arXiv subjects

Yue Xu

Publications and source records attributed to Yue Xu.

102 records · Page 6Linked to original sources

arXiv2020

Symmetry and Group in Attribute-Object Compositions

Attributes and objects can compose diverse compositions. To model the compositional nature of these general concepts, it is a good choice to learn them through transformations, such as coupling and decoupling. However, complex transformations need to satisfy specific principles to guarantee the rationality. In this paper, we first propose a previously ignored principle of attribute-object transformation: Symmetry. For example, coupling peeled-apple with attribute peeled should result in peeled-apple, and decoupling peeled from apple should still output apple. Incorporating the symmetry principle, a transformation framework inspired by group theory is built, i.e. SymNet. SymNet consists of two modules, Coupling Network and Decoupling Network. With the group axioms and symmetry property as objectives, we adopt Deep Neural Networks to implement SymNet and train it in an end-to-end paradigm. Moreover, we propose a Relative Moving Distance (RMD) based recognition method to utilize the attribute change instead of the attribute pattern itself to classify attributes. Our symmetry learning can be utilized for the Compositional Zero-Shot Learning task and outperforms the state-of-the-art on widely-used benchmarks. Code is available at https://github.com/DirtyHarryLYL/SymNet.

cs.CV↗

arXiv2020

Search for a generic heavy Higgs at the LHC

A generic heavy Higgs has both dim-4 and effective dim-6 interactions with the Standard Model (SM) particles. The former has been the focus of LHC searches in all major Higgs production channels, just as the SM one, but with negative results so far. If the heavy Higgs is connected with Beyond Standard Model (BSM) physics at a few TeV scale, its dim-6 operators will play a very important role - they significantly enhance the Higgs momentum, and reduce the SM background in a special phase space corner to a level such that a heavy Higgs emerges, which is not possible with dim-4 operators only. We focus on the associated VH production channel, where the effect of dim-6 operators is the largest and the SM background is the lowest. Main search regions for this type of signal are identified, and substructure variables of boosted jets are employed to enhance the signal from backgrounds. The parameter space of these operators are scanned over, and expected exclusion regions with 300 fb$^{-1}$ and 3 ab$^{-1}$ LHC data are shown, if no BSM is present. The strategy given in this paper will shed light on a heavy Higgs which may be otherwise hiding in the present and future LHC data.

hep-ph↗

arXiv2020

Scalable Learning Paradigms for Data-Driven Wireless Communication

The marriage of wireless big data and machine learning techniques revolutionizes the wireless system by the data-driven philosophy. However, the ever exploding data volume and model complexity will limit centralized solutions to learn and respond within a reasonable time. Therefore, scalability becomes a critical issue to be solved. In this article, we aim to provide a systematic discussion on the building blocks of scalable data-driven wireless networks. On one hand, we discuss the forward-looking architecture and computing framework of scalable data-driven systems from a global perspective. On the other hand, we discuss the learning algorithms and model training strategies performed at each individual node from a local perspective. We also highlight several promising research directions in the context of scalable data-driven wireless communications to inspire future research.

cs.LG↗

arXiv2020

$\ell$-Class groups of fields in Kummer towers

Let $\ell$ and $p$ be prime numbers and $K_{n,m}=\mathbb{Q}(p^{\frac{1}{\ell^n}},ζ_{2\ell^{m}})$. We study the $\ell$-class group of $K_{n,m}$ in this paper. When $\ell=2$, we determine the structure of the $2$-class group of $K_{n,m}$ for all $(n,m)\in \mathbb{Z}_{\geq 0}^2$ in the case $p=2$ or $p\equiv 3, 5\bmod{8}$, and for $(n,m)=(n,0)$, $(n,1)$ or $(1,m)$ in the case $p\equiv 7\bmod{16}$, eneralizing the results of Parry about the $2$-divisibility of the class number of $K_{2,0}$. We also obtain results about the $\ell$-class group of $K_{n,m}$ when $\ell$ is odd and in particular $\ell=3$. The main tools we use are class field theory, including Chevalley's ambiguous class number formula and its generalization by Gras, and a stationary result about the $\ell$-class groups in the $2$-dimensional Kummer tower $\{K_{n,m}\}$.

math.NT↗

arXiv2019

On Class Numbers of Pure Quartic fields

Let $p$ be a prime. The $2$-primary part of the class group of the pure quartic field $\mathbb{Q}(\sqrt[4]{p})$ has been determined by Parry and Lemmermeyer when $p \not\equiv \pm 1\bmod 16$. In this paper, we improve the known results in the case $p\equiv \pm 1\bmod 16$. In particular, we determine all primes $p$ such that $4$ does not divide the class number of $\mathbb{Q}(\sqrt[4]{p})$. We also conjecture a relation between the class numbers of $\mathbb{Q}(\sqrt[4]{p})$ and $\mathbb{Q}(\sqrt{-2p})$. We show that this conjecture implies a distribution result of the $2$-class numbers of $\mathbb{Q}(\sqrt[4]{p})$.

math.NT↗

arXiv2019

Load Balancing for Ultra-Dense Networks: A Deep Reinforcement Learning Based Approach

In this paper, we propose a deep reinforcement learning (DRL) based mobility load balancing (MLB) algorithm along with a two-layer architecture to solve the large-scale load balancing problem for ultra-dense networks (UDNs). Our contribution is three-fold. First, this work proposes a two-layer architecture to solve the large-scale load balancing problem in a self-organized manner. The proposed architecture can alleviate the global traffic variations by dynamically grouping small cells into self-organized clusters according to their historical loads, and further adapt to local traffic variations through intra-cluster load balancing afterwards. Second, for the intra-cluster load balancing, this paper proposes an off-policy DRL-based MLB algorithm to autonomously learn the optimal MLB policy under an asynchronous parallel learning framework, without any prior knowledge assumed over the underlying UDN environments. Moreover, the algorithm enables joint exploration with multiple behavior policies, such that the traditional MLB methods can be used to guide the learning process thereby improving the learning efficiency and stability. Third, this work proposes an offline-evaluation based safeguard mechanism to ensure that the online system can always operate with the optimal and well-trained MLB policy, which not only stabilizes the online performance but also enables the exploration beyond current policies to make full use of machine learning in a safe way. Empirical results verify that the proposed framework outperforms the existing MLB methods in general UDN environments featured with irregular network topologies, coupled interferences, and random user movements, in terms of the load balancing performance.

cs.LG↗

arXiv2019

HAKE: Human Activity Knowledge Engine

Human activity understanding is crucial for building automatic intelligent system. With the help of deep learning, activity understanding has made huge progress recently. But some challenges such as imbalanced data distribution, action ambiguity, complex visual patterns still remain. To address these and promote the activity understanding, we build a large-scale Human Activity Knowledge Engine (HAKE) based on the human body part states. Upon existing activity datasets, we annotate the part states of all the active persons in all images, thus establish the relationship between instance activity and body part states. Furthermore, we propose a HAKE based part state recognition model with a knowledge extractor named Activity2Vec and a corresponding part state based reasoning network. With HAKE, our method can alleviate the learning difficulty brought by the long-tail data distribution, and bring in interpretability. Now our HAKE has more than 7 M+ part state annotations and is still under construction. We first validate our approach on a part of HAKE in this preliminary paper, where we show 7.2 mAP performance improvement on Human-Object Interaction recognition, and 12.38 mAP improvement on the one-shot subsets.

cs.CV↗

arXiv2019

Precision Higgs Physics at CEPC

The discovery of the Higgs boson with its mass around 125 GeV by the ATLAS and CMS Collaborations marked the beginning of a new era in high energy physics. The Higgs boson will be the subject of extensive studies of the ongoing LHC program. At the same time, lepton collider based Higgs factories have been proposed as a possible next step beyond the LHC, with its main goal to precisely measure the properties of the Higgs boson and probe potential new physics associated with the Higgs boson. The Circular Electron Positron Collider~(CEPC) is one of such proposed Higgs factories. The CEPC is an $e^+e^-$ circular collider proposed by and to be hosted in China. Located in a tunnel of approximately 100~km in circumference, it will operate at a center-of-mass energy of 240~GeV as the Higgs factory. In this paper, we present the first estimates on the precision of the Higgs boson property measurements achievable at the CEPC and discuss implications of these measurements.

hep-ex↗

arXiv2019

Wireless Traffic Prediction with Scalable Gaussian Process: Framework, Algorithms, and Verification

The cloud radio access network (C-RAN) is a promising paradigm to meet the stringent requirements of the fifth generation (5G) wireless systems. Meanwhile, wireless traffic prediction is a key enabler for C-RANs to improve both the spectrum efficiency and energy efficiency through load-aware network managements. This paper proposes a scalable Gaussian process (GP) framework as a promising solution to achieve large-scale wireless traffic prediction in a cost-efficient manner. Our contribution is three-fold. First, to the best of our knowledge, this paper is the first to empower GP regression with the alternating direction method of multipliers (ADMM) for parallel hyper-parameter optimization in the training phase, where such a scalable training framework well balances the local estimation in baseband units (BBUs) and information consensus among BBUs in a principled way for large-scale executions. Second, in the prediction phase, we fuse local predictions obtained from the BBUs via a cross-validation based optimal strategy, which demonstrates itself to be reliable and robust for general regression tasks. Moreover, such a cross-validation based optimal fusion strategy is built upon a well acknowledged probabilistic model to retain the valuable closed-form GP inference properties. Third, we propose a C-RAN based scalable wireless prediction architecture, where the prediction accuracy and the time consumption can be balanced by tuning the number of the BBUs according to the real-time system demands. Experimental results show that our proposed scalable GP model can outperform the state-of-the-art approaches considerably, in terms of wireless traffic prediction performance.

cs.LG↗

arXiv2019

Efforts estimation of doctors annotating medical image

Accurate annotation of medical image is the crucial step for image AI clinical application. However, annotating medical image will incur a great deal of annotation effort and expense due to its high complexity and needing experienced doctors. To alleviate annotation cost, some active learning methods are proposed. But such methods just cut the number of annotation candidates and do not study how many efforts the doctor will exactly take, which is not enough since even annotating a small amount of medical data will take a lot of time for the doctor. In this paper, we propose a new criterion to evaluate efforts of doctors annotating medical image. First, by coming active learning and U-shape network, we employ a suggestive annotation strategy to choose the most effective annotation candidates. Then we exploit a fine annotation platform to alleviate annotating efforts on each candidate and first utilize a new criterion to quantitatively calculate the efforts taken by doctors. In our work, we take MR brain tissue segmentation as an example to evaluate the proposed method. Extensive experiments on the well-known IBSR18 dataset and MRBrainS18 Challenge dataset show that, using proposed strategy, state-of-the-art segmentation performance can be achieved by using only 60% annotation candidates and annotation efforts can be alleviated by at least 44%, 44%, 47% on CSF, GM, WM separately.

cs.LG↗

arXiv2018

A Multi-channel Network with Image Retrieval for Accurate Brain Tissue Segmentation

Magnetic Resonance Imaging (MRI) is widely used in the pathological and functional studies of the brain, such as epilepsy, tumor diagnosis, etc. Automated accurate brain tissue segmentation like cerebro-spinal fluid (CSF), gray matter (GM), white matter (WM) is the basis of these studies and many researchers are seeking it to the best. Based on the truth that multi-channel segmentation network with its own ground truth achieves up to average dice ratio 0.98, we propose a novel method that we add a fourth channel with the ground truth of the most similar image's obtained by CBIR from the database. The results show that the method improves the segmentation performance, as measured by average dice ratio, by approximately 0.01 in the MRBrainS18 database. In addition, our method is concise and robust, which can be used to any network architecture that needs not be modified a lot.

cs.CV↗

arXiv2018

Handover Control in Wireless Systems via Asynchronous Multi-User Deep Reinforcement Learning

In this paper, we propose a two-layer framework to learn the optimal handover (HO) controllers in possibly large-scale wireless systems supporting mobile Internet-of-Things (IoT) users or traditional cellular users, where the user mobility patterns could be heterogeneous. In particular, our proposed framework first partitions the user equipments (UEs) with different mobility patterns into clusters, where the mobility patterns are similar in the same cluster. Then, within each cluster, an asynchronous multi-user deep reinforcement learning scheme is developed to control the HO processes across the UEs in each cluster, in the goal of lowering the HO rate while ensuring certain system throughput. In this scheme, we use a deep neural network (DNN) as an HO controller learned by each UE via reinforcement learning in a collaborative fashion. Moreover, we use supervised learning in initializing the DNN controller before the execution of reinforcement learning to exploit what we already know with traditional HO schemes and to mitigate the negative effects of random exploration at the initial stage. Furthermore, we show that the adopted global-parameter-based asynchronous framework enables us to train faster with more UEs, which could nicely address the scalability issue to support large systems. Finally, simulation results demonstrate that the proposed framework can achieve better performance than the state-of-art on-line schemes, in terms of HO rates.

cs.NI↗