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 6851–6900 of 10580 papers

TitleStatusHype
HYDEN: Hyperbolic Density Representations for Medical Images and Reports—0
OCTAL: Graph Representation Learning for LTL Model Checking—0
Octave Graph Convolutional Network—0
OCTScenes: A Versatile Real-World Dataset of Tabletop Scenes for Object-Centric Learning—0
Deep learning-based person re-identification methods: A survey and outlook of recent works—0
Black-box Gradient Attack on Graph Neural Networks: Deeper Insights in Graph-based Attack and Defense—0
Offline Action-Free Learning of Ex-BMDPs by Comparing Diverse Datasets—0
Offline Multitask Representation Learning for Reinforcement Learning—0
Deep Learning Based Page Creation for Improving E-Commerce Organic Search Traffic—0
Offline Q-Learning on Diverse Multi-Task Data Both Scales And Generalizes—0
Epistemic Graph: A Plug-And-Play Module For Hybrid Representation Learning—0
A New Bidirectional Unsupervised Domain Adaptation Segmentation Framework—0
Deep Learning based, end-to-end metaphor detection in Greek language with Recurrent and Convolutional Neural Networks—0
Hybrid of representation learning and reinforcement learning for dynamic and complex robotic motion planning—0
Bi-VLDoc: Bidirectional Vision-Language Modeling for Visually-Rich Document Understanding—0
OMG-ATTACK: Self-Supervised On-Manifold Generation of Transferable Evasion Attacks—0
Omni-directional Feature Learning for Person Re-identification—0
Omni-Granular Ego-Semantic Propagation for Self-Supervised Graph Representation Learning—0
Pair DETR: Contrastive Learning Speeds Up DETR Training—0
Hybrid Mutual Information Lower-bound Estimators for Representation Learning—0
Deep-Learning-Assisted Analysis of Cataract Surgery Videos—0
Bitext Mining Using Distilled Sentence Representations for Low-Resource Languages—0
Hybrid Low-order and Higher-order Graph Convolutional Networks—0
Factorized Visual Tokenization and Generation—0
Contextures: The Mechanism of Representation Learning—0
Contextures: Representations from Contexts—0
Deep Learning Approach on Information Diffusion in Heterogeneous Networks—0
On Deep Representation Learning from Noisy Web Images—0
Adversarial Active Learning based Heterogeneous Graph Neural Network for Fake News Detection—0
Hybrid Graph: A Unified Graph Representation with Datasets and Benchmarks for Complex Graphs—0
Interpretable Deep Representation Learning from Temporal Multi-view Data—0
On Discriminative Probabilistic Modeling for Self-Supervised Representation Learning—0
One4all User Representation for Recommender Systems in E-commerce—0
One at a Time: Progressive Multi-step Volumetric Probability Learning for Reliable 3D Scene Perception—0
Hybrid Gradient Boosting Trees and Neural Networks for Forecasting Operating Room Data—0
Continual Causal Inference with Incremental Observational Data—0
Bitcoin Transaction Forecasting with Deep Network Representation Learning—0
10 Years of Fair Representations: Challenges and Opportunities—0
Fair Inference for Discrete Latent Variable Models—0
Pair Distance Distribution: A Model of Semantic Representation—0
Hyperdimensional Representation Learning for Node Classification and Link Prediction—0
Hybrid Distillation: Connecting Masked Autoencoders with Contrastive Learners—0
One Size Does Not Fit All: Finding the Optimal Subword Sizes for FastText Models across Languages—0
One Stage Autoencoders for Multi-Domain Learning—0
Hybrid deep learning methods for phenotype prediction from clinical notes—0
Deep Inverse Feature Learning: A Representation Learning of Error—0
PACER: Preference-conditioned All-terrain Costmap Generation—0
Hybrid Consistency Training with Prototype Adaptation for Few-Shot Learning—0
Hybrid Active Inference—0
Deep Incomplete Multi-view Learning via Cyclic Permutation of VAEs—0
Show:102550
← PrevPage 138 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