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.

169,042 papers · 148 categories

Trend · papers per month

2.5%5.1%7.6%10.1% · Apr 201919922001200920172026
48 results for unsupervised attention

Proposes RN for unsupervised attention in neural networks.

problem Limited, imbalanced, and non-stationary input distributions in various tasks.
method Inspired by neuronal adaptation, RN uses MDL principle and universal code length for incremental layer-wise computation.
result Outperforms existing normalization methods across diverse tasks.

A new unsupervised method removes CT metal artifacts using beta-CycleGAN and attention.

problem Metal artifact reduction in computed tomography (CT) images.
method Unsupervised learning using a beta-CycleGAN architecture with attention mechanism.
result Improved metal artifact removal that preserves image details.

R-SQAIR adds relational bias to sequential object attention models for better object interactions.

problem Traditional sequential multi-object attention models struggle with relational inferences.
method Proposes R-SQAIR, a relational extension of SQAIR with a parallel pairwise interaction module.
result Demonstrates gains in object relations and combinatorial generalization over sequential mechanisms.

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.

The paper shows how continuous attention can lead to better object representations.

problem Learning good representations from data without labeled examples.
method Integrating unsupervised learning and reinforcement learning with intrinsic motivation.
result The proposed algorithm improves object recognition in few-shot settings.

Deep Divergence Graph Kernels learn graph representations without supervision.

problem Learning graph representations without feature engineering or labeled graphs.
method Unsupervised method using cross-graph attention networks and divergence scores.
result Learned representations achieve competitive results on graph classification tasks.

SPACE models complex scenes by decomposing objects and backgrounds.

problem Scalability and unsupervised object-oriented scene representation learning.
method Generative latent variable model combining spatial-attention and scene-mixture approaches.
result SPACE achieves factorized object representations and decomposes complex scenes.

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.

Graph attention auto-encoder reconstructs graph structure and attributes.

problem Lack of methods to reconstruct graph structure and node attributes in graph auto-encoders.
method Stacked encoder/decoder layers with self-attention mechanisms, regularized node representations to reconstruct graph structure.
result Competitive performance on node classification benchmarks, including inductive learning.

New method improves text classification without labeled target data.

problem Improving text classification under domain shift without labeled target data.
method Diversity-based generalization using multi-head attention with diversity constraints.
result Method matches state-of-the-art performance without labeled target data.

Transformers can cluster data from Gaussian mixtures without supervision.

problem Clustering data from Gaussian mixtures without labeled data.
method Theoretical analysis of attention-based layers, focusing on a simplified two-head attention layer and an identity matrix attention layer.
result Attention-based layers can align with true mixture centroids and adapt to input-specific distributions.

Two computational models analyze political topics in social media tweets.

problem Measuring political attention in social media is labor-intensive and restrictive.
method Two computational models: supervised classifier and unsupervised topic model.
result Models provide different benefits: supervised classifier reduces labor, unsupervised model uncovers political and non-political uses.

UGRAPHEMB embeds graphs into vectors preserving their proximity, achieving competitive results.

problem Graph-level representation learning in an unsupervised and inductive manner.
method UGRAPHEMB uses graph-graph proximity to embed graphs into a vector space. MSNA generates multi-scale node attention for graph-level embedding.
result UGRAPHEMB achieves competitive accuracy in graph classification, similarity ranking, and visualization tasks.

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.

Novel fusion of autoencoders predicts sleepiness from speech.

problem Predicting sleepiness from speech recordings.
method Attention-based and recurrent sequence to sequence autoencoders for unsupervised representation learning.
result Fusion of autoencoders' representations achieves higher correlation with sleepiness scales.

We introduce the Attentive Unsupervised Text (W)riter (AUTR), which is a word level generative model for natural language. It uses a recurrent neural network with a dynamic attention and canvas memory mechanism to iteratively construct sentences. By viewing the state of the memory at intermediate stages and where the m…

2018-06-13abs ↗pdf ↗

Graph neural networks benefit from attention under specific conditions.

problem Understanding and improving the effectiveness of attention in graph neural networks.
method Designing controlled graph reasoning tasks, analyzing performance under various conditions, proposing weakly-supervised training.
result Attention can provide significant gains in performance under certain conditions, but its effect is often negligible or harmful.

Unsupervised learning filters tweets for emergency services during crises.

problem Challenges in filtering relevant information from social web data during disasters.
method Multi-task domain adversarial attention network for unsupervised domain adaptation.
result The multi-task model outperforms single task models in filtering relevant tweets.

Proposes ACLAE-DT for unsupervised anomaly detection in multivariate time series.

problem Challenges in building anomaly detection frameworks for multivariate time series data.
method Attention-based ConvLSTM Autoencoder with Dynamic Thresholding.
result Demonstrates superior performance over state-of-the-art methods.

The ability to decompose scenes in terms of abstract building blocks is crucial for general intelligence. Where those basic building blocks share meaningful properties, interactions and other regularities across scenes, such decompositions can simplify reasoning and facilitate imagination of novel scenarios. In particu…

2019-01-22abs ↗pdf ↗

Diffusion models enhance speech without supervision.

problem Challenges in generalizing supervised speech enhancement methods to unseen conditions.
method Unsupervised speech enhancement using diffusion-based generative models.
result Demonstrates promising results compared to supervised and unsupervised baselines.

A new method for feature selection in high-dimensional data.

problem Dealing with noise and high-dimensional data in unsupervised feature selection.
method Sparse PCA via l2,pl_{2,p}-norm regularization, combined with an efficient optimization algorithm.
result The proposed method effectively selects features from real-world data sets.

A new deep learning framework selects representative samples for unsupervised learning.

problem Selecting representative samples for unsupervised learning in non-linear data.
method DUAL framework using an encoder-decoder architecture to learn nonlinear embeddings and a selection block to choose representative samples.
result DUAL outperforms state-of-the-art methods in selecting representative samples for unsupervised learning.

LORL learns object-centric representations from vision and language.

problem Learning disentangled, object-centric scene representations from vision and language.
method LORL integrates unsupervised object discovery and segmentation with language input to learn object-centric concepts.
result LORL improves unsupervised object discovery methods and aids downstream tasks.

GraphDINO learns neuronal morphologies from unlabeled data.

problem Unsupervised learning of neuronal morphologies from unlabeled data.
method Transformer-based approach with novel attention mechanism and data augmentation.
result GraphDINO yields morphological clusterings on par with expert classification.

This paper introduces GEMINI, a new mutual information metric for unsupervised neural network training.

problem The mutual information (MI) as a clustering objective does not lead to satisfactory clusters.
method The authors generalised MI by changing its core distance, introducing GEMINIs that do not require regularizations and can automatically select the number of clusters.
result GEMINIs can automatically select the number of clusters without requiring a priori knowledge of the number of clusters.

MPVAA learns holistic patient representations from mixed healthcare data.

problem Learning personalized patient representations from heterogeneous healthcare data.
method Mixed Pooling Multi-View Attention Autoencoder (MPVAA) that integrates non-linear relationships among multiple data modalities.
result MPVAA generates more effective patient representations than state-of-the-art methods.

Discrete-AIR model identifies objects in images with interpretable latent codes.

problem Identifying objects in images without labeled data.
method Recurrent Auto-Encoder with structured latent distributions for discrete, continuous, and spatial attention.
result Discrete-AIR model uses minimal latent variables for efficient inference.

This work addresses encoding biases in neural networks by tailoring models with unsupervised losses.

problem Improving neural network representations and reducing the generalization gap.
method Inspired by transductive learning, the authors propose tailoring and meta-tailoring to optimize unsupervised losses during prediction time.
result Models trained with tailoring and meta-tailoring perform better on the task objective after adapting to unsupervised losses.