Representation Learning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 14
- 평가표
- 5
- 보존된 평가 기록
- 11
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
<span style="color:grey; opacity: 0.6">( Image credit: Visualizing and Understanding Convolutional Networks )</span>
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/meszarosanna/rule_extrapolation
https://github.com/mf1024/Contrastive-Predictive-Coding-for-Image-Recognition-in-PyTorch
https://github.com/mfmceneaney/Lambda-GNNs
https://github.com/mgithubl/arxiv4tgc
https://github.com/mgmk2/StyleGAN
A Style-Based Generator Architecture for Generative Adversarial Networks
https://github.com/mgrankin/fast_tabnet
https://github.com/michiel-j/DANN-two-moons-PyTorch
https://github.com/mickaelChen/GMV
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
https://github.com/microsoft/DiscoFaceGAN
Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive Learning
https://github.com/microsoft/ExtreMA
Extreme Masking for Learning Instance and Distributed Visual Representations
https://github.com/microsoft/Graphormer
Do Transformers Really Perform Bad for Graph Representation?
https://github.com/microsoft/HittER
HittER: Hierarchical Transformers for Knowledge Graph Embeddings
https://github.com/microsoft/event-vae-rl
https://github.com/microsoft/fs-mol
https://github.com/microsoft/qlib/blob/main/qlib/contrib/model/pytorch_tabnet.py
https://github.com/microsoft/qlib/tree/main/examples/benchmarks/ADD
ADD: Augmented Disentanglement Distillation Framework for Improving Stock Trend Forecasting
https://github.com/migalkin/NodePiece/tree/main/ogb
https://github.com/mikecheninoulu/Emotional-gesture-papers
https://github.com/mindspore-ai/contrib/tree/master/application/SciNet
https://github.com/mindspore-ai/models/tree/master/official/recommend/naml
Neural News Recommendation with Attentive Multi-View Learning
https://github.com/mindspore-ai/models/tree/master/research/cv/AVA_cifar
AAG: Self-Supervised Representation Learning by Auxiliary Augmentation with GNT-Xent Loss
https://github.com/mindspore-ai/models/tree/master/research/cv/HRNetW48_cls
Deep High-Resolution Representation Learning for Visual Recognition
https://github.com/mindspore-ai/models/tree/master/research/cv/MVD
Farewell to Mutual Information: Variational Distillation for Cross-Modal Person Re-Identification
https://github.com/mindspore-ai/models/tree/master/research/cv/dcgan
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
https://github.com/mindspore-ai/models/tree/master/research/nlp/rotate
RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space
https://github.com/mindspore-courses/External-Attention-MindSpore/blob/main/model/attention/ACmixAttention.py
https://github.com/mindspore-courses/External-Attention-MindSpore/blob/main/model/backbone/DViT.py
https://github.com/mindspore-courses/External-Attention-MindSpore/blob/main/model/backbone/convnextv2.py
ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders
https://github.com/mindspore-lab/mindone
Deep High-Resolution Representation Learning for Human Pose Estimation
https://github.com/mingdachen/bilm-tf
Evaluation of sentence embeddings in downstream and linguistic probing tasks
https://github.com/mingu6/action_seg_ot
Self-labelling via simultaneous clustering and representation learning
https://github.com/minostauros/VIAR
Unsupervised Learning of View-invariant Action Representations
https://github.com/miralab-ustc/qe-cone
Learning Hierarchy-Aware Knowledge Graph Embeddings for Link Prediction
https://github.com/mistic-lab/IPSW-RFI
Unsupervised Representation Learning of Structured Radio Communication Signals
https://github.com/miszkur/SelfSupervisedLearning
Bootstrap your own latent: A new approach to self-supervised Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.