Representation Learning
3763 papers with code • 5 benchmarks • 9 datasets
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:
- Representation Learning: A Review and New Perspectives - Bengio et al. (2012)
- A Few Words on Representation Learning - Thalles Silva
( Image credit: Visualizing and Understanding Convolutional Networks )
Libraries
Use these libraries to find Representation Learning models and implementationsDatasets
Subtasks
- Disentanglement
- Graph Representation Learning
- Sentence Embeddings
- Network Embedding
- Network Embedding
- Sentence Embedding
- Knowledge Graph Embeddings
- Document Embedding
- Learning Word Embeddings
- Multilingual Word Embeddings
- Learning Semantic Representations
- Feature Upsampling
- Learning Network Representations
- Sentence Embeddings For Biomedical Texts
- Part-based Representation Learning
- Learning Representation Of Multi-View Data
- Learning Representation On Graph
Most implemented papers
Representation Learning with Contrastive Predictive Coding
The key insight of our model is to learn such representations by predicting the future in latent space by using powerful autoregressive models.
Unsupervised Cross-lingual Representation Learning at Scale
We also present a detailed empirical analysis of the key factors that are required to achieve these gains, including the trade-offs between (1) positive transfer and capacity dilution and (2) the performance of high and low resource languages at scale.
Exploring Simple Siamese Representation Learning
Our experiments show that collapsing solutions do exist for the loss and structure, but a stop-gradient operation plays an essential role in preventing collapsing.
Supervised Contrastive Learning
Contrastive learning applied to self-supervised representation learning has seen a resurgence in recent years, leading to state of the art performance in the unsupervised training of deep image models.
Unsupervised Representation Learning by Predicting Image Rotations
However, in order to successfully learn those features, they usually require massive amounts of manually labeled data, which is both expensive and impractical to scale.
HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation
HigherHRNet even surpasses all top-down methods on CrowdPose test (67. 6% AP), suggesting its robustness in crowded scene.
BioBERT: a pre-trained biomedical language representation model for biomedical text mining
Biomedical text mining is becoming increasingly important as the number of biomedical documents rapidly grows.
TabNet: Attentive Interpretable Tabular Learning
We propose a novel high-performance and interpretable canonical deep tabular data learning architecture, TabNet.
node2vec: Scalable Feature Learning for Networks
Taken together, our work represents a new way for efficiently learning state-of-the-art task-independent representations in complex networks.
Inductive Representation Learning on Large Graphs
Low-dimensional embeddings of nodes in large graphs have proved extremely useful in a variety of prediction tasks, from content recommendation to identifying protein functions.