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 5351–5400 of 10580 papers

TitleStatusHype
Learning Disentangled Representation with Mutual Information Maximization for Real-Time UAV Tracking—0
Learning Disentangled Speech Representations—0
Delayed Bottlenecking: Alleviating Forgetting in Pre-trained Graph Neural Networks—0
LiftPool: Lifting-based Graph Pooling for Hierarchical Graph Representation Learning—0
Residual or Gate? Towards Deeper Graph Neural Networks for Inductive Graph Representation Learning—0
Learning Distributed Representations for Multilingual Text Sequences—0
Learning Distributional Token Representations from Visual Features—0
Learning Domain Invariant Representations for Generalizable Person Re-Identification—0
Inductive-Biases for Contrastive Learning of Disentangled Representations—0
Causal Representation Learning for Context-Aware Face Transfer—0
Inductive and Unsupervised Representation Learning on Graph Structured Objects—0
Déjà Vu Memorization in Vision-Language Models—0
Degeneration in VAE: in the Light of Fisher Information Loss—0
Learning Dynamic Embeddings from Temporal Interactions—0
Learning Dynamic Graph Embeddings with Neural Controlled Differential Equations—0
Learning Dynamic Hierarchical Models for Anytime Scene Labeling—0
Individual Treatment Effect Estimation Through Controlled Neural Network Training in Two Stages—0
DEFTri: A Few-Shot Label Fused Contextual Representation Learning For Product Defect Triage in e-Commerce—0
A Simple Self-Supervised ECG Representation Learning Method via Manipulated Temporal-Spatial Reverse Detection—0
Learning ECG Signal Features Without Backpropagation Using Linear Laws—0
In-Distribution and Out-of-Distribution Self-supervised ECG Representation Learning for Arrhythmia Detection—0
Indicative Image Retrieval: Turning Blackbox Learning into Grey—0
Breaking the Memory Barrier of Contrastive Loss via Tile-Based Strategy—0
A 3D-Shape Similarity-based Contrastive Approach to Molecular Representation Learning—0
Lift, Splat, Map: Lifting Foundation Masks for Label-Free Semantic Scene Completion—0
Indication Finding: a novel use case for representation learning—0
Deformable Graph Transformer—0
Independent Mechanism Analysis and the Manifold Hypothesis—0
Breaking the Encoder Barrier for Seamless Video-Language Understanding—0
Distributed Representations for Compositional Semantics—0
Controllable Paraphrase Generation with a Syntactic Exemplar—0
Independence Promoted Graph Disentangled Networks—0
Learning Feature Relevance Through Step Size Adaptation in Temporal-Difference Learning—0
Learning finite-dimensional coding schemes with nonlinear reconstruction maps—0
Learning First-Order Symbolic Representations for Planning from the Structure of the State Space—0
Learning Flexible Visual Representations via Interactive Gameplay—0
Learning for Counterfactual Fairness from Observational Data—0
Learning From Graph-Structured Data: Addressing Design Issues and Exploring Practical Applications in Graph Representation Learning—0
Independence Constrained Disentangled Representation Learning from Epistemological Perspective—0
Validity Learning on Failures: Mitigating the Distribution Shift in Autonomous Vehicle Planning—0
Defining Words with Words: Beyond the Distributional Hypothesis—0
Incremental user embedding modeling for personalized text classification—0
Defining and Measuring Disentanglement for non-Independent Factors of Variation—0
Breaking Shallow Limits: Task-Driven Pixel Fusion for Gap-free RGBT Tracking—0
Anomaly Detection with Joint Representation Learning of Content and Connection—0
Learning from Streaming Video with Orthogonal Gradients—0
Lifestyle-Informed Personalized Blood Biomarker Prediction via Novel Representation Learning—0
Learning from Untrimmed Videos: Self-Supervised Video Representation Learning with Hierarchical Consistency—0
Increasing the Efficiency of Policy Learning for Autonomous Vehicles by Multi-Task Representation Learning—0
Increasing the Accessibility of Causal Domain Knowledge via Causal Information Extraction Methods: A Case Study in the Semiconductor Manufacturing Industry—0
Show:102550
← PrevPage 108 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