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 7751–7800 of 10580 papers

TitleStatusHype
Towards Impartial Multi-task LearningCode1
Self-supervised representation learning via adaptive hard-positive mining—0
A Text GAN for Language Generation with Non-Autoregressive Generator—0
RRL: A Scalable Classifier for Interpretable Rule-Based Representation Learning—0
The Unreasonable Effectiveness of Patches in Deep Convolutional Kernels Methods.—0
Self-Supervised Video Representation Learning with Constrained Spatiotemporal Jigsaw—0
LINGUINE: LearnIng to pruNe on subGraph convolUtIon NEtworks—0
Clearing the Path for Truly Semantic Representation Learning—0
Learning Visual Representation from Human Interactions—0
Learning Representations by Contrasting Clusters While Bootstrapping Instances—0
Learning Private Representations with Focal Entropy—0
Learning Flexible Visual Representations via Interactive Gameplay—0
Knowledge distillation via softmax regression representation learning—0
Invariant Representations for Reinforcement Learning without Reconstruction—0
Toward Understanding Supervised Representation Learning with RKHS and GAN—0
Improving the Unsupervised Disentangled Representation Learning with VAE Ensemble—0
Towards Robust and Efficient Contrastive Textual Representation Learning—0
Sufficient and Disentangled Representation Learning—0
How Benign is Benign Overfitting ?—0
Self-supervised Disentangled Representation Learning—0
Guiding Representation Learning in Deep Generative Models with Policy Gradients—0
Towards Powerful Graph Neural Networks: Diversity Matters—0
Ballroom Dance Movement Recognition Using a Smart Watch and Representation Learning—0
Recursive Neighborhood Pooling for Graph Representation Learning—0
Recall Loss for Imbalanced Image Classification and Semantic SegmentationCode1
Probabilistic Multimodal Representation Learning—0
Transferable Unsupervised Robust Representation Learning—0
Online Limited Memory Neural-Linear Bandits—0
Continual Lifelong Causal Effect Inference with Real World Evidence—0
Online Adversarial Purification based on Self-supervised Learning—0
Non-maximum Suppression Also Closes the Variational Approximation Gap of Multi-object Variational Autoencoders—0
Neural Bayes: A Generic Parameterization Method for Unsupervised Learning—0
Consistent Instance Classification for Unsupervised Representation Learning—0
Sequence Metric Learning as Synchronization of Recurrent Neural Networks—0
Momentum Contrastive Autoencoder—0
Dynamic Graph Representation Learning with Fourier Temporal State EmbeddingCode0
Robust Multi-view Representation Learning—0
A Flexible Framework for Discovering Novel Categories with Contrastive Learning—0
Learning Task-Relevant Features via Contrastive Input Morphing—0
UserBERT: Self-supervised User Representation Learning—0
Learning a Transferable Scheduling Policy for Various Vehicle Routing Problems based on Graph-centric Representation Learning—0
R-MONet: Region-Based Unsupervised Scene Decomposition and Representation via Consistency of Object Representations—0
Improving Generalizability of Protein Sequence Models via Data Augmentations—0
Deep Q-Learning with Low Switching Cost—0
VECoDeR - Variational Embeddings for Community Detection and Node Representation—0
Decomposing Mutual Information for Representation Learning—0
Beyond COVID-19 Diagnosis: Prognosis with Hierarchical Graph Representation Learning—0
GL-Disen: Global-Local disentanglement for unsupervised learning of graph-level representations—0
On the Importance of Looking at the Manifold—0
On the Importance of Distraction-Robust Representations for Robot Learning—0
Show:102550
← PrevPage 156 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
6CiteBERTAvg.58.8—Unverified
7BioBERTAvg.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