MINILM: DEEP SELF-ATTENTION DISTILLATION FOR TASK-AGNOSTIC COMPRESSION OF PRE-TRAINED TRANSFORMERS

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:NeurIPS (34. : 2020 : Online) 34th Conference on Neural Information Processing Systems (NeurIPS 2020) ; Volume 8 of 27
1. Verfasser: Wang, Wenhui (VerfasserIn)
Weitere Verfasser: Wei, Furu (VerfasserIn), Dong, Li (VerfasserIn), Bao, Hangbo (VerfasserIn), Yang, Nan (VerfasserIn), Zhou, Ming (VerfasserIn)
Pages:34
Format: UnknownFormat
Sprache:eng
Veröffentlicht: 2021
Schlagworte:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Titel Jahr Verfasser
OPTIMAL EPOCH STOCHASTIC GRADIENT DESCENT ASCENT METHODS FOR MIN-MAX OPTIMIZATION 2021 Yan, Yan
BAYESIAN PROBABILISTIC NUMERICAL INTEGRATION WITH TREE-BASED MODELS 2021 Zhu, Harrison
DEEP LEARNING VERSUS KERNEL LEARNING: AN EMPIRICAL STUDY OF LOSS LANDSCAPE GEOMETRY AND THE TIME EVOLUTION OF THE NEURAL TANGENT KERNEL 2021 Fort, Stanislav
GRADIENT SURGERY FOR MULTI-TASK LEARNING 2021 Yu, Tianhe
ON SECOND ORDER BEHAVIOUR IN AUGMENTED NEURAL ODES 2021 Norcliffe, Alexander
NEURON SHAPLEY: DISCOVERING THE RESPONSIBLE NEURONS 2021 Ghorbani, Amirata
MODEL AGNOSTIC MULTILEVEL EXPLANATIONS 2021 Ramamurthy, Karthikeyan Natesan
IS PLUG-IN SOLVER SAMPLE-EFFICIENT FOR FEATURE-BASED REINFORCEMENT LEARNINGH? 2021 Cui, Qiwen
META-LEARNING FROM TASKS WITH HETEROGENEOUS ATTRIBUTE SPACES 2021 Iwata, Tomoharu
SPARSE SYMPLECTICALLY INTEGRATED NEURAL NETWORKS 2021 Dipietro, Daniel
MULTIMODAL GENERATIVE LEARNING UTILIZING JENSEN-SHANNON-DIVERGENCHE 2021 Sutter, Thomas
NEUROSYMBOLIC REINFORCEMENT LEARNING WITH FORMALLY VERIFIED EXPLORATION 2021 Anderson, Greg
DEMIXED SHARED COMPONENT ANALYSIS OF NEURAL POPULATION DATA FROM MULTIPLE BRAIN AREAS 2021 Takagi, Yu
BENCHMARKING DEEP LEARNING INTERPRETABILITY IN TIME SERIES PREDICTIONS 2021 Ismail, Aya Abdelsalam
NEUTRALIZING SELF-SELECTION BIAS IN SAMPLING FOR SORTITION 2021 Flanigan, Bailey
GAUSSIAN PROCESS BANDIT OPTIMIZATION OF THE THERMODYNAMIC VARIATIONAL OBJECTIVE 2021 Nguyen, Yu
WOODBURY TRANSFORMATIONS FOR DEEP GENERATIVE FLOWS 2021 Lu, You
STOCHASTIC DEEP GAUSSIAN PROCESSES OVER GRAPHS 2021 Li, Naiqi
GRAPH META LEARNING VIA LOCAL SUBGRAPHS 2021 Huang, Kexin
REVISITING PARAMETER SHARING FOR AUTOMATIC NEURAL CHANNEL NUMBER SEARCH 2021 Wang, Jiaxing
Alle Artikel auflisten