arXiv subjects

Lin Sun

Publications and source records attributed to Lin Sun.

102 records · Page 6Linked to original sources

arXiv2019

Combinatorial Keyword Recommendations for Sponsored Search with Deep Reinforcement Learning

In sponsored search, keyword recommendations help advertisers to achieve much better performance within limited budget. Many works have been done to mine numerous candidate keywords from search logs or landing pages. However, the strategy to select from given candidates remains to be improved. The existing relevance-based, popularity-based and regular combinatorial strategies fail to take the internal or external competitions among keywords into consideration. In this paper, we regard keyword recommendations as a combinatorial optimization problem and solve it with a modified pointer network structure. The model is trained on an actor-critic based deep reinforcement learning framework. A pre-clustering method called Equal Size K-Means is proposed to accelerate the training and testing procedure on the framework by reducing the action space. The performance of framework is evaluated both in offline and online environments, and remarkable improvements can be observed.

cs.IR↗

arXiv2019

Conditional Analysis for Key-Value Data with Local Differential Privacy

Local differential privacy (LDP) has been deemed as the de facto measure for privacy-preserving distributed data collection and analysis. Recently, researchers have extended LDP to the basic data type in NoSQL systems: the key-value data, and show its feasibilities in mean estimation and frequency estimation. In this paper, we develop a set of new perturbation mechanisms for key-value data collection and analysis under the strong model of local differential privacy. Since many modern machine learning tasks rely on the availability of conditional probability or the marginal statistics, we then propose the conditional frequency estimation method for key analysis and the conditional mean estimation for value analysis in key-value data. The released statistics with conditions can further be used in learning tasks. Extensive experiments of frequency and mean estimation on both synthetic and real-world datasets validate the effectiveness and accuracy of the proposed key-value perturbation mechanisms against the state-of-art competitors.

cs.CR↗

arXiv2019

Distributed Clustering in the Anonymized Space with Local Differential Privacy

Clustering and analyzing on collected data can improve user experiences and quality of services in big data, IoT applications. However, directly releasing original data brings potential privacy concerns, which raises challenges and opportunities for privacy-preserving clustering. In this paper, we study the problem of non-interactive clustering in distributed setting under the framework of local differential privacy. We first extend the Bit Vector, a novel anonymization mechanism to be functionality-capable and privacy-preserving. Based on the modified encoding mechanism, we propose kCluster algorithm that can be used for clustering in the anonymized space. We show the modified encoding mechanism can be easily implemented in existing clustering algorithms that only rely on distance information, such as DBSCAN. Theoretical analysis and experimental results validate the effectiveness of the proposed schemes.

cs.CR↗

arXiv2019

Coupled Recurrent Network (CRN)

Many semantic video analysis tasks can benefit from multiple, heterogenous signals. For example, in addition to the original RGB input sequences, sequences of optical flow are usually used to boost the performance of human action recognition in videos. To learn from these heterogenous input sources, existing methods reply on two-stream architectural designs that contain independent, parallel streams of Recurrent Neural Networks (RNNs). However, two-stream RNNs do not fully exploit the reciprocal information contained in the multiple signals, let alone exploit it in a recurrent manner. To this end, we propose in this paper a novel recurrent architecture, termed Coupled Recurrent Network (CRN), to deal with multiple input sources. In CRN, the parallel streams of RNNs are coupled together. Key design of CRN is a Recurrent Interpretation Block (RIB) that supports learning of reciprocal feature representations from multiple signals in a recurrent manner. Different from RNNs which stack the training loss at each time step or the last time step, we propose an effective and efficient training strategy for CRN. Experiments show the efficacy of the proposed CRN. In particular, we achieve the new state of the art on the benchmark datasets of human action recognition and multi-person pose estimation.

cs.CV↗

arXiv2018

Probing vectorial near field of light: imaging theory and design principles of nanoprobes

Near-field microscopy is widely used for characterizing electromagnetic fields at nanoscale, where nanoprobes afford the opportunity to extract subwavelength optical quantities, including the amplitude, phase, polarization and chirality. However, owing to the complexity of various nanoprobes, a general and intuitive theory is highly needed to assess the vectorial field response of the nanoprobes and interpret the mechanism of the probe-field interaction. Here, we develop a general imaging theory based on the reciprocity of electromagnetism and multipole expansion analysis. The proposed theory closely resembles the multipolar Hamiltonian for light-matter interaction energy, revealing the coupling mechanism of the probe-field interaction. Based on this theory, we introduce a new paradigm for the design of functional nanoprobes by analyzing the reciprocal dipole moments, and establish effective design principles for the imaging of vectorial near fields. Moreover, we numerically analyze the responses of two typical probes, which can quantitatively reproduce and well explain the experimental results of previously reported measurements of optical magnetism and transverse spin angular momentum. Our work provides a powerful tool for the design and analysis of new functional probes that may enable the probing of various physical quantities of the vectorial near field.

physics.optics↗

arXiv2017

Feedback Networks

Currently, the most successful learning models in computer vision are based on learning successive representations followed by a decision layer. This is usually actualized through feedforward multilayer neural networks, e.g. ConvNets, where each layer forms one of such successive representations. However, an alternative that can achieve the same goal is a feedback based approach in which the representation is formed in an iterative manner based on a feedback received from previous iteration's output. We establish that a feedback based approach has several fundamental advantages over feedforward: it enables making early predictions at the query time, its output naturally conforms to a hierarchical structure in the label space (e.g. a taxonomy), and it provides a new basis for Curriculum Learning. We observe that feedback networks develop a considerably different representation compared to feedforward counterparts, in line with the aforementioned advantages. We put forth a general feedback based learning architecture with the endpoint results on par or better than existing feedforward networks with the addition of the above advantages. We also investigate several mechanisms in feedback architectures (e.g. skip connections in time) and design choices (e.g. feedback length). We hope this study offers new perspectives in quest for more natural and practical learning models.

cs.CV↗

arXiv2017

Lattice Long Short-Term Memory for Human Action Recognition

Human actions captured in video sequences are three-dimensional signals characterizing visual appearance and motion dynamics. To learn action patterns, existing methods adopt Convolutional and/or Recurrent Neural Networks (CNNs and RNNs). CNN based methods are effective in learning spatial appearances, but are limited in modeling long-term motion dynamics. RNNs, especially Long Short-Term Memory (LSTM), are able to learn temporal motion dynamics. However, naively applying RNNs to video sequences in a convolutional manner implicitly assumes that motions in videos are stationary across different spatial locations. This assumption is valid for short-term motions but invalid when the duration of the motion is long. In this work, we propose Lattice-LSTM (L2STM), which extends LSTM by learning independent hidden state transitions of memory cells for individual spatial locations. This method effectively enhances the ability to model dynamics across time and addresses the non-stationary issue of long-term motion dynamics without significantly increasing the model complexity. Additionally, we introduce a novel multi-modal training procedure for training our network. Unlike traditional two-stream architectures which use RGB and optical flow information as input, our two-stream model leverages both modalities to jointly train both input gates and both forget gates in the network rather than treating the two streams as separate entities with no information about the other. We apply this end-to-end system to benchmark datasets (UCF-101 and HMDB-51) of human action recognition. Experiments show that on both datasets, our proposed method outperforms all existing ones that are based on LSTM and/or CNNs of similar model complexities.

cs.CV↗

arXiv2017

Fine-Grained Categorization via CNN-Based Automatic Extraction and Integration of Object-Level and Part-Level Features

Fine-grained categorization can benefit from part-based features which reveal subtle visual differences between object categories. Handcrafted features have been widely used for part detection and classification. Although a recent trend seeks to learn such features automatically using powerful deep learning models such as convolutional neural networks (CNN), their training and possibly also testing require manually provided annotations which are costly to obtain. To relax these requirements, we assume in this study a general problem setting in which the raw images are only provided with object-level class labels for model training with no other side information needed. Specifically, by extracting and interpreting the hierarchical hidden layer features learned by a CNN, we propose an elaborate CNN-based system for fine-grained categorization. When evaluated on the Caltech-UCSD Birds-200-2011, FGVC-Aircraft, Cars and Stanford dogs datasets under the setting that only object-level class labels are used for training and no other annotations are available for both training and testing, our method achieves impressive performance that is superior or comparable to the state of the art. Moreover, it sheds some light on ingenious use of the hierarchical features learned by CNN which has wide applicability well beyond the current fine-grained categorization task.

cs.CV↗

arXiv2016

Coexistence of spin glass and ferroelectricity in highly ordered Bi2FeMnO6 epitaxial thin film

Highly ordered Bi2FeMnO6 epitaxial thin films have been successfully grown on SrTiO3 substrate. Both synchrotron X-ray reciprocal space mapping and high resolution transmission electron microscopy confirmed the alternative alignment of Fe and Mn along [111] direction of Bi2FeMnO6 films. Magnetic and ferroelectric properties of Bi2FeMnO6 films are characterized and analyzed. The room-temperature ferroelectricity is well kept in Bi2FeMnO6 film as expected. However, it is very interesting that Bi2FeMnO6 film exhibits a typical spin-glass behavior and very weak magnetism rather than a ferri/ferromagnetism as generally believed. Our first-principles calculations suggest a spin frustration model for Bi2FeMnO6, which can well explain the intriguing magnetic property of Bi2FeMnO6 film.

cond-mat.mtrl-sci↗

arXiv2015

Human Action Recognition using Factorized Spatio-Temporal Convolutional Networks

Human actions in video sequences are three-dimensional (3D) spatio-temporal signals characterizing both the visual appearance and motion dynamics of the involved humans and objects. Inspired by the success of convolutional neural networks (CNN) for image classification, recent attempts have been made to learn 3D CNNs for recognizing human actions in videos. However, partly due to the high complexity of training 3D convolution kernels and the need for large quantities of training videos, only limited success has been reported. This has triggered us to investigate in this paper a new deep architecture which can handle 3D signals more effectively. Specifically, we propose factorized spatio-temporal convolutional networks (FstCN) that factorize the original 3D convolution kernel learning as a sequential process of learning 2D spatial kernels in the lower layers (called spatial convolutional layers), followed by learning 1D temporal kernels in the upper layers (called temporal convolutional layers). We introduce a novel transformation and permutation operator to make factorization in FstCN possible. Moreover, to address the issue of sequence alignment, we propose an effective training and inference strategy based on sampling multiple video clips from a given action video sequence. We have tested FstCN on two commonly used benchmark datasets (UCF-101 and HMDB-51). Without using auxiliary training videos to boost the performance, FstCN outperforms existing CNN based methods and achieves comparable performance with a recent method that benefits from using auxiliary training videos.

cs.CV↗

arXiv2008

Electroweak and supersymmetric two-loop corrections to lepton anomalous magnetic and electric dipole moments

Using the effective Lagrangian method, we analyze the electroweak corrections to the anomalous dipole moments of lepton from some special two-loop diagrams where a closed neutralino/chargino loop is inserted into relevant two Higgs doublet one-loop diagrams in the minimal supersymmetric extension of the standard model with CP violation. Considering the translational invariance of loop momenta and the electromagnetic gauge invariance, we get all dimension 6 operators and derive their coefficients. After applying equations of motion to the external leptons, we obtain the anomalous dipole moments of lepton. The numerical results imply that there is parameter space where the contributions to the muon anomalous dipole moments from this sector may be significant.

hep-ph↗

arXiv2008

The two loop supersymmetric corrections to lepton anomalous dipole moments in split supersymmetry scenarios

An analysis of electroweak corrections to the anomalous dipole moments of lepton from some special two-loop diagrams where a closed neutralino/chargino loop is inserted into relevant one-loop diagrams of the standard model is presented in the split supersymmetry scenarios. Considering the translational invariance of the inner loop momenta and the electromagnetic gauge invariance, we get all dimension 6 operators and their coefficients. After applying equations of motion to the external leptons, we obtain the anomalous dipole moments of lepton. The numerical results imply that there is parameter space where the contribution to the muon anomalous magnetic dipole moment from this sector is perhaps significant, and the contribution to the electron electric dipole moment from this sector is sizable enough to be observed in next generation experiments.

hep-ph↗