arXiv subjects

Di He

Publications and source records attributed to Di He.

At least 109 records · Page 6Linked to original sources

arXiv2021

How could Neural Networks understand Programs?

Semantic understanding of programs is a fundamental problem for programming language processing (PLP). Recent works that learn representations of code based on pre-training techniques in NLP have pushed the frontiers in this direction. However, the semantics of PL and NL have essential differences. These being ignored, we believe it is difficult to build a model to better understand programs, by either directly applying off-the-shelf NLP pre-training techniques to the source code, or adding features to the model by the heuristic. In fact, the semantics of a program can be rigorously defined by formal semantics in PL theory. For example, the operational semantics, describes the meaning of a valid program as updating the environment (i.e., the memory address-value function) through fundamental operations, such as memory I/O and conditional branching. Inspired by this, we propose a novel program semantics learning paradigm, that the model should learn from information composed of (1) the representations which align well with the fundamental operations in operational semantics, and (2) the information of environment transition, which is indispensable for program understanding. To validate our proposal, we present a hierarchical Transformer-based pre-training model called OSCAR to better facilitate the understanding of programs. OSCAR learns from intermediate representation (IR) and an encoded representation derived from static analysis, which are used for representing the fundamental operations and approximating the environment transitions respectively. OSCAR empirically shows the outstanding capability of program semantics understanding on many practical software engineering tasks.

cs.PL↗

arXiv2021

Rethinking Positional Encoding in Language Pre-training

In this work, we investigate the positional encoding methods used in language pre-training (e.g., BERT) and identify several problems in the existing formulations. First, we show that in the absolute positional encoding, the addition operation applied on positional embeddings and word embeddings brings mixed correlations between the two heterogeneous information resources. It may bring unnecessary randomness in the attention and further limit the expressiveness of the model. Second, we question whether treating the position of the symbol \texttt{[CLS]} the same as other words is a reasonable design, considering its special role (the representation of the entire sentence) in the downstream tasks. Motivated from above analysis, we propose a new positional encoding method called \textbf{T}ransformer with \textbf{U}ntied \textbf{P}ositional \textbf{E}ncoding (TUPE). In the self-attention module, TUPE computes the word contextual correlation and positional correlation separately with different parameterizations and then adds them together. This design removes the mixed and noisy correlations over heterogeneous embeddings and offers more expressiveness by using different projection matrices. Furthermore, TUPE unties the \texttt{[CLS]} symbol from other positions, making it easier to capture information from all positions. Extensive experiments and ablation studies on GLUE benchmark demonstrate the effectiveness of the proposed method. Codes and models are released at https://github.com/guolinke/TUPE.

cs.CL↗

arXiv2021

Taking Notes on the Fly Helps BERT Pre-training

How to make unsupervised language pre-training more efficient and less resource-intensive is an important research direction in NLP. In this paper, we focus on improving the efficiency of language pre-training methods through providing better data utilization. It is well-known that in language data corpus, words follow a heavy-tail distribution. A large proportion of words appear only very few times and the embeddings of rare words are usually poorly optimized. We argue that such embeddings carry inadequate semantic signals, which could make the data utilization inefficient and slow down the pre-training of the entire model. To mitigate this problem, we propose Taking Notes on the Fly (TNF), which takes notes for rare words on the fly during pre-training to help the model understand them when they occur next time. Specifically, TNF maintains a note dictionary and saves a rare word's contextual information in it as notes when the rare word occurs in a sentence. When the same rare word occurs again during training, the note information saved beforehand can be employed to enhance the semantics of the current sentence. By doing so, TNF provides better data utilization since cross-sentence information is employed to cover the inadequate semantics caused by rare words in the sentences. We implement TNF on both BERT and ELECTRA to check its efficiency and effectiveness. Experimental results show that TNF's training time is $60\%$ less than its backbone pre-training models when reaching the same performance. When trained with the same number of iterations, TNF outperforms its backbone methods on most of downstream tasks and the average GLUE score. Source code is attached in the supplementary material.

cs.CL↗

arXiv2021

Transformers with Competitive Ensembles of Independent Mechanisms

An important development in deep learning from the earliest MLPs has been a move towards architectures with structural inductive biases which enable the model to keep distinct sources of information and routes of processing well-separated. This structure is linked to the notion of independent mechanisms from the causality literature, in which a mechanism is able to retain the same processing as irrelevant aspects of the world are changed. For example, convnets enable separation over positions, while attention-based architectures (especially Transformers) learn which combination of positions to process dynamically. In this work we explore a way in which the Transformer architecture is deficient: it represents each position with a large monolithic hidden representation and a single set of parameters which are applied over the entire hidden representation. This potentially throws unrelated sources of information together, and limits the Transformer's ability to capture independent mechanisms. To address this, we propose Transformers with Independent Mechanisms (TIM), a new Transformer layer which divides the hidden representation and parameters into multiple mechanisms, which only exchange information through attention. Additionally, we propose a competition mechanism which encourages these mechanisms to specialize over time steps, and thus be more independent. We study TIM on a large-scale BERT model, on the Image Transformer, and on speech enhancement and find evidence for semantically meaningful specialization as well as improved performance.

cs.LG↗

arXiv2021

LazyFormer: Self Attention with Lazy Update

Improving the efficiency of Transformer-based language pre-training is an important task in NLP, especially for the self-attention module, which is computationally expensive. In this paper, we propose a simple but effective solution, called \emph{LazyFormer}, which computes the self-attention distribution infrequently. LazyFormer composes of multiple lazy blocks, each of which contains multiple Transformer layers. In each lazy block, the self-attention distribution is only computed once in the first layer and then is reused in all upper layers. In this way, the cost of computation could be largely saved. We also provide several training tricks for LazyFormer. Extensive experiments demonstrate the effectiveness of the proposed method.

cs.CL↗

arXiv2021

Revisiting Language Encoding in Learning Multilingual Representations

Transformer has demonstrated its great power to learn contextual word representations for multiple languages in a single model. To process multilingual sentences in the model, a learnable vector is usually assigned to each language, which is called "language embedding". The language embedding can be either added to the word embedding or attached at the beginning of the sentence. It serves as a language-specific signal for the Transformer to capture contextual representations across languages. In this paper, we revisit the use of language embedding and identify several problems in the existing formulations. By investigating the interaction between language embedding and word embedding in the self-attention module, we find that the current methods cannot reflect the language-specific word correlation well. Given these findings, we propose a new approach called Cross-lingual Language Projection (XLP) to replace language embedding. For a sentence, XLP projects the word embeddings into language-specific semantic space, and then the projected embeddings will be fed into the Transformer model to process with their language-specific meanings. In such a way, XLP achieves the purpose of appropriately encoding "language" in a multilingual Transformer model. Experimental results show that XLP can freely and significantly boost the model performance on extensive multilingual benchmark datasets. Codes and models will be released at https://github.com/lsj2408/XLP.

cs.CL↗

arXiv2021

CODE-AE: A Coherent De-confounding Autoencoder for Predicting Patient-Specific Drug Response From Cell Line Transcriptomics

Accurate and robust prediction of patient's response to drug treatments is critical for developing precision medicine. However, it is often difficult to obtain a sufficient amount of coherent drug response data from patients directly for training a generalized machine learning model. Although the utilization of rich cell line data provides an alternative solution, it is challenging to transfer the knowledge obtained from cell lines to patients due to various confounding factors. Few existing transfer learning methods can reliably disentangle common intrinsic biological signals from confounding factors in the cell line and patient data. In this paper, we develop a Coherent Deconfounding Autoencoder (CODE-AE) that can extract both common biological signals shared by incoherent samples and private representations unique to each data set, transfer knowledge learned from cell line data to tissue data, and separate confounding factors from them. Extensive studies on multiple data sets demonstrate that CODE-AE significantly improves the accuracy and robustness over state-of-the-art methods in both predicting patient drug response and de-confounding biological signals. Thus, CODE-AE provides a useful framework to take advantage of in vitro omics data for developing generalized patient predictive models. The source code is available at https://github.com/XieResearchGroup/CODE-AE.

cs.LG↗

arXiv2021

A new approach to the thermodynamic analysis of gas power cycles

Engineering Thermodynamics has been the core course of many science and engineering majors around the world, including energy and power, mechanical engineering, civil engineering, aerospace, cryogenic refrigeration, food engineering, chemical engineering, and environmental engineering, among which gas power cycle is one of the important contents. However, many Engineering Thermodynamics textbooks focus only on evaluating the thermal efficiency of gas power cycle, while the important concept of specific cycle work is ignored. Based on the generalized temperature-entropy diagram for the gas power cycles proposed by the authors, an ideal Otto cycle and an ideal Miller-Diesel cycle are taking as examples for the thermodynamic analyses of gas power cycles. The optimum compression ratio (or the pressure ratio) for the maximum specific cycle work or the maximum mean effective pressure is analyzed and determined. The ideal Otto and the ideal Miller-Diesel cycles, and also other gas power cycles for movable applications, are concluded that the operation under the maximum specific cycle work or the maximum mean effective pressure, instead of under the higher efficiency, is more economic and more reasonable. We concluded that the very important concept, i.e., the optimum compression (or pressure) ratio for the gas power cycles, should be emphasized in the Engineering Thermodynamics teaching process and in the latter revised or the newly edited textbooks, in order to better guide the engineering applications.

physics.ed-ph↗

arXiv2020

A Cross-Level Information Transmission Network for Predicting Phenotype from New Genotype: Application to Cancer Precision Medicine

An unsolved fundamental problem in biology and ecology is to predict observable traits (phenotypes) from a new genetic constitution (genotype) of an organism under environmental perturbations (e.g., drug treatment). The emergence of multiple omics data provides new opportunities but imposes great challenges in the predictive modeling of genotype-phenotype associations. Firstly, the high-dimensionality of genomics data and the lack of labeled data often make the existing supervised learning techniques less successful. Secondly, it is a challenging task to integrate heterogeneous omics data from different resources. Finally, the information transmission from DNA to phenotype involves multiple intermediate levels of RNA, protein, metabolite, etc. The higher-level features (e.g., gene expression) usually have stronger discriminative power than the lower level features (e.g., somatic mutation). To address above issues, we proposed a novel Cross-LEvel Information Transmission network (CLEIT) framework. CLEIT aims to explicitly model the asymmetrical multi-level organization of the biological system. Inspired by domain adaptation, CLEIT first learns the latent representation of high-level domain then uses it as ground-truth embedding to improve the representation learning of the low-level domain in the form of contrastive loss. In addition, we adopt a pre-training-fine-tuning approach to leveraging the unlabeled heterogeneous omics data to improve the generalizability of CLEIT. We demonstrate the effectiveness and performance boost of CLEIT in predicting anti-cancer drug sensitivity from somatic mutations via the assistance of gene expressions when compared with state-of-the-art methods.

cs.LG↗

arXiv2020

Transferred Discrepancy: Quantifying the Difference Between Representations

Understanding what information neural networks capture is an essential problem in deep learning, and studying whether different models capture similar features is an initial step to achieve this goal. Previous works sought to define metrics over the feature matrices to measure the difference between two models. However, different metrics sometimes lead to contradictory conclusions, and there has been no consensus on which metric is suitable to use in practice. In this work, we propose a novel metric that goes beyond previous approaches. Recall that one of the most practical scenarios of using the learned representations is to apply them to downstream tasks. We argue that we should design the metric based on a similar principle. For that, we introduce the transferred discrepancy (TD), a new metric that defines the difference between two representations based on their downstream-task performance. Through an asymptotic analysis, we show how TD correlates with downstream tasks and the necessity to define metrics in such a task-dependent fashion. In particular, we also show that under specific conditions, the TD metric is closely related to previous metrics. Our experiments show that TD can provide fine-grained information for varied downstream tasks, and for the models trained from different initializations, the learned features are not the same in terms of downstream-task predictions. We find that TD may also be used to evaluate the effectiveness of different training strategies. For example, we demonstrate that the models trained with proper data augmentations that improve the generalization capture more similar features in terms of TD, while those with data augmentations that hurt the generalization will not. This suggests a training strategy that leads to more robust representation also trains models that generalize better.

cs.LG↗

arXiv2020

On Layer Normalization in the Transformer Architecture

The Transformer is widely used in natural language processing tasks. To train a Transformer however, one usually needs a carefully designed learning rate warm-up stage, which is shown to be crucial to the final performance but will slow down the optimization and bring more hyper-parameter tunings. In this paper, we first study theoretically why the learning rate warm-up stage is essential and show that the location of layer normalization matters. Specifically, we prove with mean field theory that at initialization, for the original-designed Post-LN Transformer, which places the layer normalization between the residual blocks, the expected gradients of the parameters near the output layer are large. Therefore, using a large learning rate on those gradients makes the training unstable. The warm-up stage is practically helpful for avoiding this problem. On the other hand, our theory also shows that if the layer normalization is put inside the residual blocks (recently proposed as Pre-LN Transformer), the gradients are well-behaved at initialization. This motivates us to remove the warm-up stage for the training of Pre-LN Transformers. We show in our experiments that Pre-LN Transformers without the warm-up stage can reach comparable results with baselines while requiring significantly less training time and hyper-parameter tuning on a wide range of applications.

cs.LG↗

arXiv2020

MC-BERT: Efficient Language Pre-Training via a Meta Controller

Pre-trained contextual representations (e.g., BERT) have become the foundation to achieve state-of-the-art results on many NLP tasks. However, large-scale pre-training is computationally expensive. ELECTRA, an early attempt to accelerate pre-training, trains a discriminative model that predicts whether each input token was replaced by a generator. Our studies reveal that ELECTRA's success is mainly due to its reduced complexity of the pre-training task: the binary classification (replaced token detection) is more efficient to learn than the generation task (masked language modeling). However, such a simplified task is less semantically informative. To achieve better efficiency and effectiveness, we propose a novel meta-learning framework, MC-BERT. The pre-training task is a multi-choice cloze test with a reject option, where a meta controller network provides training input and candidates. Results over GLUE natural language understanding benchmark demonstrate that our proposed method is both efficient and effective: it outperforms baselines on GLUE semantic tasks given the same computational budget.

cs.CL↗

arXiv2020

Invertible Image Rescaling

High-resolution digital images are usually downscaled to fit various display screens or save the cost of storage and bandwidth, meanwhile the post-upscaling is adpoted to recover the original resolutions or the details in the zoom-in images. However, typical image downscaling is a non-injective mapping due to the loss of high-frequency information, which leads to the ill-posed problem of the inverse upscaling procedure and poses great challenges for recovering details from the downscaled low-resolution images. Simply upscaling with image super-resolution methods results in unsatisfactory recovering performance. In this work, we propose to solve this problem by modeling the downscaling and upscaling processes from a new perspective, i.e. an invertible bijective transformation, which can largely mitigate the ill-posed nature of image upscaling. We develop an Invertible Rescaling Net (IRN) with deliberately designed framework and objectives to produce visually-pleasing low-resolution images and meanwhile capture the distribution of the lost information using a latent variable following a specified distribution in the downscaling process. In this way, upscaling is made tractable by inversely passing a randomly-drawn latent variable with the low-resolution image through the network. Experimental results demonstrate the significant improvement of our model over existing methods in terms of both quantitative and qualitative evaluations of image upscaling reconstruction from downscaled images.

eess.IV↗

arXiv2020

FRAGE: Frequency-Agnostic Word Representation

Continuous word representation (aka word embedding) is a basic building block in many neural network-based models used in natural language processing tasks. Although it is widely accepted that words with similar semantics should be close to each other in the embedding space, we find that word embeddings learned in several tasks are biased towards word frequency: the embeddings of high-frequency and low-frequency words lie in different subregions of the embedding space, and the embedding of a rare word and a popular word can be far from each other even if they are semantically similar. This makes learned word embeddings ineffective, especially for rare words, and consequently limits the performance of these neural network models. In this paper, we develop a neat, simple yet effective way to learn \emph{FRequency-AGnostic word Embedding} (FRAGE) using adversarial training. We conducted comprehensive studies on ten datasets across four natural language processing tasks, including word similarity, language modeling, machine translation and text classification. Results show that with FRAGE, we achieve higher performance than the baselines in all tasks.

cs.CL↗

arXiv2020

Incorporating BERT into Neural Machine Translation

The recently proposed BERT has shown great power on a variety of natural language understanding tasks, such as text classification, reading comprehension, etc. However, how to effectively apply BERT to neural machine translation (NMT) lacks enough exploration. While BERT is more commonly used as fine-tuning instead of contextual embedding for downstream language understanding tasks, in NMT, our preliminary exploration of using BERT as contextual embedding is better than using for fine-tuning. This motivates us to think how to better leverage BERT for NMT along this direction. We propose a new algorithm named BERT-fused model, in which we first use BERT to extract representations for an input sequence, and then the representations are fused with each layer of the encoder and decoder of the NMT model through attention mechanisms. We conduct experiments on supervised (including sentence-level and document-level translations), semi-supervised and unsupervised machine translation, and achieve state-of-the-art results on seven benchmark datasets. Our code is available at \url{https://github.com/bert-nmt/bert-nmt}.

cs.CL↗

arXiv2020

Fast Structured Decoding for Sequence Models

Autoregressive sequence models achieve state-of-the-art performance in domains like machine translation. However, due to the autoregressive factorization nature, these models suffer from heavy latency during inference. Recently, non-autoregressive sequence models were proposed to reduce the inference time. However, these models assume that the decoding process of each token is conditionally independent of others. Such a generation process sometimes makes the output sentence inconsistent, and thus the learned non-autoregressive models could only achieve inferior accuracy compared to their autoregressive counterparts. To improve then decoding consistency and reduce the inference cost at the same time, we propose to incorporate a structured inference module into the non-autoregressive models. Specifically, we design an efficient approximation for Conditional Random Fields (CRF) for non-autoregressive sequence models, and further propose a dynamic transition technique to model positional contexts in the CRF. Experiments in machine translation show that while increasing little latency (8~14ms), our model could achieve significantly better translation performance than previous non-autoregressive models on different translation datasets. In particular, for the WMT14 En-De dataset, our model obtains a BLEU score of 26.80, which largely outperforms the previous non-autoregressive baselines and is only 0.61 lower in BLEU than purely autoregressive models.

cs.LG↗

arXiv2019

Discussions of gas power cycle performance analysis method in the course of Engineering Thermodynamics

Engineering Thermodynamics has been the core course of many science and engineering majors at home and abroad, including energy and power, mechanical engineering, civil engineering, aerospace, cryogenic refrigeration, food engineering, chemical engineering, and environmental engineering, among which gas power cycle is one of the important contents. However, many Engineering Thermodynamics textbooks at home and abroad focus only on evaluating the thermal efficiency of gas power cycle, while the important concept of specific cycle net work is ignored. Taking an ideal Otto cycle and an ideal Brayton as examples, the optimum compression ratio (or the pressure ratio) and the maximum specific cycle net work are analyzed and determined. The ideal Otto and the ideal Brayton cycles, and also other gas power cycles, are concluded that the operation under the optimum compression/pressure ratio of the engine, instead of under the higher efficiency, is more economic and more reasonable. We concluded that the two very important concepts, i.e., the maximum specific cycle net work and the optimum compression (or pressure) ratio for the gas power cycles, should be emphasized in the Engineering Thermodynamics teaching process and the latter revised or the newly edited textbooks, in order to better guide the engineering applications. In the end, general T-s diagram is proposed for the gas power cycles.

physics.ed-ph↗

arXiv2019

On the Anomalous Generalization of GANs

Generative models, especially Generative Adversarial Networks (GANs), have received significant attention recently. However, it has been observed that in terms of some attributes, e.g. the number of simple geometric primitives in an image, GANs are not able to learn the target distribution in practice. Motivated by this observation, we discover two specific problems of GANs leading to anomalous generalization behaviour, which we refer to as the sample insufficiency and the pixel-wise combination. For the first problem of sample insufficiency, we show theoretically and empirically that the batchsize of the training samples in practice may be insufficient for the discriminator to learn an accurate discrimination function. It could result in unstable training dynamics for the generator, leading to anomalous generalization. For the second problem of pixel-wise combination, we find that besides recognizing the positive training samples as real, under certain circumstances, the discriminator could be fooled to recognize the pixel-wise combinations (e.g. pixel-wise average) of the positive training samples as real. However, those combinations could be visually different from the real samples in the target distribution. With the fooled discriminator as reference, the generator would obtain biased supervision further, leading to the anomalous generalization behaviour. Additionally, in this paper, we propose methods to mitigate the anomalous generalization of GANs. Extensive experiments on benchmark show our proposed methods improve the FID score up to 30\% on natural image dataset.

cs.LG↗