arXiv subjects

Jian Yu

Publications and source records attributed to Jian Yu.

At least 55 records · Page 3Linked to original sources

arXiv2022

Nextformer: A ConvNeXt Augmented Conformer For End-To-End Speech Recognition

Conformer models have achieved state-of-the-art(SOTA) results in end-to-end speech recognition. However Conformer mainly focuses on temporal modeling while pays less attention on time-frequency property of speech feature. In this paper we augment Conformer with ConvNeXt and propose Nextformer structure. We use stacks of ConvNeXt block to replace the commonly used subsampling module in Conformer for utilizing the information contained in time-frequency speech feature. Besides, we insert an additional downsampling module in middle of Conformer layers to make our model more efficient and accurate. We conduct experiments on two opening datasets, AISHELL-1 and WenetSpeech. On AISHELL-1, compared to Conformer baselines, Nextformer obtains 7.3% and 6.3% relative CER reduction in non-streaming and streaming mode respectively, and on a much larger WenetSpeech dataset, Nextformer gives 5.0%~6.5% and 7.5%~14.6% relative CER reduction in non-streaming and streaming mode, while keep the computational cost FLOPs comparable to Conformer. To the best of our knowledge, the proposed Nextformer model achieves SOTA results on AISHELL-1(CER 4.06%) and WenetSpeech(CER 7.56%/11.29%).

eess.AS↗

arXiv2022

Deep Embedded Clustering with Distribution Consistency Preservation for Attributed Networks

Many complex systems in the real world can be characterized by attributed networks. To mine the potential information in these networks, deep embedded clustering, which obtains node representations and clusters simultaneously, has been paid much attention in recent years. Under the assumption of consistency for data in different views, the cluster structure of network topology and that of node attributes should be consistent for an attributed network. However, many existing methods ignore this property, even though they separately encode node representations from network topology and node attributes meanwhile clustering nodes on representation vectors learnt from one of the views. Therefore, in this study, we propose an end-to-end deep embedded clustering model for attributed networks. It utilizes graph autoencoder and node attribute autoencoder to respectively learn node representations and cluster assignments. In addition, a distribution consistency constraint is introduced to maintain the latent consistency of cluster distributions of two views. Extensive experiments on several datasets demonstrate that the proposed model achieves significantly better or competitive performance compared with the state-of-the-art methods. The source code can be found at https://github.com/Zhengymm/DCP.

cs.LG↗

arXiv2021

Homogeneous and Heterogeneous Relational Graph for Visible-infrared Person Re-identification

Visible-infrared person re-identification (VI Re-ID) aims to match person images between the visible and infrared modalities. Existing VI Re-ID methods mainly focus on extracting homogeneous structural relationships in an image, i.e. the relations between local features, while ignoring the heterogeneous correlation of local features in different modalities. The heterogeneous structured relationship is crucial to learn effective identity representations and perform cross-modality matching. In this paper, we model the homogenous structural relationship by a modality-specific graph within individual modality and then mine the heterogeneous structural correlation with the modality-specific graph of visible and infrared modality. First, the homogeneous structured graph (HOSG) mines one-vs.-rest relation between an arbitrary node (local feature) and all the rest nodes within a visible or infrared image to learn effective identity representation. Second, to find cross-modality identity-consistent correspondence, the heterogeneous graph alignment module (HGAM) further measures the relational edge strength between local node features of two modalities with routing search way. Third, we propose the cross-modality cross-correlation (CMCC) loss to extract the modality invariance of feature representations of visible and infrared graphs. CMCC computes the mutual information between modalities and expels semantic redundancy. Extensive experiments on SYSU-MM01 and RegDB datasets demonstrate that our method outperforms state-of-the-arts with a gain of 13.73\% and 9.45\% Rank1/mAP. The code is available at https://github.com/fegnyujian/Homogeneous-and-Heterogeneous-Relational-Graph.

cs.CV↗

arXiv2021

FGraDA: A Dataset and Benchmark for Fine-Grained Domain Adaptation in Machine Translation

Previous research for adapting a general neural machine translation (NMT) model into a specific domain usually neglects the diversity in translation within the same domain, which is a core problem for domain adaptation in real-world scenarios. One representative of such challenging scenarios is to deploy a translation system for a conference with a specific topic, e.g., global warming or coronavirus, where there are usually extremely less resources due to the limited schedule. To motivate wider investigation in such a scenario, we present a real-world fine-grained domain adaptation task in machine translation (FGraDA). The FGraDA dataset consists of Chinese-English translation task for four sub-domains of information technology: autonomous vehicles, AI education, real-time networks, and smart phone. Each sub-domain is equipped with a development set and test set for evaluation purposes. To be closer to reality, FGraDA does not employ any in-domain bilingual training data but provides bilingual dictionaries and wiki knowledge base, which can be easier obtained within a short time. We benchmark the fine-grained domain adaptation task and present in-depth analyses showing that there are still challenging problems to further improve the performance with heterogeneous resources.

cs.CL↗

arXiv2021

Learning to Learn a Cold-start Sequential Recommender

The cold-start recommendation is an urgent problem in contemporary online applications. It aims to provide users whose behaviors are literally sparse with as accurate recommendations as possible. Many data-driven algorithms, such as the widely used matrix factorization, underperform because of data sparseness. This work adopts the idea of meta-learning to solve the user's cold-start recommendation problem. We propose a meta-learning based cold-start sequential recommendation framework called metaCSR, including three main components: Diffusion Representer for learning better user/item embedding through information diffusion on the interaction graph; Sequential Recommender for capturing temporal dependencies of behavior sequences; Meta Learner for extracting and propagating transferable knowledge of prior users and learning a good initialization for new users. metaCSR holds the ability to learn the common patterns from regular users' behaviors and optimize the initialization so that the model can quickly adapt to new users after one or a few gradient updates to achieve optimal performance. The extensive quantitative experiments on three widely-used datasets show the remarkable performance of metaCSR in dealing with user cold-start problem. Meanwhile, a series of qualitative analysis demonstrates that the proposed metaCSR has good generalization.

cs.IR↗

arXiv2021

Knowledge Graph-enhanced Sampling for Conversational Recommender System

The traditional recommendation systems mainly use offline user data to train offline models, and then recommend items for online users, thus suffering from the unreliable estimation of user preferences based on sparse and noisy historical data. Conversational Recommendation System (CRS) uses the interactive form of the dialogue systems to solve the intrinsic problems of traditional recommendation systems. However, due to the lack of contextual information modeling, the existing CRS models are unable to deal with the exploitation and exploration (E&E) problem well, resulting in the heavy burden on users. To address the aforementioned issue, this work proposes a contextual information enhancement model tailored for CRS, called Knowledge Graph-enhanced Sampling (KGenSam). KGenSam integrates the dynamic graph of user interaction data with the external knowledge into one heterogeneous Knowledge Graph (KG) as the contextual information environment. Then, two samplers are designed to enhance knowledge by sampling fuzzy samples with high uncertainty for obtaining user preferences and reliable negative samples for updating recommender to achieve efficient acquisition of user preferences and model updating, and thus provide a powerful solution for CRS to deal with E&E problem. Experimental results on two real-world datasets demonstrate the superiority of KGenSam with significant improvements over state-of-the-art methods.

cs.IR↗

arXiv2021

Abnormal Staebler-Wronski effect of amorphous silicon

Great achievements in last five years, such as record-efficient amorphous/crystalline silicon heterojunction (SHJ) solar cells and cutting-edge perovskite/SHJ tandem solar cells, place hydrogenated amorphous silicon (a-Si:H) at the forefront of emerging photovoltaics. Due to the extremely low doping efficiency of trivalent boron (B) in amorphous tetravalent silicon, light harvesting of aforementioned devices are limited by their fill factors (FF), which is a direct metric of the charge carrier transport. It is challenging but crucial to develop highly conductive doped a-Si:H for minimizing the FF losses. Here we report intensive light soaking can efficiently boost the dark conductance of B-doped a-Si:H "thin" films, which is an abnormal Staebler-Wronski effect. By implementing this abnormal effect to SHJ solar cells, we achieve a certificated power conversion efficiency (PCE) of 25.18% (26.05% on designated area) with FF of 85.42% on a 244.63-cm2 wafer. This PCE is one of the highest reported values for total-area "top/rear" contact silicon solar cells. The FF reaches 98.30 per cent of its Shockley-Queisser limit.

physics.app-ph↗

arXiv2021

Comparative Analysis of Machine Learning Approaches to Analyze and Predict the Covid-19 Outbreak

Background. Forecasting the time of forthcoming pandemic reduces the impact of diseases by taking precautionary steps such as public health messaging and raising the consciousness of doctors. With the continuous and rapid increase in the cumulative incidence of COVID-19, statistical and outbreak prediction models including various machine learning (ML) models are being used by the research community to track and predict the trend of the epidemic, and also in developing appropriate strategies to combat and manage its spread. Methods. In this paper, we present a comparative analysis of various ML approaches including Support Vector Machine, Random Forest, K-Nearest Neighbor and Artificial Neural Network in predicting the COVID-19 outbreak in the epidemiological domain. We first apply the autoregressive distributed lag (ARDL) method to identify and model the short and long-run relationships of the time-series COVID-19 datasets. That is, we determine the lags between a response variable and its respective explanatory time series variables as independent variables. Then, the resulting significant variables concerning their lags are used in the regression model selected by the ARDL for predicting and forecasting the trend of the epidemic. Results. Statistical measures i.e., Root Mean Square Error (RMSE), Mean Absolute Error (MAE) and Mean Absolute Percentage Error (MAPE) are used for model accuracy. The values of MAPE for the best selected models for confirmed, recovered and deaths cases are 0.407, 0.094 and 0.124 respectively, which falls under the category of highly accurate forecasts. In addition, we computed fifteen days ahead forecast for the daily deaths, recover, and confirm patients and the cases fluctuated across time in all aspects. Besides, the results reveal the advantages of ML algorithms for supporting decision making of evolving short term policies.

stat.ML↗

arXiv2020

Learning Contextualized Sentence Representations for Document-Level Neural Machine Translation

Document-level machine translation incorporates inter-sentential dependencies into the translation of a source sentence. In this paper, we propose a new framework to model cross-sentence dependencies by training neural machine translation (NMT) to predict both the target translation and surrounding sentences of a source sentence. By enforcing the NMT model to predict source context, we want the model to learn "contextualized" source sentence representations that capture document-level dependencies on the source side. We further propose two different methods to learn and integrate such contextualized sentence embeddings into NMT: a joint training method that jointly trains an NMT model with the source context prediction model and a pre-training & fine-tuning method that pretrains the source context prediction model on a large-scale monolingual document corpus and then fine-tunes it with the NMT model. Experiments on Chinese-English and English-German translation show that both methods can substantially improve the translation quality over a strong document-level Transformer baseline.

cs.CL↗

arXiv2019

A Generalization Theory based on Independent and Task-Identically Distributed Assumption

Existing generalization theories analyze the generalization performance mainly based on the model complexity and training process. The ignorance of the task properties, which results from the widely used IID assumption, makes these theories fail to interpret many generalization phenomena or guide practical learning tasks. In this paper, we propose a new Independent and Task-Identically Distributed (ITID) assumption, to consider the task properties into the data generating process. The derived generalization bound based on the ITID assumption identifies the significance of hypothesis invariance in guaranteeing generalization performance. Based on the new bound, we introduce a practical invariance enhancement algorithm from the perspective of modifying data distributions. Finally, we verify the algorithm and theorems in the context of image classification task on both toy and real-world datasets. The experimental results demonstrate the reasonableness of the ITID assumption and the effectiveness of new generalization theory in improving practical generalization performance.

cs.LG↗

arXiv2019

Towards Measuring the Adaptability of an AO4BPEL Process

Adaptability is a significant property which enables software systems to continuously provide the required functionality and achieve optimal performance. The recognised importance of adaptability makes its evaluation an essential task. However, the various adaptability dimensions and implementation mechanisms make adaptive strategies difficult to evaluate. In service oriented computing, several frameworks that extend the WS-BPEL, the de facto standard in composing distributed business applications, focus on enabling the adaptability of processes. We aim to evaluate the adaptability of processes specified from the extended-BPEL frameworks. In this paper, we propose metrics to measure the adaptability of an AO4BPEL process. The metrics is grounded in the perspective that a process is capable of dynamically adapting to changes in business requirements. This opens potential future work on evaluating the adaptability of processes specified from various aspect-oriented WS-BPEL frameworks.

cs.SE↗

arXiv2019

Specifying and Reasoning about Contextual Preferences in the Goal-oriented Requirements Modelling

Goal-oriented requirements variability modelling has established the understanding for adaptability in the early stage of software development-the Requirements Engineering phase. Goal-oriented requirements variability modelling considers both the intentions, which are captured as goals in goal models, and the preferences of different stakeholders as the main sources of system behaviour variability. Most often, however, intentions and preferences vary according to contexts. In this paper, we propose an approach for a contextual preference-based requirements variability analysis in the goal-oriented Requirements Engineering. We introduce a quantitative contextual preference specification to express the varying preferences imposed over requirements that are represented in the goal model. Such contextual preferences are used as criteria to evaluate alternative solutions that satisfy the requirements variability problem. We utilise a state-of-the-art reasoning implementation from the Answer Set Programming domain to automate the derivation and evaluation of solutions that fulfill the goals and satisfy the contextual preferences. Our approach will support systems analysts in their decisions upon alternative design solutions that define subsequent system implementations.

cs.SE↗

arXiv2019

blessing in disguise: Designing Robust Turing Test by Employing Algorithm Unrobustness

Turing test was originally proposed to examine whether machine's behavior is indistinguishable from a human. The most popular and practical Turing test is CAPTCHA, which is to discriminate algorithm from human by offering recognition-alike questions. The recent development of deep learning has significantly advanced the capability of algorithm in solving CAPTCHA questions, forcing CAPTCHA designers to increase question complexity. Instead of designing questions difficult for both algorithm and human, this study attempts to employ the limitations of algorithm to design robust CAPTCHA questions easily solvable to human. Specifically, our data analysis observes that human and algorithm demonstrates different vulnerability to visual distortions: adversarial perturbation is significantly annoying to algorithm yet friendly to human. We are motivated to employ adversarially perturbed images for robust CAPTCHA design in the context of character-based questions. Three modules of multi-target attack, ensemble adversarial training, and image preprocessing differentiable approximation are proposed to address the characteristics of character-based CAPTCHA cracking. Qualitative and quantitative experimental results demonstrate the effectiveness of the proposed solution. We hope this study can lead to the discussions around adversarial attack/defense in CAPTCHA design and also inspire the future attempts in employing algorithm limitation for practical usage.

cs.CV↗

arXiv2018

ContextServ: Towards Model-Driven Development of Context-AwareWeb Services

In the era of Web of Things and Services, Context-aware Web Services (CASs) are emerging as an important technology for building innovative context-aware applications. CASs enable the information integration from both the physical and virtual world, which affects human living. However, it is challenging to build CASs, due to the lack of context provisioning management approach and limited generic approach for formalizing the development process. We therefore propose ContextServ, a platform that uses a model-driven approach to support the full life cycle of CASs development, hence offering significant design and management flexibility. ContextServ implements a proposed UML-based modelling language ContextUML to support multiple modelling languages. It also supports dynamic adaptation of WS-BPEL based context-aware composite services by weaving context-aware rules into the process. Extensive experimental evaluations on ContextServ and its components showcase that ContextServ can support effective development and efficient execution of context-aware Web services.

cs.SE↗

arXiv2018

Survey and Performance Evaluation of the Upcoming Next Generation WLAN Standard - IEEE 802.11ax

With the ever-increasing demand for wireless traffic and quality of serives (QoS), wireless local area networks (WLANs) have developed into one of the most dominant wireless networks that fully influence human life. As the most widely used WLANs standard, Institute of Electrical and Electronics Engineers (IEEE) 802.11 will release the upcoming next generation WLANs standard amendment: IEEE 802.11ax. This article comprehensively surveys and analyzes the application scenarios, technical requirements, standardization process, key technologies, and performance evaluations of IEEE 802.11ax. Starting from the technical objectives and requirements of IEEE 802.11ax, this article pays special attention to high-dense deployment scenarios. After that, the key technologies of IEEE 802.11ax, including the physical layer (PHY) enhancements, multi-user (MU) medium access control (MU-MAC), spatial reuse (SR), and power efficiency are discussed in detail, covering both standardization technologies as well as the latest academic studies. Furthermore, performance requirements of IEEE 802.11ax are evaluated via a newly proposed systems and link-level integrated simulation platform (SLISP). Simulations results confirm that IEEE 802.11ax significantly improves the user experience in high-density deployment, while successfully achieves the average per user throughput requirement in project authorization request (PAR) by four times compared to the legacy IEEE 802.11. Finally, potential advancement beyond IEEE 802.11ax are discussed to complete this holistic study on the latest IEEE 802.11ax. To the best of our knowledge, this article is the first study to directly investigate and analyze the latest stable version of IEEE 802.11ax, and the first work to thoroughly and deeply evaluate the compliance of the performance requirements of IEEE 802.11ax.

cs.NI↗

arXiv2018

Preservation of Indigenous Culture among Indigenous Migrants through Social Media: the Igorot Peoples

The value and relevance of indigenous knowledge towards sustainability of human societies drives for its preservation. This work explored the use of Facebook groups to promote indigenous knowledge among Igorot peoples in the diaspora. The virtual communities help intensify the connection of Igorot migrants to their traditional culture despite the challenges of assimilation to a different society. A survey of posts on 20 Facebook groups identified and classified the indigenous cultural elements conveyed through social media. A subsequent survey of 56 Igorot migrants revealed that popular social media has a significant role in the exchange, revitalization, practice, and learning of indigenous culture; inciting an effective medium to leverage preservation strategies.

cs.CY↗

arXiv2016

Generalized Categorization Axioms

Categorization axioms have been proposed to axiomatizing clustering results, which offers a hint of bridging the difference between human recognition system and machine learning through an intuitive observation: an object should be assigned to its most similar category. However, categorization axioms cannot be generalized into a general machine learning system as categorization axioms become trivial when the number of categories becomes one. In order to generalize categorization axioms into general cases, categorization input and categorization output are reinterpreted by inner and outer category representation. According to the categorization reinterpretation, two category representation axioms are presented. Category representation axioms and categorization axioms can be combined into a generalized categorization axiomatic framework, which accurately delimit the theoretical categorization constraints and overcome the shortcoming of categorization axioms. The proposed axiomatic framework not only discuses categorization test issue but also reinterprets many results in machine learning in a unified way, such as dimensionality reduction,density estimation, regression, clustering and classification.

cs.LG↗

arXiv2016

Categorization Axioms for Clustering Results

Cluster analysis has attracted more and more attention in the field of machine learning and data mining. Numerous clustering algorithms have been proposed and are being developed due to diverse theories and various requirements of emerging applications. Therefore, it is very worth establishing an unified axiomatic framework for data clustering. In the literature, it is an open problem and has been proved very challenging. In this paper, clustering results are axiomatized by assuming that an proper clustering result should satisfy categorization axioms. The proposed axioms not only introduce classification of clustering results and inequalities of clustering results, but also are consistent with prototype theory and exemplar theory of categorization models in cognitive science. Moreover, the proposed axioms lead to three principles of designing clustering algorithm and cluster validity index, which follow many popular clustering algorithms and cluster validity indices.

cs.LG↗