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 9201–9250 of 10580 papers

TitleStatusHype
A Knowledge Graph-Enhanced Tensor Factorisation Model for Discovering Drug Targets—0
Difficulty-Based Sampling for Debiased Contrastive Representation Learning—0
Predicting S&P500 Index direction with Transfer Learning and a Causal Graph as main Input—0
Predicting the Co-Evolution of Event and Knowledge Graphs—0
Adapting Self-Supervised Representations to Multi-Domain Setups—0
Predicting the outcome of team movements -- Player time series analysis using fuzzy and deep methods for representation learning—0
Diffuse and Disperse: Image Generation with Representation Regularization—0
DiffuseGAE: Controllable and High-fidelity Image Manipulation from Disentangled Representation—0
Diffusion Adversarial Representation Learning for Self-supervised Vessel Segmentation—0
Diffusion-augmented Graph Contrastive Learning for Collaborative Filter—0
Diffusion Based Causal Representation Learning—0
Predicting What You Already Know Helps: Provable Self-Supervised Learning—0
Diffusion Bridge AutoEncoders for Unsupervised Representation Learning—0
DiffusionCom: Structure-Aware Multimodal Diffusion Model for Multimodal Knowledge Graph Completion—0
Diffusion Model Agnostic Social Influence Maximization in Hyperbolic Space—0
Diffusion Model based Semi-supervised Learning on Brain Hemorrhage Images for Efficient Midline Shift Quantification—0
Diffusion Model with Cross Attention as an Inductive Bias for Disentanglement—0
Diffusion Policies for Out-of-Distribution Generalization in Offline Reinforcement Learning—0
Prediction of Frame-to-Frame Relations in the FrameNet Hierarchy with Frame Embeddings—0
Diffusion Spectral Representation for Reinforcement Learning—0
Predictive auxiliary objectives in deep RL mimic learning in the brain—0
Predictive Learning: Using Future Representation Learning Variantial Autoencoder for Human Action Prediction—0
Dilated Strip Attention Network for Image Restoration—0
DimeRec: A Unified Framework for Enhanced Sequential Recommendation via Generative Diffusion Models—0
DINE: A Framework for Deep Incomplete Network Embedding—0
Adapting Behaviour via Intrinsic Reward: A Survey and Empirical Study—0
Predictive Modeling of Homeless Service Assignment: A Representation Learning Approach—0
Predictive Representation Learning for Language Modeling—0
Preference or Intent? Double Disentangled Collaborative Filtering—0
Direct Coloring for Self-Supervised Enhanced Feature Decoupling—0
Directed Graph Embeddings in Pseudo-Riemannian Manifolds—0
Directed Semi-Simplicial Learning with Applications to Brain Activity Decoding—0
Directional diffusion models for graph representation learning—0
Directionally Convolutional Networks for 3D Shape Segmentation—0
Directional Self-supervised Learning for Heavy Image Augmentations—0
Directional Sign Loss: A Topology-Preserving Loss Function that Approximates the Sign of Finite Differences—0
Direction-Aware Hybrid Representation Learning for 3D Hand Pose and Shape Estimation—0
Self-Supervised Face Presentation Attack Detection with Dynamic Grayscale Snippets—0
DiRW: Path-Aware Digraph Learning for Heterophily—0
Disassembling Object Representations without Labels—0
DISC: Deep Image Saliency Computing via Progressive Representation Learning—0
Prerequisite Relation Learning for Concepts in MOOCs—0
DisCoRL: Continual Reinforcement Learning via Policy Distillation—0
Discourse-Aware Graph Networks for Textual Logical Reasoning—0
Discourse-Based Objectives for Fast Unsupervised Sentence Representation Learning—0
Self-Supervised Facial Representation Learning with Facial Region Awareness—0
Preserve Pre-trained Knowledge: Transfer Learning With Self-Distillation For Action Recognition—0
DisCover: Disentangled Music Representation Learning for Cover Song Identification—0
Discovering interpretable Lagrangian of dynamical systems from data—0
Discovering interpretable models of scientific image data with deep learning—0
Show:102550
← PrevPage 185 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