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 6751–6800 of 10580 papers

TitleStatusHype
Domain Generalization via Selective Consistency Regularization for Time Series Classification—0
Learning Robust Representations for Computer Vision—0
Exploring Efficient-Tuned Learning Audio Representation Method from BriVL—0
New Benchmark for Household Garbage Image Recognition—0
Characterizing the adversarial vulnerability of speech self-supervised learning—0
Learning Robust and Multilingual Speech Representations—0
Domain Generalization -- A Causal Perspective—0
A Scalable and Effective Alternative to Graph Transformers—0
nGPT: Normalized Transformer with Representation Learning on the Hypersphere—0
Domain-aware Self-supervised Pre-training for Label-Efficient Meme Analysis—0
Learning Retrospective Knowledge with Reverse Reinforcement Learning—0
Domain-aware Self-supervised Pre-training for Weakly-supervised Meme Analysis—0
Learning Representations Using Complex-Valued Nets—0
NLP and Online Health Reports: What do we say and what do we mean?—0
NODDLE: Node2vec based deep learning model for link prediction—0
node2coords: Graph Representation Learning with Wasserstein Barycenters—0
Learning Representations Robust to Group Shifts and Adversarial Examples—0
Domain Aligned CLIP for Few-shot Classification—0
Domain-Agnostic Prior for Transfer Semantic Segmentation—0
Node Embeddings via Neighbor Embeddings—0
Channel Mapping Based on Interleaved Learning with Complex-Domain MLP-Mixer—0
A Sample Complexity Separation between Non-Convex and Convex Meta-Learning—0
A theory of representation learning gives a deep generalisation of kernel methods—0
Node Representation Learning for Directed Graphs—0
Learning Representations of Missing Data for Predicting Patient Outcomes—0
Learning Representations of Hierarchical Slates in Collaborative Filtering—0
Learning Representations of Emotional Speech with Deep Convolutional Generative Adversarial Networks—0
No Free Lunch in Self Supervised Representation Learning—0
Domain-Agnostic Clustering with Self-Distillation—0
Learning Representations of Affect from Speech—0
Learning Representations in Reinforcement Learning: an Information Bottleneck Approach—0
Learning Representations in Reinforcement Learning:An Information Bottleneck Approach—0
Learning Representations from Healthcare Time Series Data for Unsupervised Anomaly Detection—0
Change Detection from Synthetic Aperture Radar Images via Dual Path Denoising Network—0
ARVideo: Autoregressive Pretraining for Self-Supervised Video Representation Learning—0
Learning Representations from Audio-Visual Spatial Alignment—0
Learning Representations for Pixel-based Control: What Matters and Why?—0
Domain-Adversarial and Conditional State Space Model for Imitation Learning—0
Learning Representations for Incomplete Time Series Clustering—0
Learning Representations for Detecting Abusive Language—0
Domain Adaptive Graph Classification—0
ARTxAI: Explainable Artificial Intelligence Curates Deep Representation Learning for Artistic Images using Fuzzy Techniques—0
Learning Representations for Axis-Aligned Decision Forests through Input Perturbation—0
DOMAIN ADAPTATION VIA DISTRIBUTION AND REPRESENTATION MATCHING: A CASE STUDY ON TRAINING DATA SELECTION VIA REINFORCEMENT LEARNING—0
DynamicVAE: Decoupling Reconstruction Error and Disentangled Representation Learning—0
Nonlinear spiked covariance matrices and signal propagation in deep neural networks—0
Learning Representations by Humans, for Humans—0
Learning Representations by Contrasting Clusters While Bootstrapping Instances—0
Domain Adaptation Meets Disentangled Representation Learning and Style Transfer—0
Learning Representation over Dynamic Graph using Aggregation-Diffusion Mechanism—0
Show:102550
← PrevPage 136 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