Papers with Code 아카이브
Extreme Multi-Label Classification
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
Extreme Multi-Label Classification is a supervised learning problem where an instance may be associated with multiple labels. The two main problems are the unbalanced labels in the dataset and the amount of different labels.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/Extreme-classification/DECAF
공식 코드https://github.com/Extreme-classification/ECLARE
공식 코드ECLARE: Extreme Classification with Label Graph Correlations
https://github.com/Nishiken1/Circular-HRR
공식 코드https://github.com/OctoberChang/X-Transformer
공식 코드Taming Pretrained Transformers for Extreme Multi-label Text Classification
https://github.com/Priberam/mesinesp-svm
공식 코드Priberam at MESINESP Multi-label Classification of Medical Texts Task
https://github.com/YMA33/HeteroGPU
공식 코드Adaptive Elastic Training for Sparse Deep Learning on Heterogeneous Multi-GPU Servers
https://github.com/alexa/xlgen-eacl-2023
공식 코드Cluster-Guided Label Generation in Extreme Multi-Label Classification
https://github.com/amzn/pecos
공식 코드Extreme Multi-label Learning for Semantic Matching in Product Search
https://github.com/hiro4bbh/sticker
공식 코드https://github.com/kareldo/xmc.dspy
공식 코드https://github.com/lotus-data/lotus
공식 코드Semantic Operators: A Declarative Model for Rich, AI-based Data Processing
https://github.com/luka-group/ddr
공식 코드Dense Retrieval as Indirect Supervision for Large-space Decision Making
https://github.com/maxitron93/stratified_sampling_for_XML
공식 코드https://github.com/mwydmuch/extremeText
공식 코드A no-regret generalization of hierarchical softmax to extreme multi-label classification
https://github.com/mwydmuch/napkinXC
공식 코드Probabilistic Label Trees for Extreme Multi-label Classification
https://github.com/mwydmuch/xcolumns
공식 코드Generalized test utilities for long-tail performance in extreme multi-label classification
https://github.com/nilesh2797/dexml
공식 코드https://github.com/nilesh2797/elias
공식 코드ELIAS: End-to-End Learning to Index and Search in Large Output Spaces
https://github.com/stanford-futuredata/lotus
공식 코드Semantic Operators: A Declarative Model for Rich, AI-based Data Processing
https://github.com/wushanshan/L1AE
공식 코드Learning a Compressed Sensing Measurement Matrix via Gradient Unrolling
https://github.com/xmc-aalto/bonsai
공식 코드Bonsai -- Diverse and Shallow Trees for Extreme Multi-label Classification
https://github.com/xmc-aalto/proxml
공식 코드https://github.com/yaxinzhuars/icxml
공식 코드ICXML: An In-Context Learning Framework for Zero-Shot Extreme Multi-Label Classification
https://github.com/JerryKwon/melon_plylst_continuation
Taming Pretrained Transformers for Extreme Multi-label Text Classification
https://github.com/OctoberChang/GAMLP?fbclid=IwAR03ugAd7H0U_kQrkihBDMJ-Bxy3siwKVbnBTNkz_IVp5J25L0DFlTK0yfc
Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Prediction
https://github.com/Refefer/fastxml
DiSMEC - Distributed Sparse Machines for Extreme Multi-label Classification
https://github.com/arbasher/straSplit
https://github.com/elichienxD/SAGN_with_SLE
Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Prediction
https://github.com/elichienxD/deep_gcns_torch
Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Prediction
https://github.com/kareldo/biodex
https://github.com/mwydmuch/extweme_wabbit
Probabilistic Label Trees for Extreme Multi-label Classification
https://github.com/mwydmuch/macro-measures-in-xmlc
Generalized test utilities for long-tail performance in extreme multi-label classification
https://github.com/rajatsen91/XtremeContextualBandits
https://github.com/scakc/ConvBonsai-Tree
Bonsai -- Diverse and Shallow Trees for Extreme Multi-label Classification
https://github.com/theGuyWithBlackTie/Deep-Extreme-Multi-Label-Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.