arXiv subjects

Xin Shen

Publications and source records attributed to Xin Shen.

At least 55 records · Page 3Linked to original sources

arXiv2023

Semantic Embedded Deep Neural Network: A Generic Approach to Boost Multi-Label Image Classification Performance

Fine-grained multi-label classification models have broad applications in e-commerce, such as visual based label predictions ranging from fashion attribute detection to brand recognition. One challenge to achieve satisfactory performance for those classification tasks in real world is the wild visual background signal that contains irrelevant pixels which confuses model to focus onto the region of interest and make prediction upon the specific region. In this paper, we introduce a generic semantic-embedding deep neural network to apply the spatial awareness semantic feature incorporating a channel-wise attention based model to leverage the localization guidance to boost model performance for multi-label prediction. We observed an Avg.relative improvement of 15.27% in terms of AUC score across all labels compared to the baseline approach. Core experiment and ablation studies involve multi-label fashion attribute classification performed on Instagram fashion apparels' image. We compared the model performances among our approach, baseline approach, and 3 alternative approaches to leverage semantic features. Results show favorable performance for our approach.

cs.CV↗

arXiv2023

Learning Personalized Page Content Ranking Using Customer Representation

On E-commerce stores, there are rich recommendation content to help shoppers shopping more efficiently. However given numerous products, it's crucial to select most relevant content to reduce the burden of information overload. We introduced a content ranking service powered by a linear causal bandit algorithm to rank and select content for each shopper under each context. The algorithm mainly leverages aggregated customer behavior features, and ignores single shopper level past activities. We study the problem of inferring shoppers interest from historical activities. We propose a deep learning based bandit algorithm that incorporates historical shopping behavior, customer latent shopping goals, and the correlation between customers and content categories. This model produces more personalized content ranking measured by 12.08% nDCG lift.

cs.IR↗

arXiv2023

Text Is All You Need: Learning Language Representations for Sequential Recommendation

Sequential recommendation aims to model dynamic user behavior from historical interactions. Existing methods rely on either explicit item IDs or general textual features for sequence modeling to understand user preferences. While promising, these approaches still struggle to model cold-start items or transfer knowledge to new datasets. In this paper, we propose to model user preferences and item features as language representations that can be generalized to new items and datasets. To this end, we present a novel framework, named Recformer, which effectively learns language representations for sequential recommendation. Specifically, we propose to formulate an item as a "sentence" (word sequence) by flattening item key-value attributes described by text so that an item sequence for a user becomes a sequence of sentences. For recommendation, Recformer is trained to understand the "sentence" sequence and retrieve the next "sentence". To encode item sequences, we design a bi-directional Transformer similar to the model Longformer but with different embedding layers for sequential recommendation. For effective representation learning, we propose novel pretraining and finetuning methods which combine language understanding and recommendation tasks. Therefore, Recformer can effectively recommend the next item based on language representations. Extensive experiments conducted on six datasets demonstrate the effectiveness of Recformer for sequential recommendation, especially in low-resource and cold-start settings.

cs.IR↗

arXiv2023

Learning to Personalize Recommendation based on Customers' Shopping Intents

Understanding the customers' high level shopping intent, such as their desire to go camping or hold a birthday party, is critically important for an E-commerce platform; it can help boost the quality of shopping experience by enabling provision of more relevant, explainable, and diversified recommendations. However, such high level shopping intent has been overlooked in the industry due to practical challenges. In this work, we introduce Amazon's new system that explicitly identifies and utilizes each customer's high level shopping intents for personalizing recommendations. We develop a novel technique that automatically identifies various high level goals being pursued by the Amazon customers, such as "go camping", and "preparing for a beach party". Our solution is in a scalable fashion (in 14 languages across 21 countries). Then a deep learning model maps each customer's online behavior, e.g. product search and individual item engagements, into a subset of high level shopping intents. Finally, a realtime ranker considers both the identified intents as well as the granular engagements to present personalized intent-aware recommendations. Extensive offline analysis ensures accuracy and relevance of the new recommendations and we further observe an 10% improvement in the business metrics. This system is currently serving online traffic at amazon.com, powering several production features, driving significant business impacts

cs.IR↗

arXiv2022

MNER-QG: An End-to-End MRC framework for Multimodal Named Entity Recognition with Query Grounding

Multimodal named entity recognition (MNER) is a critical step in information extraction, which aims to detect entity spans and classify them to corresponding entity types given a sentence-image pair. Existing methods either (1) obtain named entities with coarse-grained visual clues from attention mechanisms, or (2) first detect fine-grained visual regions with toolkits and then recognize named entities. However, they suffer from improper alignment between entity types and visual regions or error propagation in the two-stage manner, which finally imports irrelevant visual information into texts. In this paper, we propose a novel end-to-end framework named MNER-QG that can simultaneously perform MRC-based multimodal named entity recognition and query grounding. Specifically, with the assistance of queries, MNER-QG can provide prior knowledge of entity types and visual regions, and further enhance representations of both texts and images. To conduct the query grounding task, we provide manual annotations and weak supervisions that are obtained via training a highly flexible visual grounding model with transfer learning. We conduct extensive experiments on two public MNER datasets, Twitter2015 and Twitter2017. Experimental results show that MNER-QG outperforms the current state-of-the-art models on the MNER task, and also improves the query grounding performance.

cs.CV↗

arXiv2022

Information fusion approach for biomass estimation in a plateau mountainous forest using a synergistic system comprising UAS-based digital camera and LiDAR

Forest land plays a vital role in global climate, ecosystems, farming and human living environments. Therefore, forest biomass estimation methods are necessary to monitor changes in the forest structure and function, which are key data in natural resources research. Although accurate forest biomass measurements are important in forest inventory and assessments, high-density measurements that involve airborne light detection and ranging (LiDAR) at a low flight height in large mountainous areas are highly expensive. The objective of this study was to quantify the aboveground biomass (AGB) of a plateau mountainous forest reserve using a system that synergistically combines an unmanned aircraft system (UAS)-based digital aerial camera and LiDAR to leverage their complementary advantages. In this study, we utilized digital aerial photogrammetry (DAP), which has the unique advantages of speed, high spatial resolution, and low cost, to compensate for the deficiency of forestry inventory using UAS-based LiDAR that requires terrain-following flight for high-resolution data acquisition. Combined with the sparse LiDAR points acquired by using a high-altitude and high-speed UAS for terrain extraction, dense normalized DAP point clouds can be obtained to produce an accurate and high-resolution canopy height model (CHM). Based on the CHM and spectral attributes obtained from multispectral images, we estimated and mapped the AGB of the region of interest with considerable cost efficiency. Our study supports the development of predictive models for large-scale wall-to-wall AGB mapping by leveraging the complementarity between DAP and LiDAR measurements. This work also reveals the potential of utilizing a UAS-based digital camera and LiDAR synergistically in a plateau mountainous forest area.

eess.IV↗

arXiv2022

Fast Parallel Hypertree Decompositions in Logarithmic Recursion Depth

Modern trends in data collection are bringing current mainstream techniques for database query processing to their limits. Consequently, various novel approaches for efficient query processing are being actively studied. One such approach is based on hypertree decompositions (HDs), which have been shown to carry great potential to process complex queries more efficiently and with stronger theoretical guarantees. However, using HDs for query execution relies on the difficult task of computing decompositions of the query structure, which guides the efficient execution of the query. From theoretical results we know that the performance of purely sequential methods is inherently limited, yet the problem is susceptible to parallelisation. In this paper we propose the first algorithm for computing hypertree decompositions that is well-suited for parallelisation. The proposed algorithm log-k-decomp requires only a logarithmic number of recursion levels and additionally allows for highly parallelised pruning of the search space by restriction to balanced separators. We provide detailed experimental evaluation over the HyperBench benchmark and demonstrate that our approach is highly effective especially for complex queries.

cs.DB↗

arXiv2022

Link between \emph{Zitterbewegung} and topological phase transition

Topological quantum state described by the global invariant has been extensively studied in theory and experiment. In this letter, we investigate the relationship between \emph{Zitterbewegung} and the topology of systems that reflect the properties of the local and whole energy bands, respectively. We generalize the usual two-band effective Hamiltonian to characterize the topological phase transition of the spin-$J$ topological insulator. By studying \emph{Zitterbewegung} dynamics before and after topological phase transition, we find that the direction of quasiparticles' oscillation can well reflect topological properties. Furthermore, we develop a quantitative calculation formula for the topological invariant in the spin-$J$ Chern insulator and give the selection rule of the corresponding dynamics. Finally, we demonstrate that our theory is valid in different topological systems. The topological invariant can be represented by local dynamical properties of the high-symmetry points in the first Brillouin zone, which provides a new measurement method from the dynamical perspective.

quant-ph↗

arXiv2022

Scalable production of single 2D van der Waals layers through atomic layer deposition: Bilayer silica on metal foils and films

The self-limiting nature of atomic layer deposition (ALD) makes it an appealing option for growing single layers of two-dimensional van der Waals (2D-VDW) materials. In this paper it is demonstrated that a single layer of a 2D-VDW form of SiO2 can be grown by ALD on Au and Pd polycrystalline foils and epitaxial films. The silica was deposited by two cycles of bis (diethylamino) silane and oxygen plasma exposure at 525 K. Initial deposition produced a three-dimensionally disordered silica layer; however, subsequent annealing above 950 K drove a structural rearrangement resulting in 2D-VDW; this annealing could be performed at ambient pressure. Surface spectra recorded after annealing indicated that the two ALD cycles yielded close to the silica coverage obtained for 2D-VDW silica prepared by precision SiO deposition in ultra-high vacuum. Analysis of ALD-grown 2D-VDW silica on a Pd(111) film revealed the co-existence of amorphous and incommensurate crystalline 2D phases. In contrast, ALD growth on Au(111) films produced predominantly the amorphous phase while SiO deposition in UHV led to only the crystalline phase, suggesting that the choice of Si source can enable phase control.

cond-mat.mtrl-sci↗

arXiv2021

Identifying Untrustworthy Samples: Data Filtering for Open-domain Dialogues with Bayesian Optimization

Being able to reply with a related, fluent, and informative response is an indispensable requirement for building high-quality conversational agents. In order to generate better responses, some approaches have been proposed, such as feeding extra information by collecting large-scale datasets with human annotations, designing neural conversational models (NCMs) with complex architecture and loss functions, or filtering out untrustworthy samples based on a dialogue attribute, e.g., Relatedness or Genericness. In this paper, we follow the third research branch and present a data filtering method for open-domain dialogues, which identifies untrustworthy samples from training data with a quality measure that linearly combines seven dialogue attributes. The attribute weights are obtained via Bayesian Optimization (BayesOpt) that aims to optimize an objective function for dialogue generation iteratively on the validation set. Then we score training samples with the quality measure, sort them in descending order, and filter out those at the bottom. Furthermore, to accelerate the "filter-train-evaluate" iterations involved in BayesOpt on large-scale datasets, we propose a training framework that integrates maximum likelihood estimation (MLE) and negative training method (NEG). The training method updates parameters of a trained NCMs on two small sets with newly maintained and removed samples, respectively. Specifically, MLE is applied to maximize the log-likelihood of newly maintained samples, while NEG is used to minimize the log-likelihood of newly removed ones. Experimental results on two datasets show that our method can effectively identify untrustworthy samples, and NCMs trained on the filtered datasets achieve better performance.

cs.CL↗

arXiv2021

Efficient Medical Image Segmentation Based on Knowledge Distillation

Recent advances have been made in applying convolutional neural networks to achieve more precise prediction results for medical image segmentation problems. However, the success of existing methods has highly relied on huge computational complexity and massive storage, which is impractical in the real-world scenario. To deal with this problem, we propose an efficient architecture by distilling knowledge from well-trained medical image segmentation networks to train another lightweight network. This architecture empowers the lightweight network to get a significant improvement on segmentation capability while retaining its runtime efficiency. We further devise a novel distillation module tailored for medical image segmentation to transfer semantic region information from teacher to student network. It forces the student network to mimic the extent of difference of representations calculated from different tissue regions. This module avoids the ambiguous boundary problem encountered when dealing with medical imaging but instead encodes the internal information of each semantic region for transferring. Benefited from our module, the lightweight network could receive an improvement of up to 32.6% in our experiment while maintaining its portability in the inference phase. The entire structure has been verified on two widely accepted public CT datasets LiTS17 and KiTS19. We demonstrate that a lightweight network distilled by our method has non-negligible value in the scenario which requires relatively high operating speed and low storage usage.

eess.IV↗

arXiv2021

Analysis of an Incomplete Binary Outcome Dichotomized From an Underlying Continuous Variable in Clinical Trials

In many clinical trials, outcomes of interest include binary-valued endpoints. It is not uncommon that a binary-valued outcome is dichotomized from a continuous outcome at a threshold of clinical interest. To reach the objective, common approaches include (a) fitting the generalized linear mixed model (GLMM) to the dichotomized longitudinal binary outcome and (b) imputation method (MI): imputing the missing values in the continuous outcome, dichotomizing it into a binary outcome, and then fitting the generalized linear model for the "complete" data. We conducted comprehensive simulation studies to compare the performance of GLMM with MI for estimating risk difference and logarithm of odds ratio between two treatment arms at the end of study. In those simulation studies, we considered a range of multivariate distribution options for the continuous outcome (including a multivariate normal distribution, a multivariate t-distribution, a multivariate log-normal distribution, and the empirical distribution from a real clinical trial data) to evaluate the robustness of the estimators to various data-generating models. Simulation results demonstrate that both methods work well under those considered distribution options, but MI is more efficient with smaller mean squared errors compared to GLMM. We further applied both the GLMM and MI to 29 phase 3 diabetes clinical trials, and found that the MI method generally led to smaller variance estimates compared to GLMM.

stat.AP↗

arXiv2021

Two-stage Training for Learning from Label Proportions

Learning from label proportions (LLP) aims at learning an instance-level classifier with label proportions in grouped training data. Existing deep learning based LLP methods utilize end-to-end pipelines to obtain the proportional loss with Kullback-Leibler divergence between the bag-level prior and posterior class distributions. However, the unconstrained optimization on this objective can hardly reach a solution in accordance with the given proportions. Besides, concerning the probabilistic classifier, this strategy unavoidably results in high-entropy conditional class distributions at the instance level. These issues further degrade the performance of the instance-level classification. In this paper, we regard these problems as noisy pseudo labeling, and instead impose the strict proportion consistency on the classifier with a constrained optimization as a continuous training stage for existing LLP classifiers. In addition, we introduce the mixup strategy and symmetric crossentropy to further reduce the label noise. Our framework is model-agnostic, and demonstrates compelling performance improvement in extensive experiments, when incorporated into other deep LLP models as a post-hoc phase.

cs.LG↗

arXiv2021

Learning to Select Context in a Hierarchical and Global Perspective for Open-domain Dialogue Generation

Open-domain multi-turn conversations mainly have three features, which are hierarchical semantic structure, redundant information, and long-term dependency. Grounded on these, selecting relevant context becomes a challenge step for multi-turn dialogue generation. However, existing methods cannot differentiate both useful words and utterances in long distances from a response. Besides, previous work just performs context selection based on a state in the decoder, which lacks a global guidance and could lead some focuses on irrelevant or unnecessary information. In this paper, we propose a novel model with hierarchical self-attention mechanism and distant supervision to not only detect relevant words and utterances in short and long distances, but also discern related information globally when decoding. Experimental results on two public datasets of both automatic and human evaluations show that our model significantly outperforms other baselines in terms of fluency, coherence, and informativeness.

cs.CL↗

arXiv2019

Landau-Zener-Stückelberg Interferometry in $\mathcal{PT}$-symmetric Non-Hermitian models

We systematically investigate the non-Hermitian generalisations of the Landau-Zener (LZ) transition and the Landau-Zener-Stückelberg (LZS) interferometry. The LZ transition probabilities, or band populations, are calculated for a generic non-Hermitian model and their asymptotic behaviour analysed. We then focus on non-Hermitian systems with a real adiabatic parameter and study the LZS interferometry formed out of two identical avoided level crossings. Four distinctive cases of interferometry are identified and the analytic formulae for the transition probabilities are calculated for each case. The differences and similarities between the non-Hermitian case and its Hermitian counterpart are emphasised. In particular, the geometrical phase originated from the sign change of the mass term at the two level crossings is still present in the non-Hermitian system, indicating its robustness against the non-Hermiticity. We further apply our non-Hermitian LZS theory to describing the Bloch oscillation in one-dimensional parity-time $(\mathcal{PT})$ reversal symmetric non-Hermitian Su-Schrieffer-Heeger model and propose an experimental scheme to simulate such dynamics using photonic waveguide arrays. The Landau-Zener transition, as well as the LZS interferometry, can be visualised through the beam intensity profile and the transition probabilitiess measured by the centre of mass of the profile.

quant-ph↗

arXiv2018

Simulating the Klein tunneling of pseudospin-one Maxwell particles with trapped ions

We propose an experimental scheme to simulate and observe the Klein tunneling of relativistic Maxwell particles with trapped ions. We explore the scattering dynamics of the pseudospin-one Maxwell particles and demonstrate that the scattered state should be a superposition of a reflection state, a localization state, and a transmission state. The probabilities of these states can be analytically obtained by the approach of Landau-Zener transition. We further show that the Maxwell Hamiltonian and the associated scattering dynamics can be mimicked with two trapped ions. The Maxwell spinors are encoded by three internal states of the first ion, the position and momentum are described by those of the motional modes, and the desired linear potential barrier is built by the second ion.

quant-ph↗

arXiv2018

A Novel Large-scale Ordinal Regression Model

Ordinal regression (OR) is a special multiclass classification problem where an order relation exists among the labels. Recent years, people share their opinions and sentimental judgments conveniently with social networks and E-Commerce so that plentiful large-scale OR problems arise. However, few studies have focused on this kind of problems. Nonparallel Support Vector Ordinal Regression (NPSVOR) is a SVM-based OR model, which learns a hyperplane for each rank by solving a series of independent sub-optimization problems and then ensembles those learned hyperplanes to predict. The previous studies are focused on its nonlinear case and got a competitive testing performance, but its training is time consuming, particularly for large-scale data. In this paper, we consider NPSVOR's linear case and design an efficient training method based on the dual coordinate descent method (DCD). To utilize the order information among labels in prediction, a new prediction function is also proposed. Extensive contrast experiments on the text OR datasets indicate that the carefully implemented DCD is very suitable for training large data.

cs.LG↗

arXiv2018

A Penalty Method for Rank Minimization Problems in Symmetric Matrices

The problem of minimizing the rank of a symmetric positive semidefinite matrix subject to constraints can be cast equivalently as a semidefinite program with complementarity constraints (SDCMPCC). The formulation requires two positive semidefinite matrices to be complementary. This is a continuous and nonconvex reformulation of the rank minimization problem. We investigate calmness of locally optimal solutions to the SDCMPCC formulation and hence show that any locally optimal solution is a KKT point. We develop a penalty formulation of the problem. We present calmness results for locally optimal solutions to the penalty formulation. We also develop a proximal alternating linearized minimization (PALM) scheme for the penalty formulation, and investigate the incorporation of a momentum term into the algorithm. Computational results are presented.

math.OC↗