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 7801–7850 of 10580 papers

TitleStatusHype
DECRL: A Deep Evolutionary Clustering Jointed Temporal Knowledge Graph Representation Learning Approach—0
Representation Learning for Recommender Systems with Application to the Scientific Literature—0
Heterogeneous Graph Neural Network with Multi-view Representation Learning—0
Heterogeneous Graph Contrastive Learning with Spectral Augmentation—0
Beyond Spatial Pooling: Fine-Grained Representation Learning in Multiple Domains—0
Heterogeneous Face Attribute Estimation: A Deep Multi-Task Learning Approach—0
Research on Joint Representation Learning Methods for Entity Neighborhood Information and Description Information—0
Combining Self-Supervised and Supervised Learning with Noisy Labels—0
Research on Domain Information Mining and Theme Evolution of Scientific Papers—0
Research Team Identification Based on Representation Learning of Academic Heterogeneous Information Network—0
Residual Connections Encourage Iterative Inference—0
Representation Learning for Spatial Graphs—0
ReSW-VL: Representation Learning for Surgical Workflow Analysis Using Vision-Language Model—0
Heterogeneous Contrastive Learning: Encoding Spatial Information for Compact Visual Representations—0
An Efficient Cross-lingual Model for Sentence Classification Using Convolutional Neural Network—0
Hetero^2Net: Heterophily-aware Representation Learning on Heterogenerous Graphs—0
GeSubNet: Gene Interaction Inference for Disease Subtype Network Generation—0
3D Denoisers are Good 2D Teachers: Molecular Pretraining via Denoising and Cross-Modal Distillation—0
Reprogramming Pretrained Language Models for Protein Sequence Representation Learning—0
Representation Learning for Unseen Words by Bridging Subwords to Semantic Networks—0
Decoupling feature propagation from the design of graph auto-encoders—0
A Unified Mixture-View Framework for Unsupervised Representation Learning—0
Reprogramming Language Models for Molecular Representation Learning—0
Representation Learning for Weakly Supervised Relation Extraction—0
Representation Learning for Wearable-Based Applications in the Case of Missing Data—0
Representation Learning for Words and Entities—0
Repurposing Foundation Model for Generalizable Medical Time Series Classification—0
Beyond Similarity: Relation Embedding with Dual Attentions for Item-based Recommendation—0
GIQ: Benchmarking 3D Geometric Reasoning of Vision Foundation Models with Simulated and Real Polyhedra—0
Representation Learning in Anomaly Detection: Successes, Limits and a Grand Challenge—0
Diffusion-Based Representation Learning—0
Representation Learning in Continuous-Time Score-Based Generative Models—0
Representation Learning in Deep RL via Discrete Information Bottleneck—0
Representation Learning in Geology and GilBERT—0
Representation Learning in Low-rank Slate-based Recommender Systems—0
GLAD: Global-Local-Alignment Descriptor for Pedestrian Retrieval—0
Hebbian Graph Embeddings—0
Representation Learning in Partially Observable Environments using Sensorimotor Prediction—0
Representing Spatial Trajectories as Distributions—0
Hebbian Continual Representation Learning—0
Representation Learning of Complex Assemblies, An Effort to Improve Corporate Scope 3 Emissions Calculation—0
GLCC: A General Framework for Graph-Level Clustering—0
Hearing Loss Detection from Facial Expressions in One-on-one Conversations—0
Representation learning of drug and disease terms for drug repositioning—0
Representation learning of dynamic networks—0
Representation Learning of EHR Data via Graph-Based Medical Entity Embedding—0
Decoupling anomaly discrimination and representation learning: self-supervised learning for anomaly detection on attributed graph—0
Representation Learning of Geometric Trees—0
Reproducible, incremental representation learning with Rosetta VAE—0
Healthcare cost prediction for heterogeneous patient profiles using deep learning models with administrative claims data—0
Show:102550
← PrevPage 157 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