arXiv subjects

Kun Zhang

Publications and source records attributed to Kun Zhang.

At least 397 records · Page 22Linked to original sources

arXiv2021

Asymmetric steerability of quantum equilibrium and nonequilibrium steady states through entanglement detection

Einstein-Podolsky-Rosen steering describes a quantum correlation in addition to entanglement and Bell nonlocality. However, conceptually different from entanglement and Bell nonlocality, quantum steering has an asymmetric definition. Motivated by the asymmetric definition of quantum steering, we study the steerability of two-interacting qubits, which have asymmetric energy levels, coupled with asymmetric environments. The asymmetric (nonequilibrium) environments are two environments with different temperatures or chemical potentials. The Bloch-Redfield equation is applied to study the dynamics of two qubits and its long-time behavior. In our study, the steady-state steerability is determined by an experimentally friendly steering criteria, which demonstrates steering through the entanglement detection. Our results show that the steady states of two asymmetric qubits have the advantage for one direction of steering, compared to the symmetric setup. We also provide analytical results on the minimal coupling strength between the two qubits in order to be steerable. The asymmetric steerability is collectively determined by the nature of the two qubits and the influence from equilibrium or nonequilibrium environments. Nonequilibrium environments with the cost of nonzero entropy production can enhance the steerability in one direction. We also show the strict hierarchy of entanglement, steering and Bell nonlocality of the nonequilibrium steady states, which shows a richer structure of steering than entanglement and Bell nonlocality.

quant-ph↗

arXiv2021

Relativistic electron flux model in the outer radiation belt using a neural network approach

We present a machine-learning-based model of relativistic electron fluxes >1.8 MeV using a neural network approach in the Earth's outer radiation belt. The Outer RadIation belt Electron Neural net model for Relativistic electrons (ORIENT-R) uses only solar wind conditions and geomagnetic indices as input. For the first time, we show that the state of the outer radiation belt can be determined using only solar wind conditions and geomagnetic indices, without any initial and boundary conditions. The most important features for determining outer radiation belt dynamics are found to be AL, solar wind flow speed and density, and SYM-H indices. ORIENT-R reproduces out-of-sample relativistic electron fluxes with a correlation coefficient of 0.95 and an uncertainty factor of ~2. ORIENT-R reproduces radiation belt dynamics during an out-of-sample geomagnetic storm with good agreement to the observations. In addition, ORIENT-R was run for a completely out-of-sample period between March 2018 and October 2019 when the AL index ended and was replaced with the predicted AL index (lasp.colorado.edu/~lix). It reproduces electron fluxes with a correlation coefficient of 0.92 and an out-of-sample uncertainty factor of ~3. Furthermore, ORIENT-R captured the trend in the electron fluxes from low-earth-orbit (LEO) SAMPEX, which is a completely out-of-sample dataset both temporally and spatially. In sum, the ORIENT-R model can reproduce transport, acceleration, decay, and dropouts of the outer radiation belt anywhere from short timescales (i.e., geomagnetic storms) and very long timescales (i.e., solar cycle) variations.

physics.space-ph↗

arXiv2021

Unaligned Image-to-Image Translation by Learning to Reweight

Unsupervised image-to-image translation aims at learning the mapping from the source to target domain without using paired images for training. An essential yet restrictive assumption for unsupervised image translation is that the two domains are aligned, e.g., for the selfie2anime task, the anime (selfie) domain must contain only anime (selfie) face images that can be translated to some images in the other domain. Collecting aligned domains can be laborious and needs lots of attention. In this paper, we consider the task of image translation between two unaligned domains, which may arise for various possible reasons. To solve this problem, we propose to select images based on importance reweighting and develop a method to learn the weights and perform translation simultaneously and automatically. We compare the proposed method with state-of-the-art image translation approaches and present qualitative and quantitative results on different tasks with unaligned domains. Extensive empirical evidence demonstrates the usefulness of the proposed problem formulation and the superiority of our method.

cs.CV↗

arXiv2021

A Fast PC Algorithm with Reversed-order Pruning and A Parallelization Strategy

The PC algorithm is the state-of-the-art algorithm for causal structure discovery on observational data. It can be computationally expensive in the worst case due to the conditional independence tests are performed in an exhaustive-searching manner. This makes the algorithm computationally intractable when the task contains several hundred or thousand nodes, particularly when the true underlying causal graph is dense. We propose a critical observation that the conditional set rendering two nodes independent is non-unique, and including certain redundant nodes do not sacrifice result accuracy. Based on this finding, the innovations of our work are two-folds. First, we innovate on a reserve order linkage pruning PC algorithm which significantly increases the algorithm's efficiency. Second, we propose a parallel computing strategy for statistical independence tests by leveraging tensor computation, which brings further speedup. We also prove the proposed algorithm does not induce statistical power loss under mild graph and data dimensionality assumptions. Experimental results show that the single-threaded version of the proposed algorithm can achieve a 6-fold speedup compared to the PC algorithm on a dense 95-node graph, and the parallel version can make a 825-fold speed-up. We also provide proof that the proposed algorithm is consistent under the same set of conditions with conventional PC algorithm.

cs.LG↗

arXiv2021

DAE-GAN: Dynamic Aspect-aware GAN for Text-to-Image Synthesis

Text-to-image synthesis refers to generating an image from a given text description, the key goal of which lies in photo realism and semantic consistency. Previous methods usually generate an initial image with sentence embedding and then refine it with fine-grained word embedding. Despite the significant progress, the 'aspect' information (e.g., red eyes) contained in the text, referring to several words rather than a word that depicts 'a particular part or feature of something', is often ignored, which is highly helpful for synthesizing image details. How to make better utilization of aspect information in text-to-image synthesis still remains an unresolved challenge. To address this problem, in this paper, we propose a Dynamic Aspect-awarE GAN (DAE-GAN) that represents text information comprehensively from multiple granularities, including sentence-level, word-level, and aspect-level. Moreover, inspired by human learning behaviors, we develop a novel Aspect-aware Dynamic Re-drawer (ADR) for image refinement, in which an Attended Global Refinement (AGR) module and an Aspect-aware Local Refinement (ALR) module are alternately employed. AGR utilizes word-level embedding to globally enhance the previously generated image, while ALR dynamically employs aspect-level embedding to refine image details from a local perspective. Finally, a corresponding matching loss function is designed to ensure the text-image semantic consistency at different levels. Extensive experiments on two well-studied and publicly available datasets (i.e., CUB-200 and COCO) demonstrate the superiority and rationality of our method.

cs.CV↗

arXiv2021

Outdoor Position Recovery from HeterogeneousTelco Cellular Data

Recent years have witnessed unprecedented amounts of data generated by telecommunication (Telco) cellular networks. For example, measurement records (MRs) are generated to report the connection states between mobile devices and Telco networks, e.g., received signal strength. MR data have been widely used to localize outdoor mobile devices for human mobility analysis, urban planning, and traffic forecasting. Existing works using first-order sequence models such as the Hidden Markov Model (HMM) attempt to capture spatio-temporal locality in underlying mobility patterns for lower localization errors. The HMM approaches typically assume stable mobility patterns of the underlying mobile devices. Yet real MR datasets exhibit heterogeneous mobility patterns due to mixed transportation modes of the underlying mobile devices and uneven distribution of the positions associated with MR samples. Thus, the existing solutions cannot handle these heterogeneous mobility patterns. we propose a multi-task learning-based deep neural network (DNN) framework, namely PRNet+, to incorporate outdoor position recovery and transportation mode detection. To make sure the framework work, PRNet+ develops a feature extraction module to precisely learn local-, short- and long-term spatio-temporal locality from heterogeneous MR samples. Extensive evaluation on eight datasets collected at three representative areas in Shanghai indicates that PRNet+ greatly outperforms state-of-the-arts.

cs.NI↗

arXiv2021

LadRa-Net: Locally-Aware Dynamic Re-read Attention Net for Sentence Semantic Matching

Sentence semantic matching requires an agent to determine the semantic relation between two sentences, which is widely used in various natural language tasks, such as Natural Language Inference (NLI), Paraphrase Identification (PI), and so on. Much recent progress has been made in this area, especially attention-based methods and pre-trained language model based methods. However, most of these methods focus on all the important parts in sentences in a static way and only emphasize how important the words are to the query, inhibiting the ability of attention mechanism. In order to overcome this problem and boost the performance of attention mechanism, we propose a novel dynamic re-read attention, which can pay close attention to one small region of sentences at each step and re-read the important parts for better sentence representations. Based on this attention variation, we develop a novel Dynamic Re-read Network (DRr-Net) for sentence semantic matching. Moreover, selecting one small region in dynamic re-read attention seems insufficient for sentence semantics, and employing pre-trained language models as input encoders will introduce incomplete and fragile representation problems. To this end, we extend DRrNet to Locally-Aware Dynamic Re-read Attention Net (LadRa-Net), in which local structure of sentences is employed to alleviate the shortcoming of Byte-Pair Encoding (BPE) in pre-trained language models and boost the performance of dynamic reread attention. Extensive experiments on two popular sentence semantic matching tasks demonstrate that DRr-Net can significantly improve the performance of sentence semantic matching. Meanwhile, LadRa-Net is able to achieve better performance by considering the local structures of sentences. In addition, it is exceedingly interesting that some discoveries in our experiments are consistent with some findings of psychological research.

cs.CL↗

arXiv2021

RIS-Aided Wireless Communications: Prototyping, Adaptive Beamforming, and Indoor/Outdoor Field Trials

The prospects of using a Reconfigurable Intelligent Surface (RIS) to aid wireless communication systems have recently received much attention from academia and industry. Most papers make theoretical studies based on elementary models, while the prototyping of RIS-aided wireless communication and real-world field trials are scarce. In this paper, we describe a new RIS prototype consisting of 1100 controllable elements working at 5.8 GHz band. We propose an efficient algorithm for configuring the RIS over the air by exploiting the geometrical array properties and a practical receiver-RIS feedback link. In our indoor test, where the transmitter and receiver are separated by a 30 cm thick concrete wall, our RIS prototype provides a 26 dB power gain compared to the baseline case where the RIS is replaced by a copper plate. A 27 dB power gain was observed in the short-distance outdoor measurement. We also carried out long-distance measurements and successfully transmitted a 32 Mbps data stream over 500 m. A 1080p video was live-streamed and it only played smoothly when the RIS was utilized. The power consumption of the RIS is around 1 W. Our paper is vivid proof that the RIS is a very promising technology for future wireless communications.

cs.IT↗

arXiv2021

Multi-Channel Auto-Encoders and a Novel Dataset for Learning Domain Invariant Representations of Histopathology Images

Domain shift is a problem commonly encountered when developing automated histopathology pipelines. The performance of machine learning models such as convolutional neural networks within automated histopathology pipelines is often diminished when applying them to novel data domains due to factors arising from differing staining and scanning protocols. The Dual-Channel Auto-Encoder (DCAE) model was previously shown to produce feature representations that are less sensitive to appearance variation introduced by different digital slide scanners. In this work, the Multi-Channel Auto-Encoder (MCAE) model is presented as an extension to DCAE which learns from more than two domains of data. Additionally, a synthetic dataset is generated using CycleGANs that contains aligned tissue images that have had their appearance synthetically modified. Experimental results show that the MCAE model produces feature representations that are less sensitive to inter-domain variations than the comparative StaNoSA method when tested on the novel synthetic data. Additionally, the MCAE and StaNoSA models are tested on a novel tissue classification task. The results of this experiment show the MCAE model out performs the StaNoSA model by 5 percentage-points in the f1-score. These results show that the MCAE model is able to generalise better to novel data and tasks than existing approaches by actively learning normalised feature representations.

eess.IV↗

arXiv2021

Implementation of efficient quantum search algorithms on NISQ computers

Despite the advent of Grover's algorithm for the unstructured search, its successful implementation on near-term quantum devices is still limited. We apply three strategies to reduce the errors associated with implementing quantum search algorithms. Our improved search algorithms have been implemented on the IBM quantum processors. Using them, we demonstrate three- and four-qubit search algorithm with higher average success probabilities compared to previous works. We present the successful execution of the five-qubit search on the IBM quantum processor for the first time. The results have been benchmarked using degraded ratio, which is the ratio between the experimental and the theoretical success probabilities. The fast decay of the degraded ratio supports our divide-and-conquer strategy. Our proposed strategies are also useful for implementation of quantum search algorithms in the post-NISQ era.

quant-ph↗

arXiv2021

Graph Domain Adaptation: A Generative View

Recent years have witnessed tremendous interest in deep learning on graph-structured data. Due to the high cost of collecting labeled graph-structured data, domain adaptation is important to supervised graph learning tasks with limited samples. However, current graph domain adaptation methods are generally adopted from traditional domain adaptation tasks, and the properties of graph-structured data are not well utilized. For example, the observed social networks on different platforms are controlled not only by the different crowd or communities but also by the domain-specific policies and the background noise. Based on these properties in graph-structured data, we first assume that the graph-structured data generation process is controlled by three independent types of latent variables, i.e., the semantic latent variables, the domain latent variables, and the random latent variables. Based on this assumption, we propose a disentanglement-based unsupervised domain adaptation method for the graph-structured data, which applies variational graph auto-encoders to recover these latent variables and disentangles them via three supervised learning modules. Extensive experimental results on two real-world datasets in the graph classification task reveal that our method not only significantly outperforms the traditional domain adaptation methods and the disentangled-based domain adaptation methods but also outperforms the state-of-the-art graph domain adaptation algorithms.

cs.LG↗

arXiv2021

DGA-Net Dynamic Gaussian Attention Network for Sentence Semantic Matching

Sentence semantic matching requires an agent to determine the semantic relation between two sentences, where much recent progress has been made by the advancement of representation learning techniques and inspiration of human behaviors. Among all these methods, attention mechanism plays an essential role by selecting important parts effectively. However, current attention methods either focus on all the important parts in a static way or only select one important part at one attention step dynamically, which leaves a large space for further improvement. To this end, in this paper, we design a novel Dynamic Gaussian Attention Network (DGA-Net) to combine the advantages of current static and dynamic attention methods. More specifically, we first leverage pre-trained language model to encode the input sentences and construct semantic representations from a global perspective. Then, we develop a Dynamic Gaussian Attention (DGA) to dynamically capture the important parts and corresponding local contexts from a detailed perspective. Finally, we combine the global information and detailed local information together to decide the semantic relation of sentences comprehensively and precisely. Extensive experiments on two popular sentence semantic matching tasks demonstrate that our proposed DGA-Net is effective in improving the ability of attention mechanism.

cs.CL↗

arXiv2021

Progressive Open-Domain Response Generation with Multiple Controllable Attributes

It is desirable to include more controllable attributes to enhance the diversity of generated responses in open-domain dialogue systems. However, existing methods can generate responses with only one controllable attribute or lack a flexible way to generate them with multiple controllable attributes. In this paper, we propose a Progressively trained Hierarchical Encoder-Decoder (PHED) to tackle this task. More specifically, PHED deploys Conditional Variational AutoEncoder (CVAE) on Transformer to include one aspect of attributes at one stage. A vital characteristic of the CVAE is to separate the latent variables at each stage into two types: a global variable capturing the common semantic features and a specific variable absorbing the attribute information at that stage. PHED then couples the CVAE latent variables with the Transformer encoder and is trained by minimizing a newly derived ELBO and controlled losses to produce the next stage's input and produce responses as required. Finally, we conduct extensive evaluations to show that PHED significantly outperforms the state-of-the-art neural generation models and produces more diverse responses as expected.

cs.CL↗

arXiv2021

Graph-based Exercise- and Knowledge-Aware Learning Network for Student Performance Prediction

Predicting student performance is a fundamental task in Intelligent Tutoring Systems (ITSs), by which we can learn about students' knowledge level and provide personalized teaching strategies for them. Researchers have made plenty of efforts on this task. They either leverage educational psychology methods to predict students' scores according to the learned knowledge proficiency, or make full use of Collaborative Filtering (CF) models to represent latent factors of students and exercises. However, most of these methods either neglect the exercise-specific characteristics (e.g., exercise materials), or cannot fully explore the high-order interactions between students, exercises, as well as knowledge concepts. To this end, we propose a Graph-based Exercise- and Knowledge-Aware Learning Network for accurate student score prediction. Specifically, we learn students' mastery of exercises and knowledge concepts respectively to model the two-fold effects of exercises and knowledge concepts. Then, to model the high-order interactions, we apply graph convolution techniques in the prediction process. Extensive experiments on two real-world datasets prove the effectiveness of our proposed Graph-EKLN.

cs.AI↗

arXiv2021

Privileged Graph Distillation for Cold Start Recommendation

The cold start problem in recommender systems is a long-standing challenge, which requires recommending to new users (items) based on attributes without any historical interaction records. In these recommendation systems, warm users (items) have privileged collaborative signals of interaction records compared to cold start users (items), and these Collaborative Filtering (CF) signals are shown to have competing performance for recommendation. Many researchers proposed to learn the correlation between collaborative signal embedding space and the attribute embedding space to improve the cold start recommendation, in which user and item categorical attributes are available in many online platforms. However, the cold start recommendation is still limited by two embedding spaces modeling and simple assumptions of space transformation. As user-item interaction behaviors and user (item) attributes naturally form a heterogeneous graph structure, in this paper, we propose a privileged graph distillation model~(PGD). The teacher model is composed of a heterogeneous graph structure for warm users and items with privileged CF links. The student model is composed of an entity-attribute graph without CF links. Specifically, the teacher model can learn better embeddings of each entity by injecting complex higher-order relationships from the constructed heterogeneous graph. The student model can learn the distilled output with privileged CF embeddings from the teacher embeddings. Our proposed model is generally applicable to different cold start scenarios with new user, new item, or new user-new item. Finally, extensive experimental results on the real-world datasets clearly show the effectiveness of our proposed model on different types of cold start problems, with average $6.6\%, 5.6\%, $ and $17.1\%$ improvement over state-of-the-art baselines on three datasets, respectively.

cs.IR↗

arXiv2021

Set2setRank: Collaborative Set to Set Ranking for Implicit Feedback based Recommendation

As users often express their preferences with binary behavior data~(implicit feedback), such as clicking items or buying products, implicit feedback based Collaborative Filtering~(CF) models predict the top ranked items a user might like by leveraging implicit user-item interaction data. For each user, the implicit feedback is divided into two sets: an observed item set with limited observed behaviors, and a large unobserved item set that is mixed with negative item behaviors and unknown behaviors. Given any user preference prediction model, researchers either designed ranking based optimization goals or relied on negative item mining techniques for better optimization. Despite the performance gain of these implicit feedback based models, the recommendation results are still far from satisfactory due to the sparsity of the observed item set for each user. To this end, in this paper, we explore the unique characteristics of the implicit feedback and propose Set2setRank framework for recommendation. The optimization criteria of Set2setRank are two folds: First, we design an item to an item set comparison that encourages each observed item from the sampled observed set is ranked higher than any unobserved item from the sampled unobserved set. Second, we model set level comparison that encourages a margin between the distance summarized from the observed item set and the most "hard" unobserved item from the sampled negative set. Further, an adaptive sampling technique is designed to implement these two goals. We have to note that our proposed framework is model-agnostic and can be easily applied to most recommendation prediction approaches, and is time efficient in practice. Finally, extensive experiments on three real-world datasets demonstrate the superiority of our proposed approach.

cs.IR↗

arXiv2021

Learning Graph Meta Embeddings for Cold-Start Ads in Click-Through Rate Prediction

Click-through rate (CTR) prediction is one of the most central tasks in online advertising systems. Recent deep learning-based models that exploit feature embedding and high-order data nonlinearity have shown dramatic successes in CTR prediction. However, these models work poorly on cold-start ads with new IDs, whose embeddings are not well learned yet. In this paper, we propose Graph Meta Embedding (GME) models that can rapidly learn how to generate desirable initial embeddings for new ad IDs based on graph neural networks and meta learning. Previous works address this problem from the new ad itself, but ignore possibly useful information contained in existing old ads. In contrast, GMEs simultaneously consider two information sources: the new ad and existing old ads. For the new ad, GMEs exploit its associated attributes. For existing old ads, GMEs first build a graph to connect them with new ads, and then adaptively distill useful information. We propose three specific GMEs from different perspectives to explore what kind of information to use and how to distill information. In particular, GME-P uses Pre-trained neighbor ID embeddings, GME-G uses Generated neighbor ID embeddings and GME-A uses neighbor Attributes. Experimental results on three real-world datasets show that GMEs can significantly improve the prediction performance in both cold-start (i.e., no training data is available) and warm-up (i.e., a small number of training samples are collected) scenarios over five major deep learning-based CTR prediction models. GMEs can be applied to conversion rate (CVR) prediction as well.

cs.IR↗

arXiv2021

The kinetics and its turnover of Hawking-Page phase transition under the black hole evaporation

The thermodynamics and the kinetics of Hawking-Page phase transition were studied previously based on the free energy landscape. The AdS black hole can evaporate if imposing the absorbing boundary conditions at infinity. We suggest that the kinetics of Hawking-Page phase transition should be governed by the reaction-diffusion equation, where the Hawking evaporation plays the role of the reaction on the background of the free energy landscape. By calculating the mean first passage time from the large black hole phase to the thermal gas phase, we show that the phase transition can occur more easily under the Hawking radiation. In particular, a kinetic turnover is observed when increasing the ensemble temperature or the frictions. This kinetic turnover can be viewed as the dynamical phase transition to identify the time scale where Hawking evaporation process is comparable to Hawking-Page phase transition.

gr-qc↗