arXiv subjects

Xian Li

Publications and source records attributed to Xian Li.

At least 127 records · Page 7Linked to original sources

arXiv2021

An Integrated Optimization-Learning Framework for Online Combinatorial Computation Offloading in MEC Networks

Mobile edge computing (MEC) is a promising paradigm to accommodate the increasingly prosperous delay-sensitive and computation-intensive applications in 5G systems. To achieve optimum computation performance in a dynamic MEC environment, mobile devices often need to make online decisions on whether to offload the computation tasks to nearby edge terminals under the uncertainty of future system information (e.g., random wireless channel gain and task arrivals). The design of an efficient online offloading algorithm is challenging. On one hand, the fast-varying edge environment requires frequently solving a hard combinatorial optimization problem where the integer offloading decision and continuous resource allocation variables are strongly coupled. On the other hand, the uncertainty of future system states makes it hard for the online decisions to satisfy long-term system constraints. To address these challenges, this article overviews the existing methods and introduces a novel framework that efficiently integrates model-based optimization and model-free learning techniques. Besides, we suggest some promising future research directions of online computation offloading control in MEC networks.

cs.IT↗

arXiv2021

Distributionally Robust Multilingual Machine Translation

Multilingual neural machine translation (MNMT) learns to translate multiple language pairs with a single model, potentially improving both the accuracy and the memory-efficiency of deployed models. However, the heavy data imbalance between languages hinders the model from performing uniformly across language pairs. In this paper, we propose a new learning objective for MNMT based on distributionally robust optimization, which minimizes the worst-case expected loss over the set of language pairs. We further show how to practically optimize this objective for large translation corpora using an iterated best response scheme, which is both effective and incurs negligible additional computational cost compared to standard empirical risk minimization. We perform extensive experiments on three sets of languages from two datasets and show that our method consistently outperforms strong baseline methods in terms of average and per-language performance under both many-to-one and one-to-many translation settings.

cs.CL↗

arXiv2021

FST: the FAIR Speech Translation System for the IWSLT21 Multilingual Shared Task

In this paper, we describe our end-to-end multilingual speech translation system submitted to the IWSLT 2021 evaluation campaign on the Multilingual Speech Translation shared task. Our system is built by leveraging transfer learning across modalities, tasks and languages. First, we leverage general-purpose multilingual modules pretrained with large amounts of unlabelled and labelled data. We further enable knowledge transfer from the text task to the speech task by training two tasks jointly. Finally, our multilingual model is finetuned on speech translation task-specific data to achieve the best translation results. Experimental results show our system outperforms the reported systems, including both end-to-end and cascaded based approaches, by a large margin. In some translation directions, our speech translation results evaluated on the public Multilingual TEDx test set are even comparable with the ones from a strong text-to-text translation system, which uses the oracle speech transcripts as input.

cs.CL↗

arXiv2021

Improving Speech Translation by Understanding and Learning from the Auxiliary Text Translation Task

Pretraining and multitask learning are widely used to improve the speech to text translation performance. In this study, we are interested in training a speech to text translation model along with an auxiliary text to text translation task. We conduct a detailed analysis to understand the impact of the auxiliary task on the primary task within the multitask learning framework. Our analysis confirms that multitask learning tends to generate similar decoder representations from different modalities and preserve more information from the pretrained text translation modules. We observe minimal negative transfer effect between the two tasks and sharing more parameters is helpful to transfer knowledge from the text task to the speech task. The analysis also reveals that the modality representation difference at the top decoder layers is still not negligible, and those layers are critical for the translation quality. Inspired by these findings, we propose three methods to improve translation quality. First, a parameter sharing and initialization strategy is proposed to enhance information sharing between the tasks. Second, a novel attention-based regularization is proposed for the encoders and pulls the representations from different modalities closer. Third, an online knowledge distillation is proposed to enhance the knowledge transfer from the text to the speech task. Our experiments show that the proposed approach improves translation performance by more than 2 BLEU over a strong baseline and achieves state-of-the-art results on the \textsc{MuST-C} English-German, English-French and English-Spanish language pairs.

cs.CL↗

arXiv2021

Improving Zero-Shot Translation by Disentangling Positional Information

Multilingual neural machine translation has shown the capability of directly translating between language pairs unseen in training, i.e. zero-shot translation. Despite being conceptually attractive, it often suffers from low output quality. The difficulty of generalizing to new translation directions suggests the model representations are highly specific to those language pairs seen in training. We demonstrate that a main factor causing the language-specific representations is the positional correspondence to input tokens. We show that this can be easily alleviated by removing residual connections in an encoder layer. With this modification, we gain up to 18.5 BLEU points on zero-shot translation while retaining quality on supervised directions. The improvements are particularly prominent between related languages, where our proposed model outperforms pivot-based translation. Moreover, our approach allows easy integration of new languages, which substantially expands translation coverage. By thorough inspections of the hidden layer outputs, we show that our approach indeed leads to more language-independent representations.

cs.CL↗

arXiv2021

Unaware Fairness: Hierarchical Random Forest for Protected Classes

Procedural fairness has been a public concern, which leads to controversy when making decisions with respect to protected classes, such as race, social status, and disability. Some protected classes can be inferred according to some safe proxies like surname and geolocation for the race. Hence, implicitly utilizing the predicted protected classes based on the related proxies when making decisions is an efficient approach to circumvent this issue and seek just decisions. In this article, we propose a hierarchical random forest model for prediction without explicitly involving protected classes. Simulation experiments are conducted to show the performance of the hierarchical random forest model. An example is analyzed from Boston police interview records to illustrate the usefulness of the proposed model.

cs.LG↗

arXiv2021

Online Cognitive Data Sensing and Processing Optimization in Energy-harvesting Edge Computing Systems

Mobile edge computing (MEC) has recently become a prevailing technique to alleviate the intensive computation burden in Internet of Things (IoT) networks. However, the limited device battery capacity and stringent spectrum resource significantly restrict the data processing performance of MEC-enabled IoT networks. To address the two performance limitations, we consider in this paper an MEC-enabled IoT system with an energy harvesting (EH) wireless device (WD) which opportunistically accesses the licensed spectrum of an overlaid primary communication link for task offloading. We aim to maximize the long-term average sensing rate of the WD subject to quality of service (QoS) requirement of primary link, average power constraint of MEC server (MS) and data queue stability of both MS and WD. We formulate the problem as a multi-stage stochastic optimization and propose an online algorithm named PLySE that applies the perturbed Lyapunov optimization technique to decompose the original problem into per-slot deterministic optimization problems. For each per-slot problem, we derive the closed-form optimal solution of data sensing and processing control to facilitate low-complexity real-time implementation. Interestingly, our analysis finds that the optimal solution exhibits an threshold-based structure. Simulation results collaborate with our analysis and demonstrate more than 46.7\% data sensing rate improvement of the proposed PLySE over representative benchmark methods.

cs.IT↗

arXiv2021

Pay Better Attention to Attention: Head Selection in Multilingual and Multi-Domain Sequence Modeling

Multi-head attention has each of the attention heads collect salient information from different parts of an input sequence, making it a powerful mechanism for sequence modeling. Multilingual and multi-domain learning are common scenarios for sequence modeling, where the key challenge is to maximize positive transfer and mitigate negative transfer across languages and domains. In this paper, we find that non-selective attention sharing is sub-optimal for achieving good generalization across all languages and domains. We further propose attention sharing strategies to facilitate parameter sharing and specialization in multilingual and multi-domain sequence modeling. Our approach automatically learns shared and specialized attention heads for different languages and domains to mitigate their interference. Evaluated in various tasks including speech recognition, text-to-text and speech-to-text translation, the proposed attention sharing strategies consistently bring gains to sequence models built upon multi-head attention. For speech-to-text translation, our approach yields an average of $+2.0$ BLEU over $13$ language directions in multilingual setting and $+2.0$ BLEU over $3$ domains in multi-domain setting.

cs.CL↗

arXiv2021

Gender Bias Amplification During Speed-Quality Optimization in Neural Machine Translation

Is bias amplified when neural machine translation (NMT) models are optimized for speed and evaluated on generic test sets using BLEU? We investigate architectures and techniques commonly used to speed up decoding in Transformer-based models, such as greedy search, quantization, average attention networks (AANs) and shallow decoder models and show their effect on gendered noun translation. We construct a new gender bias test set, SimpleGEN, based on gendered noun phrases in which there is a single, unambiguous, correct answer. While we find minimal overall BLEU degradation as we apply speed optimizations, we observe that gendered noun translation performance degrades at a much faster rate.

cs.CL↗

arXiv2021

Insight-HXMT observations of jet-like corona in a black hole X-ray binary MAXI J1820+070

A black hole X-ray binary produces hard X-ray radiation from its corona and disk when the accreting matter heats up. During an outburst, the disk and corona co-evolves with each other. However, such an evolution is still unclear in both its geometry and dynamics. Here we report the unusual decrease of the reflection fraction in MAXI J1820+070, which is the ratio of the coronal intensity illuminating the disk to the coronal intensity reaching the observer, as the corona is observed to contrast during the decay phase. We postulate a jet-like corona model, in which the corona can be understood as a standing shock where the material flowing through. In this dynamical scenario, the decrease of the reflection fraction is a signature of the corona's bulk velocity. Our findings suggest that as the corona is observed to get closer to the black hole, the coronal material might be outflowing faster.

astro-ph.HE↗

arXiv2021

On the Subbagging Estimation for Massive Data

This article introduces subbagging (subsample aggregating) estimation approaches for big data analysis with memory constraints of computers. Specifically, for the whole dataset with size $N$, $m_N$ subsamples are randomly drawn, and each subsample with a subsample size $k_N\ll N$ to meet the memory constraint is sampled uniformly without replacement. Aggregating the estimators of $m_N$ subsamples can lead to subbagging estimation. To analyze the theoretical properties of the subbagging estimator, we adapt the incomplete $U$-statistics theory with an infinite order kernel to allow overlapping drawn subsamples in the sampling procedure. Utilizing this novel theoretical framework, we demonstrate that via a proper hyperparameter selection of $k_N$ and $m_N$, the subbagging estimator can achieve $\sqrt{N}$-consistency and asymptotic normality under the condition $(k_Nm_N)/N\to α\in (0,\infty]$. Compared to the full sample estimator, we theoretically show that the $\sqrt{N}$-consistent subbagging estimator has an inflation rate of $1/α$ in its asymptotic variance. Simulation experiments are presented to demonstrate the finite sample performances. An American airline dataset is analyzed to illustrate that the subbagging estimate is numerically close to the full sample estimate, and can be computationally fast under the memory constraint.

stat.ME↗

arXiv2021

Towards Understanding the Behaviors of Optimal Deep Active Learning Algorithms

Active learning (AL) algorithms may achieve better performance with fewer data because the model guides the data selection process. While many algorithms have been proposed, there is little study on what the optimal AL algorithm looks like, which would help researchers understand where their models fall short and iterate on the design. In this paper, we present a simulated annealing algorithm to search for this optimal oracle and analyze it for several tasks. We present qualitative and quantitative insights into the behaviors of this oracle, comparing and contrasting them with those of various heuristics. Moreover, we are able to consistently improve the heuristics using one particular insight. We hope that our findings can better inform future active learning research. The code is available at https://github.com/YilunZhou/optimal-active-learning.

cs.LG↗

arXiv2021

Multilingual Speech Translation with Efficient Finetuning of Pretrained Models

We present a simple yet effective approach to build multilingual speech-to-text (ST) translation by efficient transfer learning from pretrained speech encoder and text decoder. Our key finding is that a minimalistic LNA (LayerNorm and Attention) finetuning can achieve zero-shot crosslingual and cross-modality transfer ability by only finetuning less than 10% of the pretrained parameters. This enables effectively leveraging large pretrained models with low training cost. Using wav2vec 2.0 for acoustic modeling, and mBART for multilingual text generation, our approach advanced the new state-of-the-art for 34 translation directions (and surpassing cascaded ST for 23 of them) on large-scale multilingual ST benchmark CoVoST 2 (+6.4 BLEU on average across 15 En-X directions and +5.1 BLEU on average across 19 X-En directions). Our approach demonstrates strong zero-shot performance in a many-to-many multilingual model (+5.7 BLEU on average across 18 non-English directions), making it an appealing approach for attaining high-quality speech translation with improved parameter and data efficiency.

cs.CL↗

arXiv2020

Cross-lingual Retrieval for Iterative Self-Supervised Training

Recent studies have demonstrated the cross-lingual alignment ability of multilingual pretrained language models. In this work, we found that the cross-lingual alignment can be further improved by training seq2seq models on sentence pairs mined using their own encoder outputs. We utilized these findings to develop a new approach -- cross-lingual retrieval for iterative self-supervised training (CRISS), where mining and training processes are applied iteratively, improving cross-lingual alignment and translation ability at the same time. Using this method, we achieved state-of-the-art unsupervised machine translation results on 9 language directions with an average improvement of 2.4 BLEU, and on the Tatoeba sentence retrieval task in the XTREME benchmark on 16 languages with an average improvement of 21.5% in absolute accuracy. Furthermore, CRISS also brings an additional 1.8 BLEU improvement on average compared to mBART, when finetuned on supervised machine translation downstream tasks.

cs.CL↗

arXiv2020

DeFuzz: Deep Learning Guided Directed Fuzzing

Fuzzing is one of the most effective technique to identify potential software vulnerabilities. Most of the fuzzers aim to improve the code coverage, and there is lack of directedness (e.g., fuzz the specified path in a software). In this paper, we proposed a deep learning (DL) guided directed fuzzing for software vulnerability detection, named DeFuzz. DeFuzz includes two main schemes: (1) we employ a pre-trained DL prediction model to identify the potentially vulnerable functions and the locations (i.e., vulnerable addresses). Precisely, we employ Bidirectional-LSTM (BiLSTM) to identify attention words, and the vulnerabilities are associated with these attention words in functions. (2) then we employ directly fuzzing to fuzz the potential vulnerabilities by generating inputs that tend to arrive the predicted locations. To evaluate the effectiveness and practical of the proposed DeFuzz technique, we have conducted experiments on real-world data sets. Experimental results show that our DeFuzz can discover coverage more and faster than AFL. Moreover, DeFuzz exposes 43 more bugs than AFL on real-world applications.

cs.CR↗

arXiv2020

Deep Transformers with Latent Depth

The Transformer model has achieved state-of-the-art performance in many sequence modeling tasks. However, how to leverage model capacity with large or variable depths is still an open challenge. We present a probabilistic framework to automatically learn which layer(s) to use by learning the posterior distributions of layer selection. As an extension of this framework, we propose a novel method to train one shared Transformer network for multilingual machine translation with different layer selection posteriors for each language pair. The proposed method alleviates the vanishing gradient issue and enables stable training of deep Transformers (e.g. 100 layers). We evaluate on WMT English-German machine translation and masked language modeling tasks, where our method outperforms existing approaches for training deeper Transformers. Experiments on multilingual machine translation demonstrate that this approach can effectively leverage increased model capacity and bring universal improvement for both many-to-one and one-to-many translation with diverse language pairs.

cs.CL↗

arXiv2020

Nonlinear rotational spectroscopy reveals many-body interactions in water molecules

Because of their central importance in chemistry and biology, water molecules have been the subject of decades of intense spectroscopic investigations. Rotational spectroscopy of water vapor has yielded detailed information about the structure and dynamics of isolated water molecules as well as water dimers and clusters. Nonlinear rotational spectroscopy in the terahertz regime has been developed recently to investigate the rotational dynamics of linear and symmetric-top molecules whose rotational energy levels are regularly spaced, but it has not previously been applied to water or other lower-symmetry molecules with irregularly spaced levels. We report the use of recently developed two-dimensional terahertz rotational spectroscopy to observe high-order rotational coherences and correlations between rotational transitions that could not be observed previously. The results include two-quantum (2Q) peaks at frequencies that are shifted slightly from the sums of distinct rotational transitions on two molecules, which directly reveal the presence of previously unseen metastable water complexes with lifetimes of 100 ps or longer. Several such peaks observed at distinct 2Q frequencies indicate that the complexes have multiple preferred bimolecular geometries. Our results demonstrate sensitivity of rotational correlations measured in 2D THz spectroscopy to molecular interactions and complexation in the gas phase.

physics.chem-ph↗

arXiv2020

Timing analysis of the black hole candidate EXO 1846-031 with Insight-HXMT monitoring

We present the observational results from a detailed timing analysis of the black hole candidate EXO 1846-031 during its outburst in 2019 with the observations of Insight-HXMT, NICER and MAXI. This outburst can be classfied roughly into four different states. Type-C quasi-periodic oscillations (QPOs) observed by NICER (about 0.1-6Hz) and Insight-HXMT (about 0.7-8Hz) are also reported in this work. Meanwhile, we study various physical quantities related to QPO frequency.The QPO rms-frequency relationship in three energy band 1-10 keV indicates that there is a turning pointing in frequency around 2 Hz,which is similar to that of GRS 1915+105. A possible hypothesis for the relationship above may be related to the inclination of the source, which may require a high inclination to explain it. The relationships between QPO frequency and QPO rms,hardness,total fractional rms and count rate have also been found in other transient sources, which can indicate that the origin of type-C QPOs is non-thermal.

astro-ph.HE↗