SlideShare a Scribd company logo
1 of 17
Super Tickets in Pre-Trained Language Models: From
Model Compression to Improving Generalization
Chen Liang, Simiao Zuo, Minshuo Chen , Haoming Jiang, Xiaodong Liu, Pengcheng
He, Tuo Zhao, Weizhu Chen
Lottery Ticket Hypothesis
• A randomly-initialized, dense neural network contains a subnetwork
that is initialized such that—when trained in isolation—it can match the
test accuracy of the original network after training for at most the same
number of iterations.
Lottery Ticket Hypothesis
Phase Transition on LTH
1) Phase Transition: The change in the test accuracy of the compressed model
2) Super Ticket: The best value for weight remaining(esp. between Phase1 and Phase2 in this paper ).
Contributions
• The first to identify the phase transition phenomenon in pruning large
neural language models
• The first to show that pruning can improve the generalization when the
models are lightly compressed
• Propose a new pruning approach for multi-task fine-tunning of neural
language models
Transformer – MultiHeadAttention
• Attention
• Multi-Head Attention
Finding Super Tickets
• Prunning of attention heads and feed-forward layers.
• Adopt Importance score
Low Importance Score: small contribution towards the output
High Importance Score: high expressive power for the output
Multi-task learning with Tickets Sharing
Experiments - Single Task
- Baseline: ST-DNN(Base/Large): BERT(Base/Large) with Single Task FFN.
- Proposed: SuperT(Base/Large): BERT(Base/Large) with Super Tickets.
• Models
spec. pruning by 8 different sparsity(e.g. 10% heads/20% FFN) -> choose best!
- Optimizer: Adamax
- Learning rate: {5e-5, 1e-4, 2e-4}
- Batch size: {8, 6, 32}
• Compile/Train Options
Experiment results on GLUE Benchmarks
Experiment results on GLUE Benchmarks
In all the tasks, SuperT consistently archieves
better generalization than ST-DNN.
Performance gain of the super tickets is more
Significant in small task.
Performance of the super tickets is related to
Model size. In large models, more non-
expressive tickets can be pruned without
Performance degradation.
Experiment results on GLUE Benchmarks
Single task fine-tunning evaluation results of
1) Super tickets(blue) 2) random(orange) 3) losing tickets(8 different sparsity levels)
Experiments – Multi Task
Baseline:
1) MT-DNN(Base/Large): BERT(Base/Large) with task shared layers
2) MT-DNN(Base/Large)+ ST Fine-tuning: further trained MT-DNN on individual downstream task
• Models
-Same as the ones of Single Task.
• Compile/Train Options
Proposed:
1) Ticket-Share(Base/Large): MT-DNN model refined through the ticket sharing strategy.
2) Ticket-Share(Base/Large)+ ST Fine-tunning: A fine-tuned single-task Ticket-Share model.
Experiment results on GLUE
Experiment results on SNLI/ SciTail
Analysis
• Sensitivity to Random Seed
Training with super tickets effectively reduces
model variance on the performance caused
by the random initialization.
• Tickets Importance Across Tasks
SST-2 benefits little from tickets sharing(see
Figure6(a)(c)(d))
CoLA (Figure 6(c)), or dominated jointly by
two tasks, e.g., CoLA and STS-B (Figure 6(d))
are dominated by a single Task.
Thus, some tickets only learn task-specific
knowledge, and the two tasks may share
certain task-specific knowledge.
Discussion
• Structured Lottery Tickets
• Searching Better Generalized Super Tickets
• Searching Super Tickets Efficiently

More Related Content

What's hot

Policy Based reinforcement Learning for time series Anomaly detection
Policy Based reinforcement Learning for time series Anomaly detectionPolicy Based reinforcement Learning for time series Anomaly detection
Policy Based reinforcement Learning for time series Anomaly detectionKishor Datta Gupta
 
Triangular Learner Model
Triangular Learner ModelTriangular Learner Model
Triangular Learner ModelLoc Nguyen
 
Aaa ped-14-Ensemble Learning: About Ensemble Learning
Aaa ped-14-Ensemble Learning: About Ensemble LearningAaa ped-14-Ensemble Learning: About Ensemble Learning
Aaa ped-14-Ensemble Learning: About Ensemble LearningAminaRepo
 
Analyzing individual neurons in pre trained language models
Analyzing individual neurons in pre trained language modelsAnalyzing individual neurons in pre trained language models
Analyzing individual neurons in pre trained language modelsken-ando
 
Ensemble learning Techniques
Ensemble learning TechniquesEnsemble learning Techniques
Ensemble learning TechniquesBabu Priyavrat
 
Lecture 9 slides: Machine learning for Protein Structure ...
Lecture 9 slides: Machine learning for Protein Structure ...Lecture 9 slides: Machine learning for Protein Structure ...
Lecture 9 slides: Machine learning for Protein Structure ...butest
 
THE IMPACT OF MOBILE NODES ARRIVAL PATTERNS IN MANETS USING POISSON MODELS
THE IMPACT OF MOBILE NODES ARRIVAL PATTERNS IN MANETS USING POISSON MODELSTHE IMPACT OF MOBILE NODES ARRIVAL PATTERNS IN MANETS USING POISSON MODELS
THE IMPACT OF MOBILE NODES ARRIVAL PATTERNS IN MANETS USING POISSON MODELSIJMIT JOURNAL
 
Ensemble learning
Ensemble learningEnsemble learning
Ensemble learningHaris Jamil
 
RapidMiner: Learning Schemes In Rapid Miner
RapidMiner:  Learning Schemes In Rapid MinerRapidMiner:  Learning Schemes In Rapid Miner
RapidMiner: Learning Schemes In Rapid MinerDataminingTools Inc
 

What's hot (11)

Policy Based reinforcement Learning for time series Anomaly detection
Policy Based reinforcement Learning for time series Anomaly detectionPolicy Based reinforcement Learning for time series Anomaly detection
Policy Based reinforcement Learning for time series Anomaly detection
 
L4. Ensembles of Decision Trees
L4. Ensembles of Decision TreesL4. Ensembles of Decision Trees
L4. Ensembles of Decision Trees
 
Triangular Learner Model
Triangular Learner ModelTriangular Learner Model
Triangular Learner Model
 
Aaa ped-14-Ensemble Learning: About Ensemble Learning
Aaa ped-14-Ensemble Learning: About Ensemble LearningAaa ped-14-Ensemble Learning: About Ensemble Learning
Aaa ped-14-Ensemble Learning: About Ensemble Learning
 
Borderline Smote
Borderline SmoteBorderline Smote
Borderline Smote
 
Analyzing individual neurons in pre trained language models
Analyzing individual neurons in pre trained language modelsAnalyzing individual neurons in pre trained language models
Analyzing individual neurons in pre trained language models
 
Ensemble learning Techniques
Ensemble learning TechniquesEnsemble learning Techniques
Ensemble learning Techniques
 
Lecture 9 slides: Machine learning for Protein Structure ...
Lecture 9 slides: Machine learning for Protein Structure ...Lecture 9 slides: Machine learning for Protein Structure ...
Lecture 9 slides: Machine learning for Protein Structure ...
 
THE IMPACT OF MOBILE NODES ARRIVAL PATTERNS IN MANETS USING POISSON MODELS
THE IMPACT OF MOBILE NODES ARRIVAL PATTERNS IN MANETS USING POISSON MODELSTHE IMPACT OF MOBILE NODES ARRIVAL PATTERNS IN MANETS USING POISSON MODELS
THE IMPACT OF MOBILE NODES ARRIVAL PATTERNS IN MANETS USING POISSON MODELS
 
Ensemble learning
Ensemble learningEnsemble learning
Ensemble learning
 
RapidMiner: Learning Schemes In Rapid Miner
RapidMiner:  Learning Schemes In Rapid MinerRapidMiner:  Learning Schemes In Rapid Miner
RapidMiner: Learning Schemes In Rapid Miner
 

Similar to Super tickets in pre trained language models

Switch Transformers: Scaling to Trillion Parameter Models with Simple and Eff...
Switch Transformers: Scaling to Trillion Parameter Models with Simple and Eff...Switch Transformers: Scaling to Trillion Parameter Models with Simple and Eff...
Switch Transformers: Scaling to Trillion Parameter Models with Simple and Eff...taeseon ryu
 
Lifelong Learning for Dynamically Expandable Networks
Lifelong Learning for Dynamically Expandable NetworksLifelong Learning for Dynamically Expandable Networks
Lifelong Learning for Dynamically Expandable NetworksNAVER Engineering
 
PR095: Modularity Matters: Learning Invariant Relational Reasoning Tasks
PR095: Modularity Matters: Learning Invariant Relational Reasoning TasksPR095: Modularity Matters: Learning Invariant Relational Reasoning Tasks
PR095: Modularity Matters: Learning Invariant Relational Reasoning TasksJinwon Lee
 
LongT5_Efficient Text-toText Transformer for Long Sequences_san.pptx
LongT5_Efficient Text-toText Transformer for Long Sequences_san.pptxLongT5_Efficient Text-toText Transformer for Long Sequences_san.pptx
LongT5_Efficient Text-toText Transformer for Long Sequences_san.pptxSan Kim
 
MEME – An Integrated Tool For Advanced Computational Experiments
MEME – An Integrated Tool For Advanced Computational ExperimentsMEME – An Integrated Tool For Advanced Computational Experiments
MEME – An Integrated Tool For Advanced Computational ExperimentsGIScRG
 
Machine Learning Algorithm - Decision Trees
Machine Learning Algorithm - Decision Trees Machine Learning Algorithm - Decision Trees
Machine Learning Algorithm - Decision Trees Kush Kulshrestha
 
ML Module 3 Non Linear Learning.pptx
ML Module 3 Non Linear Learning.pptxML Module 3 Non Linear Learning.pptx
ML Module 3 Non Linear Learning.pptxDebabrataPain1
 
Learning to Search Henry Kautz
Learning to Search Henry KautzLearning to Search Henry Kautz
Learning to Search Henry Kautzbutest
 
Learning to Search Henry Kautz
Learning to Search Henry KautzLearning to Search Henry Kautz
Learning to Search Henry Kautzbutest
 
PR-344: A Battle of Network Structures: An Empirical Study of CNN, Transforme...
PR-344: A Battle of Network Structures: An Empirical Study of CNN, Transforme...PR-344: A Battle of Network Structures: An Empirical Study of CNN, Transforme...
PR-344: A Battle of Network Structures: An Empirical Study of CNN, Transforme...Jinwon Lee
 
PR-187 : MorphNet: Fast & Simple Resource-Constrained Structure Learning of D...
PR-187 : MorphNet: Fast & Simple Resource-Constrained Structure Learning of D...PR-187 : MorphNet: Fast & Simple Resource-Constrained Structure Learning of D...
PR-187 : MorphNet: Fast & Simple Resource-Constrained Structure Learning of D...Sunghoon Joo
 
240311_JW_labseminar[Sequence to Sequence Learning with Neural Networks].pptx
240311_JW_labseminar[Sequence to Sequence Learning with Neural Networks].pptx240311_JW_labseminar[Sequence to Sequence Learning with Neural Networks].pptx
240311_JW_labseminar[Sequence to Sequence Learning with Neural Networks].pptxthanhdowork
 
Data clustering using kernel based
Data clustering using kernel basedData clustering using kernel based
Data clustering using kernel basedIJITCA Journal
 
2019 Levenshtein Transformer
2019 Levenshtein Transformer2019 Levenshtein Transformer
2019 Levenshtein Transformer広樹 本間
 
Wasserstein 1031 thesis [Chung il kim]
Wasserstein 1031 thesis [Chung il kim]Wasserstein 1031 thesis [Chung il kim]
Wasserstein 1031 thesis [Chung il kim]Chung-Il Kim
 
PR-411: Model soups: averaging weights of multiple fine-tuned models improves...
PR-411: Model soups: averaging weights of multiple fine-tuned models improves...PR-411: Model soups: averaging weights of multiple fine-tuned models improves...
PR-411: Model soups: averaging weights of multiple fine-tuned models improves...Sunghoon Joo
 
Learning to Learn by Gradient Descent by Gradient Descent
Learning to Learn by Gradient Descent by Gradient DescentLearning to Learn by Gradient Descent by Gradient Descent
Learning to Learn by Gradient Descent by Gradient DescentKaty Lee
 

Similar to Super tickets in pre trained language models (20)

Switch Transformers: Scaling to Trillion Parameter Models with Simple and Eff...
Switch Transformers: Scaling to Trillion Parameter Models with Simple and Eff...Switch Transformers: Scaling to Trillion Parameter Models with Simple and Eff...
Switch Transformers: Scaling to Trillion Parameter Models with Simple and Eff...
 
Lifelong Learning for Dynamically Expandable Networks
Lifelong Learning for Dynamically Expandable NetworksLifelong Learning for Dynamically Expandable Networks
Lifelong Learning for Dynamically Expandable Networks
 
PR095: Modularity Matters: Learning Invariant Relational Reasoning Tasks
PR095: Modularity Matters: Learning Invariant Relational Reasoning TasksPR095: Modularity Matters: Learning Invariant Relational Reasoning Tasks
PR095: Modularity Matters: Learning Invariant Relational Reasoning Tasks
 
LongT5_Efficient Text-toText Transformer for Long Sequences_san.pptx
LongT5_Efficient Text-toText Transformer for Long Sequences_san.pptxLongT5_Efficient Text-toText Transformer for Long Sequences_san.pptx
LongT5_Efficient Text-toText Transformer for Long Sequences_san.pptx
 
gpt3_presentation.pdf
gpt3_presentation.pdfgpt3_presentation.pdf
gpt3_presentation.pdf
 
MEME – An Integrated Tool For Advanced Computational Experiments
MEME – An Integrated Tool For Advanced Computational ExperimentsMEME – An Integrated Tool For Advanced Computational Experiments
MEME – An Integrated Tool For Advanced Computational Experiments
 
Machine Learning Algorithm - Decision Trees
Machine Learning Algorithm - Decision Trees Machine Learning Algorithm - Decision Trees
Machine Learning Algorithm - Decision Trees
 
ML Module 3 Non Linear Learning.pptx
ML Module 3 Non Linear Learning.pptxML Module 3 Non Linear Learning.pptx
ML Module 3 Non Linear Learning.pptx
 
Learning to Search Henry Kautz
Learning to Search Henry KautzLearning to Search Henry Kautz
Learning to Search Henry Kautz
 
Learning to Search Henry Kautz
Learning to Search Henry KautzLearning to Search Henry Kautz
Learning to Search Henry Kautz
 
PR-344: A Battle of Network Structures: An Empirical Study of CNN, Transforme...
PR-344: A Battle of Network Structures: An Empirical Study of CNN, Transforme...PR-344: A Battle of Network Structures: An Empirical Study of CNN, Transforme...
PR-344: A Battle of Network Structures: An Empirical Study of CNN, Transforme...
 
Classification
ClassificationClassification
Classification
 
Classification
ClassificationClassification
Classification
 
PR-187 : MorphNet: Fast & Simple Resource-Constrained Structure Learning of D...
PR-187 : MorphNet: Fast & Simple Resource-Constrained Structure Learning of D...PR-187 : MorphNet: Fast & Simple Resource-Constrained Structure Learning of D...
PR-187 : MorphNet: Fast & Simple Resource-Constrained Structure Learning of D...
 
240311_JW_labseminar[Sequence to Sequence Learning with Neural Networks].pptx
240311_JW_labseminar[Sequence to Sequence Learning with Neural Networks].pptx240311_JW_labseminar[Sequence to Sequence Learning with Neural Networks].pptx
240311_JW_labseminar[Sequence to Sequence Learning with Neural Networks].pptx
 
Data clustering using kernel based
Data clustering using kernel basedData clustering using kernel based
Data clustering using kernel based
 
2019 Levenshtein Transformer
2019 Levenshtein Transformer2019 Levenshtein Transformer
2019 Levenshtein Transformer
 
Wasserstein 1031 thesis [Chung il kim]
Wasserstein 1031 thesis [Chung il kim]Wasserstein 1031 thesis [Chung il kim]
Wasserstein 1031 thesis [Chung il kim]
 
PR-411: Model soups: averaging weights of multiple fine-tuned models improves...
PR-411: Model soups: averaging weights of multiple fine-tuned models improves...PR-411: Model soups: averaging weights of multiple fine-tuned models improves...
PR-411: Model soups: averaging weights of multiple fine-tuned models improves...
 
Learning to Learn by Gradient Descent by Gradient Descent
Learning to Learn by Gradient Descent by Gradient DescentLearning to Learn by Gradient Descent by Gradient Descent
Learning to Learn by Gradient Descent by Gradient Descent
 

More from HyunKyu Jeon

[PR-358] Training Differentially Private Generative Models with Sinkhorn Dive...
[PR-358] Training Differentially Private Generative Models with Sinkhorn Dive...[PR-358] Training Differentially Private Generative Models with Sinkhorn Dive...
[PR-358] Training Differentially Private Generative Models with Sinkhorn Dive...HyunKyu Jeon
 
Synthesizer rethinking self-attention for transformer models
Synthesizer rethinking self-attention for transformer models Synthesizer rethinking self-attention for transformer models
Synthesizer rethinking self-attention for transformer models HyunKyu Jeon
 
Domain Invariant Representation Learning with Domain Density Transformations
Domain Invariant Representation Learning with Domain Density TransformationsDomain Invariant Representation Learning with Domain Density Transformations
Domain Invariant Representation Learning with Domain Density TransformationsHyunKyu Jeon
 
Meta back translation
Meta back translationMeta back translation
Meta back translationHyunKyu Jeon
 
Maxmin qlearning controlling the estimation bias of qlearning
Maxmin qlearning controlling the estimation bias of qlearningMaxmin qlearning controlling the estimation bias of qlearning
Maxmin qlearning controlling the estimation bias of qlearningHyunKyu Jeon
 
Adversarial Attack in Neural Machine Translation
Adversarial Attack in Neural Machine TranslationAdversarial Attack in Neural Machine Translation
Adversarial Attack in Neural Machine TranslationHyunKyu Jeon
 
십분딥러닝_19_ALL_ABOUT_CNN
십분딥러닝_19_ALL_ABOUT_CNN십분딥러닝_19_ALL_ABOUT_CNN
십분딥러닝_19_ALL_ABOUT_CNNHyunKyu Jeon
 
십분수학_Entropy and KL-Divergence
십분수학_Entropy and KL-Divergence십분수학_Entropy and KL-Divergence
십분수학_Entropy and KL-DivergenceHyunKyu Jeon
 
(edited) 십분딥러닝_17_DIM(DeepInfoMax)
(edited) 십분딥러닝_17_DIM(DeepInfoMax)(edited) 십분딥러닝_17_DIM(DeepInfoMax)
(edited) 십분딥러닝_17_DIM(DeepInfoMax)HyunKyu Jeon
 
십분딥러닝_18_GumBolt (VAE with Boltzmann Machine)
십분딥러닝_18_GumBolt (VAE with Boltzmann Machine)십분딥러닝_18_GumBolt (VAE with Boltzmann Machine)
십분딥러닝_18_GumBolt (VAE with Boltzmann Machine)HyunKyu Jeon
 
십분딥러닝_17_DIM(Deep InfoMax)
십분딥러닝_17_DIM(Deep InfoMax)십분딥러닝_17_DIM(Deep InfoMax)
십분딥러닝_17_DIM(Deep InfoMax)HyunKyu Jeon
 
십분딥러닝_16_WGAN (Wasserstein GANs)
십분딥러닝_16_WGAN (Wasserstein GANs)십분딥러닝_16_WGAN (Wasserstein GANs)
십분딥러닝_16_WGAN (Wasserstein GANs)HyunKyu Jeon
 
십분딥러닝_15_SSD(Single Shot Multibox Detector)
십분딥러닝_15_SSD(Single Shot Multibox Detector)십분딥러닝_15_SSD(Single Shot Multibox Detector)
십분딥러닝_15_SSD(Single Shot Multibox Detector)HyunKyu Jeon
 
십분딥러닝_14_YOLO(You Only Look Once)
십분딥러닝_14_YOLO(You Only Look Once)십분딥러닝_14_YOLO(You Only Look Once)
십분딥러닝_14_YOLO(You Only Look Once)HyunKyu Jeon
 
십분딥러닝_13_Transformer Networks (Self Attention)
십분딥러닝_13_Transformer Networks (Self Attention)십분딥러닝_13_Transformer Networks (Self Attention)
십분딥러닝_13_Transformer Networks (Self Attention)HyunKyu Jeon
 
십분딥러닝_12_어텐션(Attention Mechanism)
십분딥러닝_12_어텐션(Attention Mechanism)십분딥러닝_12_어텐션(Attention Mechanism)
십분딥러닝_12_어텐션(Attention Mechanism)HyunKyu Jeon
 
십분딥러닝_11_LSTM (Long Short Term Memory)
십분딥러닝_11_LSTM (Long Short Term Memory)십분딥러닝_11_LSTM (Long Short Term Memory)
십분딥러닝_11_LSTM (Long Short Term Memory)HyunKyu Jeon
 
십분딥러닝_10_R-CNN
십분딥러닝_10_R-CNN십분딥러닝_10_R-CNN
십분딥러닝_10_R-CNNHyunKyu Jeon
 
십분딥러닝_9_VAE(Variational Autoencoder)
십분딥러닝_9_VAE(Variational Autoencoder)십분딥러닝_9_VAE(Variational Autoencoder)
십분딥러닝_9_VAE(Variational Autoencoder)HyunKyu Jeon
 
십분딥러닝_7_GANs (Edited)
십분딥러닝_7_GANs (Edited)십분딥러닝_7_GANs (Edited)
십분딥러닝_7_GANs (Edited)HyunKyu Jeon
 

More from HyunKyu Jeon (20)

[PR-358] Training Differentially Private Generative Models with Sinkhorn Dive...
[PR-358] Training Differentially Private Generative Models with Sinkhorn Dive...[PR-358] Training Differentially Private Generative Models with Sinkhorn Dive...
[PR-358] Training Differentially Private Generative Models with Sinkhorn Dive...
 
Synthesizer rethinking self-attention for transformer models
Synthesizer rethinking self-attention for transformer models Synthesizer rethinking self-attention for transformer models
Synthesizer rethinking self-attention for transformer models
 
Domain Invariant Representation Learning with Domain Density Transformations
Domain Invariant Representation Learning with Domain Density TransformationsDomain Invariant Representation Learning with Domain Density Transformations
Domain Invariant Representation Learning with Domain Density Transformations
 
Meta back translation
Meta back translationMeta back translation
Meta back translation
 
Maxmin qlearning controlling the estimation bias of qlearning
Maxmin qlearning controlling the estimation bias of qlearningMaxmin qlearning controlling the estimation bias of qlearning
Maxmin qlearning controlling the estimation bias of qlearning
 
Adversarial Attack in Neural Machine Translation
Adversarial Attack in Neural Machine TranslationAdversarial Attack in Neural Machine Translation
Adversarial Attack in Neural Machine Translation
 
십분딥러닝_19_ALL_ABOUT_CNN
십분딥러닝_19_ALL_ABOUT_CNN십분딥러닝_19_ALL_ABOUT_CNN
십분딥러닝_19_ALL_ABOUT_CNN
 
십분수학_Entropy and KL-Divergence
십분수학_Entropy and KL-Divergence십분수학_Entropy and KL-Divergence
십분수학_Entropy and KL-Divergence
 
(edited) 십분딥러닝_17_DIM(DeepInfoMax)
(edited) 십분딥러닝_17_DIM(DeepInfoMax)(edited) 십분딥러닝_17_DIM(DeepInfoMax)
(edited) 십분딥러닝_17_DIM(DeepInfoMax)
 
십분딥러닝_18_GumBolt (VAE with Boltzmann Machine)
십분딥러닝_18_GumBolt (VAE with Boltzmann Machine)십분딥러닝_18_GumBolt (VAE with Boltzmann Machine)
십분딥러닝_18_GumBolt (VAE with Boltzmann Machine)
 
십분딥러닝_17_DIM(Deep InfoMax)
십분딥러닝_17_DIM(Deep InfoMax)십분딥러닝_17_DIM(Deep InfoMax)
십분딥러닝_17_DIM(Deep InfoMax)
 
십분딥러닝_16_WGAN (Wasserstein GANs)
십분딥러닝_16_WGAN (Wasserstein GANs)십분딥러닝_16_WGAN (Wasserstein GANs)
십분딥러닝_16_WGAN (Wasserstein GANs)
 
십분딥러닝_15_SSD(Single Shot Multibox Detector)
십분딥러닝_15_SSD(Single Shot Multibox Detector)십분딥러닝_15_SSD(Single Shot Multibox Detector)
십분딥러닝_15_SSD(Single Shot Multibox Detector)
 
십분딥러닝_14_YOLO(You Only Look Once)
십분딥러닝_14_YOLO(You Only Look Once)십분딥러닝_14_YOLO(You Only Look Once)
십분딥러닝_14_YOLO(You Only Look Once)
 
십분딥러닝_13_Transformer Networks (Self Attention)
십분딥러닝_13_Transformer Networks (Self Attention)십분딥러닝_13_Transformer Networks (Self Attention)
십분딥러닝_13_Transformer Networks (Self Attention)
 
십분딥러닝_12_어텐션(Attention Mechanism)
십분딥러닝_12_어텐션(Attention Mechanism)십분딥러닝_12_어텐션(Attention Mechanism)
십분딥러닝_12_어텐션(Attention Mechanism)
 
십분딥러닝_11_LSTM (Long Short Term Memory)
십분딥러닝_11_LSTM (Long Short Term Memory)십분딥러닝_11_LSTM (Long Short Term Memory)
십분딥러닝_11_LSTM (Long Short Term Memory)
 
십분딥러닝_10_R-CNN
십분딥러닝_10_R-CNN십분딥러닝_10_R-CNN
십분딥러닝_10_R-CNN
 
십분딥러닝_9_VAE(Variational Autoencoder)
십분딥러닝_9_VAE(Variational Autoencoder)십분딥러닝_9_VAE(Variational Autoencoder)
십분딥러닝_9_VAE(Variational Autoencoder)
 
십분딥러닝_7_GANs (Edited)
십분딥러닝_7_GANs (Edited)십분딥러닝_7_GANs (Edited)
십분딥러닝_7_GANs (Edited)
 

Recently uploaded

Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...
Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...
Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...dajasot375
 
办理学位证纽约大学毕业证(NYU毕业证书)原版一比一
办理学位证纽约大学毕业证(NYU毕业证书)原版一比一办理学位证纽约大学毕业证(NYU毕业证书)原版一比一
办理学位证纽约大学毕业证(NYU毕业证书)原版一比一fhwihughh
 
Customer Service Analytics - Make Sense of All Your Data.pptx
Customer Service Analytics - Make Sense of All Your Data.pptxCustomer Service Analytics - Make Sense of All Your Data.pptx
Customer Service Analytics - Make Sense of All Your Data.pptxEmmanuel Dauda
 
Brighton SEO | April 2024 | Data Storytelling
Brighton SEO | April 2024 | Data StorytellingBrighton SEO | April 2024 | Data Storytelling
Brighton SEO | April 2024 | Data StorytellingNeil Barnes
 
Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝soniya singh
 
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort servicejennyeacort
 
20240419 - Measurecamp Amsterdam - SAM.pdf
20240419 - Measurecamp Amsterdam - SAM.pdf20240419 - Measurecamp Amsterdam - SAM.pdf
20240419 - Measurecamp Amsterdam - SAM.pdfHuman37
 
Dubai Call Girls Wifey O52&786472 Call Girls Dubai
Dubai Call Girls Wifey O52&786472 Call Girls DubaiDubai Call Girls Wifey O52&786472 Call Girls Dubai
Dubai Call Girls Wifey O52&786472 Call Girls Dubaihf8803863
 
Call Girls In Mahipalpur O9654467111 Escorts Service
Call Girls In Mahipalpur O9654467111  Escorts ServiceCall Girls In Mahipalpur O9654467111  Escorts Service
Call Girls In Mahipalpur O9654467111 Escorts ServiceSapana Sha
 
High Class Call Girls Noida Sector 39 Aarushi 🔝8264348440🔝 Independent Escort...
High Class Call Girls Noida Sector 39 Aarushi 🔝8264348440🔝 Independent Escort...High Class Call Girls Noida Sector 39 Aarushi 🔝8264348440🔝 Independent Escort...
High Class Call Girls Noida Sector 39 Aarushi 🔝8264348440🔝 Independent Escort...soniya singh
 
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024thyngster
 
04242024_CCC TUG_Joins and Relationships
04242024_CCC TUG_Joins and Relationships04242024_CCC TUG_Joins and Relationships
04242024_CCC TUG_Joins and Relationshipsccctableauusergroup
 
办理(Vancouver毕业证书)加拿大温哥华岛大学毕业证成绩单原版一比一
办理(Vancouver毕业证书)加拿大温哥华岛大学毕业证成绩单原版一比一办理(Vancouver毕业证书)加拿大温哥华岛大学毕业证成绩单原版一比一
办理(Vancouver毕业证书)加拿大温哥华岛大学毕业证成绩单原版一比一F La
 
1:1定制(UQ毕业证)昆士兰大学毕业证成绩单修改留信学历认证原版一模一样
1:1定制(UQ毕业证)昆士兰大学毕业证成绩单修改留信学历认证原版一模一样1:1定制(UQ毕业证)昆士兰大学毕业证成绩单修改留信学历认证原版一模一样
1:1定制(UQ毕业证)昆士兰大学毕业证成绩单修改留信学历认证原版一模一样vhwb25kk
 
GA4 Without Cookies [Measure Camp AMS]
GA4 Without Cookies [Measure Camp AMS]GA4 Without Cookies [Measure Camp AMS]
GA4 Without Cookies [Measure Camp AMS]📊 Markus Baersch
 
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Callshivangimorya083
 
RA-11058_IRR-COMPRESS Do 198 series of 1998
RA-11058_IRR-COMPRESS Do 198 series of 1998RA-11058_IRR-COMPRESS Do 198 series of 1998
RA-11058_IRR-COMPRESS Do 198 series of 1998YohFuh
 
办理学位证中佛罗里达大学毕业证,UCF成绩单原版一比一
办理学位证中佛罗里达大学毕业证,UCF成绩单原版一比一办理学位证中佛罗里达大学毕业证,UCF成绩单原版一比一
办理学位证中佛罗里达大学毕业证,UCF成绩单原版一比一F sss
 
Amazon TQM (2) Amazon TQM (2)Amazon TQM (2).pptx
Amazon TQM (2) Amazon TQM (2)Amazon TQM (2).pptxAmazon TQM (2) Amazon TQM (2)Amazon TQM (2).pptx
Amazon TQM (2) Amazon TQM (2)Amazon TQM (2).pptxAbdelrhman abooda
 
DBA Basics: Getting Started with Performance Tuning.pdf
DBA Basics: Getting Started with Performance Tuning.pdfDBA Basics: Getting Started with Performance Tuning.pdf
DBA Basics: Getting Started with Performance Tuning.pdfJohn Sterrett
 

Recently uploaded (20)

Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...
Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...
Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...
 
办理学位证纽约大学毕业证(NYU毕业证书)原版一比一
办理学位证纽约大学毕业证(NYU毕业证书)原版一比一办理学位证纽约大学毕业证(NYU毕业证书)原版一比一
办理学位证纽约大学毕业证(NYU毕业证书)原版一比一
 
Customer Service Analytics - Make Sense of All Your Data.pptx
Customer Service Analytics - Make Sense of All Your Data.pptxCustomer Service Analytics - Make Sense of All Your Data.pptx
Customer Service Analytics - Make Sense of All Your Data.pptx
 
Brighton SEO | April 2024 | Data Storytelling
Brighton SEO | April 2024 | Data StorytellingBrighton SEO | April 2024 | Data Storytelling
Brighton SEO | April 2024 | Data Storytelling
 
Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝
 
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service
 
20240419 - Measurecamp Amsterdam - SAM.pdf
20240419 - Measurecamp Amsterdam - SAM.pdf20240419 - Measurecamp Amsterdam - SAM.pdf
20240419 - Measurecamp Amsterdam - SAM.pdf
 
Dubai Call Girls Wifey O52&786472 Call Girls Dubai
Dubai Call Girls Wifey O52&786472 Call Girls DubaiDubai Call Girls Wifey O52&786472 Call Girls Dubai
Dubai Call Girls Wifey O52&786472 Call Girls Dubai
 
Call Girls In Mahipalpur O9654467111 Escorts Service
Call Girls In Mahipalpur O9654467111  Escorts ServiceCall Girls In Mahipalpur O9654467111  Escorts Service
Call Girls In Mahipalpur O9654467111 Escorts Service
 
High Class Call Girls Noida Sector 39 Aarushi 🔝8264348440🔝 Independent Escort...
High Class Call Girls Noida Sector 39 Aarushi 🔝8264348440🔝 Independent Escort...High Class Call Girls Noida Sector 39 Aarushi 🔝8264348440🔝 Independent Escort...
High Class Call Girls Noida Sector 39 Aarushi 🔝8264348440🔝 Independent Escort...
 
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024
 
04242024_CCC TUG_Joins and Relationships
04242024_CCC TUG_Joins and Relationships04242024_CCC TUG_Joins and Relationships
04242024_CCC TUG_Joins and Relationships
 
办理(Vancouver毕业证书)加拿大温哥华岛大学毕业证成绩单原版一比一
办理(Vancouver毕业证书)加拿大温哥华岛大学毕业证成绩单原版一比一办理(Vancouver毕业证书)加拿大温哥华岛大学毕业证成绩单原版一比一
办理(Vancouver毕业证书)加拿大温哥华岛大学毕业证成绩单原版一比一
 
1:1定制(UQ毕业证)昆士兰大学毕业证成绩单修改留信学历认证原版一模一样
1:1定制(UQ毕业证)昆士兰大学毕业证成绩单修改留信学历认证原版一模一样1:1定制(UQ毕业证)昆士兰大学毕业证成绩单修改留信学历认证原版一模一样
1:1定制(UQ毕业证)昆士兰大学毕业证成绩单修改留信学历认证原版一模一样
 
GA4 Without Cookies [Measure Camp AMS]
GA4 Without Cookies [Measure Camp AMS]GA4 Without Cookies [Measure Camp AMS]
GA4 Without Cookies [Measure Camp AMS]
 
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
 
RA-11058_IRR-COMPRESS Do 198 series of 1998
RA-11058_IRR-COMPRESS Do 198 series of 1998RA-11058_IRR-COMPRESS Do 198 series of 1998
RA-11058_IRR-COMPRESS Do 198 series of 1998
 
办理学位证中佛罗里达大学毕业证,UCF成绩单原版一比一
办理学位证中佛罗里达大学毕业证,UCF成绩单原版一比一办理学位证中佛罗里达大学毕业证,UCF成绩单原版一比一
办理学位证中佛罗里达大学毕业证,UCF成绩单原版一比一
 
Amazon TQM (2) Amazon TQM (2)Amazon TQM (2).pptx
Amazon TQM (2) Amazon TQM (2)Amazon TQM (2).pptxAmazon TQM (2) Amazon TQM (2)Amazon TQM (2).pptx
Amazon TQM (2) Amazon TQM (2)Amazon TQM (2).pptx
 
DBA Basics: Getting Started with Performance Tuning.pdf
DBA Basics: Getting Started with Performance Tuning.pdfDBA Basics: Getting Started with Performance Tuning.pdf
DBA Basics: Getting Started with Performance Tuning.pdf
 

Super tickets in pre trained language models

  • 1. Super Tickets in Pre-Trained Language Models: From Model Compression to Improving Generalization Chen Liang, Simiao Zuo, Minshuo Chen , Haoming Jiang, Xiaodong Liu, Pengcheng He, Tuo Zhao, Weizhu Chen
  • 2. Lottery Ticket Hypothesis • A randomly-initialized, dense neural network contains a subnetwork that is initialized such that—when trained in isolation—it can match the test accuracy of the original network after training for at most the same number of iterations.
  • 4. Phase Transition on LTH 1) Phase Transition: The change in the test accuracy of the compressed model 2) Super Ticket: The best value for weight remaining(esp. between Phase1 and Phase2 in this paper ).
  • 5. Contributions • The first to identify the phase transition phenomenon in pruning large neural language models • The first to show that pruning can improve the generalization when the models are lightly compressed • Propose a new pruning approach for multi-task fine-tunning of neural language models
  • 6. Transformer – MultiHeadAttention • Attention • Multi-Head Attention
  • 7. Finding Super Tickets • Prunning of attention heads and feed-forward layers. • Adopt Importance score Low Importance Score: small contribution towards the output High Importance Score: high expressive power for the output
  • 8. Multi-task learning with Tickets Sharing
  • 9. Experiments - Single Task - Baseline: ST-DNN(Base/Large): BERT(Base/Large) with Single Task FFN. - Proposed: SuperT(Base/Large): BERT(Base/Large) with Super Tickets. • Models spec. pruning by 8 different sparsity(e.g. 10% heads/20% FFN) -> choose best! - Optimizer: Adamax - Learning rate: {5e-5, 1e-4, 2e-4} - Batch size: {8, 6, 32} • Compile/Train Options
  • 10. Experiment results on GLUE Benchmarks
  • 11. Experiment results on GLUE Benchmarks In all the tasks, SuperT consistently archieves better generalization than ST-DNN. Performance gain of the super tickets is more Significant in small task. Performance of the super tickets is related to Model size. In large models, more non- expressive tickets can be pruned without Performance degradation.
  • 12. Experiment results on GLUE Benchmarks Single task fine-tunning evaluation results of 1) Super tickets(blue) 2) random(orange) 3) losing tickets(8 different sparsity levels)
  • 13. Experiments – Multi Task Baseline: 1) MT-DNN(Base/Large): BERT(Base/Large) with task shared layers 2) MT-DNN(Base/Large)+ ST Fine-tuning: further trained MT-DNN on individual downstream task • Models -Same as the ones of Single Task. • Compile/Train Options Proposed: 1) Ticket-Share(Base/Large): MT-DNN model refined through the ticket sharing strategy. 2) Ticket-Share(Base/Large)+ ST Fine-tunning: A fine-tuned single-task Ticket-Share model.
  • 15. Experiment results on SNLI/ SciTail
  • 16. Analysis • Sensitivity to Random Seed Training with super tickets effectively reduces model variance on the performance caused by the random initialization. • Tickets Importance Across Tasks SST-2 benefits little from tickets sharing(see Figure6(a)(c)(d)) CoLA (Figure 6(c)), or dominated jointly by two tasks, e.g., CoLA and STS-B (Figure 6(d)) are dominated by a single Task. Thus, some tickets only learn task-specific knowledge, and the two tasks may share certain task-specific knowledge.
  • 17. Discussion • Structured Lottery Tickets • Searching Better Generalized Super Tickets • Searching Super Tickets Efficiently

Editor's Notes

  1. In multi-task learning, the shared model is highly over-parameterized to ensure a sufficient capacity for fitting individual tasks Multi-task model inevitably exhibits task-dependent redundancy when being adapted to individual tasks.