levels using attention mechanisms.

problem Traditional SR identification methods fail to adapt to modern markets.
method Multi-head attention mechanisms, dynamic correlation matrices, DBSCAN clustering.
result DeepSupp outperforms six baseline methods across six financial metrics.

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.

Transformers simplify modeling of small longitudinal cohort data by reducing parameters and incorporating attention mechanisms.

problem Challenges in modeling longitudinal cohort data due to complex temporal dependencies and large dataset requirements.
method Simplified transformer architecture with attention mechanism, autoregressive model, and kernel-based temporal decay.
result The approach recovers contextual dependencies even with small datasets, identifying temporal patterns in stress and mental health.

DyHATR learns dynamic heterogeneous networks for better link prediction.

problem Learning effective representations of dynamic heterogeneous networks for link prediction.
method Hierarchical attention for heterogeneous information and temporal RNN for evolutionary patterns.
result DyHATR significantly outperforms state-of-the-art baselines on link prediction tasks.

Calendar graph neural networks model user behavior with location and time data.

problem Modeling user behavior with location and time information for demographic prediction.
method Graph neural networks with a tripartite network of items, sessions, and locations, and a hierarchical calendar network.
result User embeddings preserve spatial and temporal patterns of various periodicity.

GUIDE detects anomalies in attributed networks by reconstructing node attributes and higher-order structures.

problem Lack of effective mechanisms for detecting anomalies in complex network interactions.
method GUIDE uses attribute and structure autoencoders, graph attention, and reconstruction errors to identify anomalies.
result GUIDE significantly outperforms state-of-the-art methods on multiple real-world datasets.

Graph Attention Networks (GATs) are the state-of-the-art neural architecture for representation learning with graphs. GATs learn attention functions that assign weights to nodes so that different nodes have different influences in the feature aggregation steps. In practice, however, induced attention functions are pron…

2019-10-25abs ↗pdf ↗

Graph convolutional networks (GCNs) have shown the powerful ability in text structure representation and effectively facilitate the task of text classification. However, challenges still exist in adapting GCN on learning discriminative features from texts due to the main issue of graph variants incurred by the textual …

2019-11-28abs ↗pdf ↗

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.

MPTE uses Transformer attention to estimate mixed-frequency factor models.

problem Estimating factor models in panel datasets with mixed frequencies and nonlinear signals.
method Mixed-Panels-Transformer Encoder (MPTE) with attention mechanisms.
result MPTE achieves competitive performance in nonlinear forecasting environments.

Time series prediction with deep learning methods, especially long short-term memory neural networks (LSTMs), have scored significant achievements in recent years. Despite the fact that the LSTMs can help to capture long-term dependencies, its ability to pay different degree of attention on sub-window feature within mu…

2018-11-09abs ↗pdf ↗

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…

2019-08-30abs ↗pdf ↗

TFPS improves time series forecasting by learning pattern-specific experts.

problem Challenges in forecasting time series data with varying patterns across segments.
method Dual-domain encoder, subspace clustering, pattern-specific experts.
result Significantly improved forecasting accuracy, especially in long-term forecasting.

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.

RestoreAI predicts landmine risk from patterns, improving clearance efficiency.

problem Predicting landmine risk from spatial patterns to enhance clearance efficiency.
method RestoreAI uses landmine patterns for risk prediction, implementing three deminers: linear, curved, and Bayesian.
result RestoreAI significantly boosts clearance efficiency, achieving a 14.37 percentage point increase in cleared landmines per timestep.