SOTAVerified

Representation Learning

Representation Learning is a process in machine learning where algorithms extract meaningful patterns from raw data to create representations that are easier to understand and process. These representations can be designed for interpretability, reveal hidden features, or be used for transfer learning. They are valuable across many fundamental machine learning tasks like image classification and retrieval.

Deep neural networks can be considered representation learning models that typically encode information which is projected into a different subspace. These representations are then usually passed on to a linear classifier to, for instance, train a classifier.

Representation learning can be divided into:

  • Supervised representation learning: learning representations on task A using annotated data and used to solve task B
  • Unsupervised representation learning: learning representations on a task in an unsupervised way (label-free data). These are then used to address downstream tasks and reducing the need for annotated data when learning news tasks. Powerful models like GPT and BERT leverage unsupervised representation learning to tackle language tasks.

More recently, self-supervised learning (SSL) is one of the main drivers behind unsupervised representation learning in fields like computer vision and NLP.

Here are some additional readings to go deeper on the task:

( Image credit: Visualizing and Understanding Convolutional Networks )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 4101–4150 of 10580 papers

TitleStatusHype
Learning Language Representations with Logical Inductive Bias—0
Generalization in Visual Reinforcement Learning with the Reward Sequence DistributionCode0
Video-Text Retrieval by Supervised Sparse Multi-Grained LearningCode0
PiRL: Participant-Invariant Representation Learning for Healthcare Using Maximum Mean Discrepancy and Triplet Loss—0
Creating generalizable downstream graph models with random projections—0
Generative Causal Representation Learning for Out-of-Distribution Motion ForecastingCode0
Self-Supervised Representation Learning from Temporal Ordering of Automated Driving Sequences—0
Learnable Topological Features for Phylogenetic Inference via Graph Neural NetworksCode1
Self-supervised Action Representation Learning from Partial Spatio-Temporal Skeleton SequencesCode1
Efficiently Forgetting What You Have Learned in Graph Representation Learning via Projection—0
Building Shortcuts between Distant Nodes with Biaffine Mapping for Graph Convolutional Networks—0
3D Human Pose Lifting with Grid ConvolutionCode1
Graph-Enhanced Emotion Neural DecodingCode0
Visible-Infrared Person Re-Identification via Patch-Mixed Cross-Modality Learning—0
GraphPrompt: Unifying Pre-Training and Downstream Tasks for Graph Neural NetworksCode1
DKT-STDRL: Spatial and Temporal Representation Learning Enhanced Deep Knowledge Tracing for Learning Performance Prediction—0
Self-Organising Neural Discrete Representation Learning à la Kohonen—0
A Deep Probabilistic Spatiotemporal Framework for Dynamic Graph Representation Learning with Application to Brain Disorder IdentificationCode0
Robust Representation Learning with Self-Distillation for Domain Generalization—0
Multi-Source Contrastive Learning from Musical AudioCode1
Learning from Noisy Labels with Decoupled Meta Label PurifierCode1
Communication-Efficient Federated Bilevel Optimization with Local and Global Lower Level Problems—0
Label-efficient Time Series Representation Learning: A Review—0
CoMAE: Single Model Hybrid Pre-training on Small-Scale RGB-D DatasetsCode1
Robust Representation Learning by Clustering with Bisimulation Metrics for Visual Reinforcement Learning with DistractionsCode0
Generalized Few-Shot Continual Learning with Contrastive Mixture of AdaptersCode1
SCLIFD:Supervised Contrastive Knowledge Distillation for Incremental Fault Diagnosis under Limited Fault Data—0
Exploiting Graph Structured Cross-Domain Representation for Multi-Domain RecommendationCode0
Efficient Fraud Detection Using Deep Boosting Decision TreesCode0
Is Distance Matrix Enough for Geometric Deep Learning?Code1
Cross-domain Random Pre-training with Prototypes for Reinforcement LearningCode0
A Survey on Spectral Graph Neural Networks—0
Vertical Federated Knowledge Transfer via Representation Distillation for Healthcare Collaboration Networks—0
Anatomical Invariance Modeling and Semantic Alignment for Self-supervised Learning in 3D Medical Image AnalysisCode1
Analyzing Multimodal Objectives Through the Lens of Generative Diffusion Guidance—0
EVC: Towards Real-Time Neural Image Compression with Mask Decay—0
Invariant Collaborative Filtering to Popularity Distribution ShiftCode1
Combining Reconstruction and Contrastive Methods for Multimodal Representations in RLCode0
Multi-task Representation Learning for Pure Exploration in Linear Bandits—0
Privacy-Preserving Representation Learning for Text-Attributed Networks with Simplicial Complexes—0
Fully Bayesian Autoencoders with Latent Sparse Gaussian Processes—0
Hierarchical Generative Adversarial Imitation Learning with Mid-level Input Generation for Autonomous Driving on Urban EnvironmentsCode1
Self-Supervised Node Representation Learning via Node-to-Neighbourhood AlignmentCode1
Trading Information between Latents in Hierarchical Variational AutoencodersCode0
Discovering interpretable Lagrangian of dynamical systems from data—0
Weakly-supervised Representation Learning for Video Alignment and Analysis—0
Geometry-Complete Diffusion for 3D Molecule Generation and OptimizationCode2
CRL+: A Novel Semi-Supervised Deep Active Contrastive Representation Learning-Based Text Classification Model for Insurance Data—0
Multiview Representation Learning from Crowdsourced Triplet ComparisonsCode0
CCRep: Learning Code Change Representations via Pre-Trained Code Model and Query BackCode1
Show:102550
← PrevPage 83 of 212Next →
All datasetsSciDocsAnimals-10CIFAR10Circle DataSports10

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1SciNCLAvg.81.8—Unverified
2SPECTERAvg.80—Unverified
3CiteomaticAvg.76—Unverified
4Sci-DeCLUTRAvg.66.6—Unverified
5SciBERTAvg.59.6—Unverified
6BioBERTAvg.58.8—Unverified
7CiteBERTAvg.58.8—Unverified
#ModelMetricClaimedVerifiedStatus
1top_model_weights_with_3d_21:1 Accuracy0.75—Unverified
#ModelMetricClaimedVerifiedStatus
1Resnet 18Accuracy (%)97.05—Unverified
#ModelMetricClaimedVerifiedStatus
1Morphological NetworkAccuracy97.3—Unverified
#ModelMetricClaimedVerifiedStatus
1Max Margin ContrastiveSilhouette Score0.56—Unverified