Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userLayer-wise Model Pruning based on Mutual Information
155
0
0.0
(
0
)
Added by
Jiwei Li
Publication date
2021
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
The proposed pruning strategy offers merits over weight-based pruning techniques: (1) it avoids irregular memory access since representations and matrices can be squeezed into their smaller but dense counterparts, leading to greater speedup; (2) in a manner of top-down pruning, the proposed method operates from a more global perspective based on training signals in the top layer, and prunes each layer by propagating the effect of global signals through layers, leading to better performances at the same sparsity level. Extensive experiments show that at the same sparsity level, the proposed strategy offers both greater speedup and higher performances than weight-based pruning methods (e.g., magnitude pruning, movement pruning).
rate research
Read More
With sequentially stacked self-attention, (optional) encoder-decoder attention, and feed-forward layers, Transformer achieves big success in natural language processing (NLP), and many variants have been proposed. Currently, almost all these models assume that the layer order is fixed and kept the same across data samples. We observe that different data samples actually favor different orders of the layers. Based on this observation, in this work, we break the assumption of the fixed layer order in the Transformer and introduce instance-wise layer reordering into the model structure. Our Instance-wise Ordered Transformer (IOT) can model variant functions by reordered layers, which enables each sample to select the better one to improve the model performance under the constraint of almost the same number of parameters. To achieve this, we introduce a light predictor with negligible parameter and inference cost to decide the most capable and favorable layer order for any input sequence. Experiments on 3 tasks (neural machine translation, abstractive summarization, and code generation) and 9 datasets demonstrate consistent improvements of our method. We further show that our method can also be applied to other architectures beyond Transformer. Our code is released at Github.
Generating some appealing questions in open-domain conversations is an effective way to improve human-machine interactions and lead the topic to a broader or deeper direction. To avoid dull or deviated questions, some researchers tried to utilize answer, the future information, to guide question generation. However, they separate a post-question-answer (PQA) triple into two parts: post-question (PQ) and question-answer (QA) pairs, which may hurt the overall coherence. Besides, the QA relationship is modeled as a one-to-one mapping that is not reasonable in open-domain conversations. To tackle these problems, we propose a generative triple-wise model with hierarchical variations for open-domain conversational question generation (CQG). Latent variables in three hierarchies are used to represent the shared background of a triple and one-to-many semantic mappings in both PQ and QA pairs. Experimental results on a large-scale CQG dataset show that our method significantly improves the quality of questions in terms of fluency, coherence and diversity over competitive baselines.
Pre-trained large-scale language models have increasingly demonstrated high accuracy on many natural language processing (NLP) tasks. However, the limited weight storage and computational speed on hardware platforms have impeded the popularity of pre-trained models, especially in the era of edge computing. In this work, we propose an efficient transformer-based large-scale language representation using hardware-friendly block structure pruning. We incorporate the reweighted group Lasso into block-structured pruning for optimization. Besides the significantly reduced weight storage and computation, the proposed approach achieves high compression rates. Experimental results on different models (BERT, RoBERTa, and DistilBERT) on the General Language Understanding Evaluation (GLUE) benchmark tasks show that we achieve up to 5.0x with zero or minor accuracy degradation on certain task(s). Our proposed method is also orthogonal to existing compact pre-trained language models such as DistilBERT using knowledge distillation, since a further 1.79x average compression rate can be achieved on top of DistilBERT with zero or minor accuracy degradation. It is suitable to deploy the final compressed model on resource-constrained edge devices.
Training deep neural networks via federated learning allows clients to share, instead of the original data, only the model trained on their data. Prior work has demonstrated that in practice a clients private information, unrelated to the main learning task, can be discovered from the models gradients, which compromises the promised privacy protection. However, there is still no formal approach for quantifying the leakage of private information via the shared updated model or gradients. In this work, we analyze property inference attacks and define two metrics based on (i) an adaptation of the empirical $mathcal{V}$-information, and (ii) a sensitivity analysis using Jacobian matrices allowing us to measure changes in the gradients with respect to latent information. We show the applicability of our proposed metrics in localizing private latent information in a layer-wise manner and in two settings where (i) we have or (ii) we do not have knowledge of the attackers capabilities. We evaluate the proposed metrics for quantifying information leakage on three real-world datasets using three benchmark models.
In Named Entity Recognition (NER), pre-trained language models have been overestimated by focusing on dataset biases to solve current benchmark datasets. However, these biases hinder generalizability which is necessary to address real-world situations such as weak name regularity and plenty of unseen mentions. To alleviate the use of dataset biases and make the models fully exploit data, we propose a debiasing method that our bias-only model can be replaced with a Pointwise Mutual Information (PMI) to enhance generalization ability while outperforming an in-domain performance. Our approach enables to debias highly correlated word and labels in the benchmark datasets; reflect informative statistics via subword frequency; alleviates a class imbalance between positive and negative examples. For long-named and complex-structure entities, our method can predict these entities through debiasing on conjunction or special characters. Extensive experiments on both general and biomedical domains demonstrate the effectiveness and generalization capabilities of the PMI.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
