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 6351–6400 of 10580 papers

TitleStatusHype
Multi-Faceted Representation Learning with Hybrid Architecture for Time Series Classification—0
Less can be more in contrastive learning—0
Dual Encoder-Decoder based Generative Adversarial Networks for Disentangled Facial Representation Learning—0
LeOCLR: Leveraging Original Images for Contrastive Learning of Visual Representations—0
Multi-fidelity Stability for Graph Representation Learning—0
ClassContrast: Bridging the Spatial and Contextual Gaps for Node Representations—0
A Simple Framework for Uncertainty in Contrastive Learning—0
Length- and Noise-aware Training Techniques for Short-utterance Speaker Recognition—0
Multi-GAT: A Graphical Attention-based Hierarchical Multimodal Representation Learning Approach for Human Activity Recognition—0
LegoNet: A Fast and Exact Unlearning Architecture—0
Learning Word Representations from Relational Graphs—0
Class-aware and Augmentation-free Contrastive Learning from Label Proportion—0
Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation—0
A Simple Framework for Open-Vocabulary Zero-Shot Segmentation—0
TraceGrad: a Framework Learning Expressive SO(3)-equivariant Non-linear Representations for Electronic-Structure Hamiltonian Prediction—0
Multi-Granularity Framework for Unsupervised Representation Learning of Time Series—0
Active metric learning and classification using similarity queries—0
Learning Word Representations by Jointly Modeling Syntagmatic and Paradigmatic Relations—0
When Noisy Labels Meet Long Tail Dilemmas: A Representation Calibration Method—0
Dual Contrastive Learning for Spatio-temporal Representation—0
Multi-Hot Compact Network Embedding—0
Learning with Memory Embeddings—0
Learning with Capsules: A Survey—0
Dual Contradistinctive Generative Autoencoder—0
Learning When the Concept Shifts: Confounding, Invariance, and Dimension Reduction—0
Dual-constrained Deep Semi-Supervised Coupled Factorization Network with Enriched Prior—0
CLAP: Unsupervised 3D Representation Learning for Fusion 3D Perception via Curvature Sampling and Prototype Learning—0
Learning What to Share: Leaky Multi-Task Network for Text Classification—0
Learning Weighted Representations for Generalization Across Designs—0
Multi-Label Graph Convolutional Network Representation Learning—0
MULTI-LABEL METRIC LEARNING WITH BIDIRECTIONAL REPRESENTATION DEEP NEURAL NETWORKS—0
Multi-Label Text Classification by Graph Neural Network with Mixing Operations—0
Dual-Channel Multiplex Graph Neural Networks for Recommendation—0
Learning Visual Representation from Human Interactions—0
Learning Visual N-Grams from Web Data—0
Learning Visually Grounded Sentence Representations—0
Learning Visual Features from Large Weakly Supervised Data—0
Multi-Level Graph Contrastive Learning—0
DTN: Deep Multiple Task-specific Feature Interactions Network for Multi-Task Recommendation—0
Self-supervised New Activity Detection in Sensor-based Smart Environments—0
A Framework for Understanding the Role of Morphology in Universal Dependency Parsing—0
Learning Visual Composition through Improved Semantic Guidance—0
Learning View-Disentangled Human Pose Representation by Contrastive Cross-View Mutual Information Maximization—0
Learning Video Representations of Human Motion From Synthetic Data—0
Multi-level Supervised Contrastive Learning—0
Multilingual Multimodal Language Processing Using Neural Networks—0
Multilingual Seq2seq Training with Similarity Loss for Cross-Lingual Document Classification—0
Multilingual Speech Evaluation: Case Studies on English, Malay and Tamil—0
DTFormer: A Transformer-Based Method for Discrete-Time Dynamic Graph Representation Learning—0
Learning Video Representations from Textual Web Supervision—0
Show:102550
← PrevPage 128 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