https://github.com/yushundong/reliant
공식 코드RELIANT: Fair Knowledge Distillation for Graph Neural Networks
Papers with Code 아카이브
Knowledge Distillation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 2
- 평가표
- 11
- 보존된 평가 기록
- 90
Knowledge distillation is the process of transferring knowledge from a large model to a smaller one. While large models (such as very deep neural networks or ensembles of many models) have higher knowledge capacity than small models, this capacity might not be fully utilized.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/yushundong/spectral-benchmark
공식 코드Graph Neural Networks Are More Than Filters: Revisiting and Benchmarking from A Spectral Perspective
https://github.com/yuxiaw/openfactcheck
공식 코드https://github.com/yuyangstat/flowsum
공식 코드Boosting Summarization with Normalizing Flows and Aggressive Training
https://github.com/yuyongcan/benchmark-tta
공식 코드Benchmarking Test-Time Adaptation against Distribution Shifts in Image Classification
https://github.com/yx-lu/benchmarking-llms--judgments-with-no-gold-standard
공식 코드https://github.com/yxymessi/dtc123
공식 코드Diffusion Time-step Curriculum for One Image to 3D Generation
https://github.com/yy6linda/synthetic-ehr-benchmarking
공식 코드A Multifaceted Benchmarking of Synthetic Electronic Health Record Generation Models
https://github.com/yzd-v/FGD
공식 코드https://github.com/yzd-v/MGD
공식 코드https://github.com/yzd-v/cls_KD
공식 코드https://github.com/yzhao062/PyHealth
공식 코드https://github.com/yzhao062/SUOD
공식 코드https://github.com/yzhao062/pyod
공식 코드https://github.com/yzqinjacob/distill-mlc
공식 코드Knowledge Distillation from Single to Multi Labels: an Empirical Study
https://github.com/zacharywang-007/g-hanet
공식 코드Histo-Genomic Knowledge Distillation For Cancer Prognosis From Histopathology Whole Slide Images
https://github.com/zahraabbasiantaeb/simquac
공식 코드Let the LLMs Talk: Simulating Human-to-Human Conversational QA via Zero-Shot LLM-to-LLM Interactions
https://github.com/zaixizhang/awesome-sbdd
공식 코드Geometric Deep Learning for Structure-Based Drug Design: A Survey
https://github.com/zalandoresearch/fashion-mnist
공식 코드Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
https://github.com/zayenz/cp-2019-nmbr9
공식 코드https://github.com/zehuichen123/bevdistill
공식 코드BEVDistill: Cross-Modal BEV Distillation for Multi-View 3D Object Detection
https://github.com/zeinabtaghavi/impliret
공식 코드ImpliRet: Benchmarking the Implicit Fact Retrieval Challenge
https://github.com/zermatt-luo/SBKA
공식 코드Symmetrical Bidirectional Knowledge Alignment for Zero-Shot Sketch-Based Image Retrieval
https://github.com/zerowst/chatcoach
공식 코드Benchmarking Large Language Models on Communicative Medical Coaching: a Novel System and Dataset
https://github.com/zezhishao/basicts
공식 코드https://github.com/zhang-henry/sclifd_tii
공식 코드https://github.com/zhang-jinghua/dbc-fscil
공식 코드A Forward and Backward Compatible Framework for Few-shot Class-incremental Pill Recognition
https://github.com/zhang-xie/wimuse
공식 코드https://github.com/zhangbo-nlp/vikdf
공식 코드https://github.com/zhangchbin/rcil
공식 코드Representation Compensation Networks for Continual Semantic Segmentation
https://github.com/zhanglab-deepneurocoglab/csegg
공식 코드Adaptive Visual Scene Understanding: Incremental Scene Graph Generation
https://github.com/zhanglab-deepneurocoglab/worm
공식 코드Decoding the Enigma: Benchmarking Humans and AIs on the Many Facets of Working Memory
https://github.com/zhanglin-pku/fedftg
공식 코드Fine-tuning Global Model via Data-Free Knowledge Distillation for Non-IID Federated Learning
https://github.com/zhangsha1024/HVDistill
공식 코드https://github.com/zhangsn-19/pan
공식 코드Towards Benchmarking and Assessing Visual Naturalness of Physical World Adversarial Attacks
https://github.com/zhangyong-tang/gmmt
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.