arXiv subjects

Jian Xu

Publications and source records attributed to Jian Xu.

At least 253 records · Page 14Linked to original sources

arXiv2021

Neural Auction: End-to-End Learning of Auction Mechanisms for E-Commerce Advertising

In e-commerce advertising, it is crucial to jointly consider various performance metrics, e.g., user experience, advertiser utility, and platform revenue. Traditional auction mechanisms, such as GSP and VCG auctions, can be suboptimal due to their fixed allocation rules to optimize a single performance metric (e.g., revenue or social welfare). Recently, data-driven auctions, learned directly from auction outcomes to optimize multiple performance metrics, have attracted increasing research interests. However, the procedure of auction mechanisms involves various discrete calculation operations, making it challenging to be compatible with continuous optimization pipelines in machine learning. In this paper, we design \underline{D}eep \underline{N}eural \underline{A}uctions (DNAs) to enable end-to-end auction learning by proposing a differentiable model to relax the discrete sorting operation, a key component in auctions. We optimize the performance metrics by developing deep models to efficiently extract contexts from auctions, providing rich features for auction design. We further integrate the game theoretical conditions within the model design, to guarantee the stability of the auctions. DNAs have been successfully deployed in the e-commerce advertising system at Taobao. Experimental evaluation results on both large-scale data set as well as online A/B test demonstrated that DNAs significantly outperformed other mechanisms widely adopted in industry.

cs.GT↗

arXiv2021

Exploration in Online Advertising Systems with Deep Uncertainty-Aware Learning

Modern online advertising systems inevitably rely on personalization methods, such as click-through rate (CTR) prediction. Recent progress in CTR prediction enjoys the rich representation capabilities of deep learning and achieves great success in large-scale industrial applications. However, these methods can suffer from lack of exploration. Another line of prior work addresses the exploration-exploitation trade-off problem with contextual bandit methods, which are recently less studied in the industry due to the difficulty in extending their flexibility with deep models. In this paper, we propose a novel Deep Uncertainty-Aware Learning (DUAL) method to learn CTR models based on Gaussian processes, which can provide predictive uncertainty estimations while maintaining the flexibility of deep neural networks. DUAL can be easily implemented on existing models and deployed in real-time systems with minimal extra computational overhead. By linking the predictive uncertainty estimation ability of DUAL to well-known bandit algorithms, we further present DUAL-based Ad-ranking strategies to boost up long-term utilities such as the social welfare in advertising systems. Experimental results on several public datasets demonstrate the effectiveness of our methods. Remarkably, an online A/B test deployed in the Alibaba display advertising platform shows an 8.2% social welfare improvement and an 8.0% revenue lift.

cs.IR↗

arXiv2021

Multi-Agent Cooperative Bidding Games for Multi-Objective Optimization in e-Commercial Sponsored Search

Bid optimization for online advertising from single advertiser's perspective has been thoroughly investigated in both academic research and industrial practice. However, existing work typically assume competitors do not change their bids, i.e., the wining price is fixed, leading to poor performance of the derived solution. Although a few studies use multi-agent reinforcement learning to set up a cooperative game, they still suffer the following drawbacks: (1) They fail to avoid collusion solutions where all the advertisers involved in an auction collude to bid an extremely low price on purpose. (2) Previous works cannot well handle the underlying complex bidding environment, leading to poor model convergence. This problem could be amplified when handling multiple objectives of advertisers which are practical demands but not considered by previous work. In this paper, we propose a novel multi-objective cooperative bid optimization formulation called Multi-Agent Cooperative bidding Games (MACG). MACG sets up a carefully designed multi-objective optimization framework where different objectives of advertisers are incorporated. A global objective to maximize the overall profit of all advertisements is added in order to encourage better cooperation and also to protect self-bidding advertisers. To avoid collusion, we also introduce an extra platform revenue constraint. We analyze the optimal functional form of the bidding formula theoretically and design a policy network accordingly to generate auction-level bids. Then we design an efficient multi-agent evolutionary strategy for model optimization. Offline experiments and online A/B tests conducted on the Taobao platform indicate both single advertiser's objective and global profit have been significantly improved compared to state-of-art methods.

cs.AI↗

arXiv2021

Towards a Better Tradeoff between Effectiveness and Efficiency in Pre-Ranking: A Learnable Feature Selection based Approach

In real-world search, recommendation, and advertising systems, the multi-stage ranking architecture is commonly adopted. Such architecture usually consists of matching, pre-ranking, ranking, and re-ranking stages. In the pre-ranking stage, vector-product based models with representation-focused architecture are commonly adopted to account for system efficiency. However, it brings a significant loss to the effectiveness of the system. In this paper, a novel pre-ranking approach is proposed which supports complicated models with interaction-focused architecture. It achieves a better tradeoff between effectiveness and efficiency by utilizing the proposed learnable Feature Selection method based on feature Complexity and variational Dropout (FSCD). Evaluations in a real-world e-commerce sponsored search system for a search engine demonstrate that utilizing the proposed pre-ranking, the effectiveness of the system is significantly improved. Moreover, compared to the systems with conventional pre-ranking models, an identical amount of computational resource is consumed.

cs.IR↗

arXiv2021

Explicit Semantic Cross Feature Learning via Pre-trained Graph Neural Networks for CTR Prediction

Cross features play an important role in click-through rate (CTR) prediction. Most of the existing methods adopt a DNN-based model to capture the cross features in an implicit manner. These implicit methods may lead to a sub-optimized performance due to the limitation in explicit semantic modeling. Although traditional statistical explicit semantic cross features can address the problem in these implicit methods, it still suffers from some challenges, including lack of generalization and expensive memory cost. Few works focus on tackling these challenges. In this paper, we take the first step in learning the explicit semantic cross features and propose Pre-trained Cross Feature learning Graph Neural Networks (PCF-GNN), a GNN based pre-trained model aiming at generating cross features in an explicit fashion. Extensive experiments are conducted on both public and industrial datasets, where PCF-GNN shows competence in both performance and memory-efficiency in various tasks.

cs.AI↗

arXiv2021

Cardiac Functional Analysis with Cine MRI via Deep Learning Reconstruction

Retrospectively gated cine (retro-cine) MRI is the clinical standard for cardiac functional analysis. Deep learning (DL) based methods have been proposed for the reconstruction of highly undersampled MRI data and show superior image quality and magnitude faster reconstruction time than CS-based methods. Nevertheless, it remains unclear whether DL reconstruction is suitable for cardiac function analysis. To address this question, in this study we evaluate and compare the cardiac functional values (EDV, ESV and EF for LV and RV, respectively) obtained from highly accelerated MRI acquisition using DL based reconstruction algorithm (DL-cine) with values from CS-cine and conventional retro-cine. To the best of our knowledge, this is the first work to evaluate the cine MRI with deep learning reconstruction for cardiac function analysis and compare it with other conventional methods. The cardiac functional values obtained from cine MRI with deep learning reconstruction are consistent with values from clinical standard retro-cine MRI.

eess.IV↗

arXiv2021

Accelerating 3D MULTIPLEX MRI Reconstruction with Deep Learning

Multi-contrast MRI images provide complementary contrast information about the characteristics of anatomical structures and are commonly used in clinical practice. Recently, a multi-flip-angle (FA) and multi-echo GRE method (MULTIPLEX MRI) has been developed to simultaneously acquire multiple parametric images with just one single scan. However, it poses two challenges for MULTIPLEX to be used in the 3D high-resolution setting: a relatively long scan time and the huge amount of 3D multi-contrast data for reconstruction. Currently, no DL based method has been proposed for 3D MULTIPLEX data reconstruction. We propose a deep learning framework for undersampled 3D MRI data reconstruction and apply it to MULTIPLEX MRI. The proposed deep learning method shows good performance in image quality and reconstruction time.

eess.IV↗

arXiv2021

A Portable, Self-Contained Neuroprosthetic Hand with Deep Learning-Based Finger Control

Objective: Deep learning-based neural decoders have emerged as the prominent approach to enable dexterous and intuitive control of neuroprosthetic hands. Yet few studies have materialized the use of deep learning in clinical settings due to its high computational requirements. Methods: Recent advancements of edge computing devices bring the potential to alleviate this problem. Here we present the implementation of a neuroprosthetic hand with embedded deep learning-based control. The neural decoder is designed based on the recurrent neural network (RNN) architecture and deployed on the NVIDIA Jetson Nano - a compacted yet powerful edge computing platform for deep learning inference. This enables the implementation of the neuroprosthetic hand as a portable and self-contained unit with real-time control of individual finger movements. Results: The proposed system is evaluated on a transradial amputee using peripheral nerve signals (ENG) with implanted intrafascicular microelectrodes. The experiment results demonstrate the system's capabilities of providing robust, high-accuracy (95-99%) and low-latency (50-120 msec) control of individual finger movements in various laboratory and real-world environments. Conclusion: Modern edge computing platforms enable the effective use of deep learning-based neural decoders for neuroprosthesis control as an autonomous system. Significance: This work helps pioneer the deployment of deep neural networks in clinical applications underlying a new class of wearable biomedical devices with embedded artificial intelligence.

cs.RO↗

arXiv2021

Computation Resource Allocation Solution in Recommender Systems

Recommender systems rely heavily on increasing computation resources to improve their business goal. By deploying computation-intensive models and algorithms, these systems are able to inference user interests and exhibit certain ads or commodities from the candidate set to maximize their business goals. However, such systems are facing two challenges in achieving their goals. On the one hand, facing massive online requests, computation-intensive models and algorithms are pushing their computation resources to the limit. On the other hand, the response time of these systems is strictly limited to a short period, e.g. 300 milliseconds in our real system, which is also being exhausted by the increasingly complex models and algorithms. In this paper, we propose the computation resource allocation solution (CRAS) that maximizes the business goal with limited computation resources and response time. We comprehensively illustrate the problem and formulate such a problem as an optimization problem with multiple constraints, which could be broken down into independent sub-problems. To solve the sub-problems, we propose the revenue function to facilitate the theoretical analysis, and obtain the optimal computation resource allocation strategy. To address the applicability issues, we devise the feedback control system to help our strategy constantly adapt to the changing online environment. The effectiveness of our method is verified by extensive experiments based on the real dataset from Taobao.com. We also deploy our method in the display advertising system of Alibaba. The online results show that our computation resource allocation solution achieves significant business goal improvement without any increment of computation cost, which demonstrates the efficacy of our method in real industrial practice.

eess.SY↗

arXiv2021

Optimizing Multiple Performance Metrics with Deep GSP Auctions for E-commerce Advertising

In e-commerce advertising, the ad platform usually relies on auction mechanisms to optimize different performance metrics, such as user experience, advertiser utility, and platform revenue. However, most of the state-of-the-art auction mechanisms only focus on optimizing a single performance metric, e.g., either social welfare or revenue, and are not suitable for e-commerce advertising with various, dynamic, difficult to estimate, and even conflicting performance metrics. In this paper, we propose a new mechanism called Deep GSP auction, which leverages deep learning to design new rank score functions within the celebrated GSP auction framework. These new rank score functions are implemented via deep neural network models under the constraints of monotone allocation and smooth transition. The requirement of monotone allocation ensures Deep GSP auction nice game theoretical properties, while the requirement of smooth transition guarantees the advertiser utilities would not fluctuate too much when the auction mechanism switches among candidate mechanisms to achieve different optimization objectives. We deployed the proposed mechanisms in a leading e-commerce ad platform and conducted comprehensive experimental evaluations with both offline simulations and online A/B tests. The results demonstrated the effectiveness of the Deep GSP auction compared to the state-of-the-art auction mechanisms.

cs.GT↗

arXiv2020

Does a pristine, unreconstructed SrTiO$_3$(001) surface exist?

The surfaces of perovskite oxides affect their functional properties, and while a bulk-truncated (1$\times$1) termination is generally assumed, its existence and stability is controversial. Here, such a surface is created by cleaving the prototypical SrTiO$_3$(001) in ultra-high vacuum, and its response to thermal annealing is observed. Atomically resolved nc-AFM shows that intrinsic point defects on the as-cleaved surface migrate at temperatures above 200\,$^\circ$C. At 400--500\,$^\circ$C, a disordered surface layer forms, albeit still with a (1$\times$1) pattern in LEED. Purely TiO$_2$-terminated surfaces, prepared by wet-chemical treatment, are also disordered despite their (1$\times$1) periodicity in LEED.

cond-mat.mtrl-sci↗

arXiv2020

Diffusing wave spectroscopy: a unified treatment on temporal sampling and speckle ensemble methods

Diffusing wave spectroscopy (DWS) is a well-known set of methods to measure the temporal dynamics of dynamic samples. In DWS, dynamic samples scatter the incident coherent light, and the information of the temporal dynamics is encoded in the scattered light. To record and analyze the light signal, there exist two types of methods - temporal sampling methods and speckle ensemble methods. Temporal sampling methods, including diffuse correlation spectroscopy (DCS), use one or multiple large bandwidth detectors to well sample and analyze the temporal light signal to infer the sample temporal dynamics. Speckle ensemble methods, including speckle visibility spectroscopy (SVS), use a high-pixel-count camera sensor to capture a speckle pattern and use the speckle contrast to infer sample temporal dynamics. In this paper, we theoretically and experimentally demonstrate that the decorrelation time (τ) measurement accuracy or SNR of the two types of methods has a unified and similar fundamental expression based on the number of independent observables (NIO) and the photon flux. Given a time measurement duration, NIO in temporal sampling methods is constrained by the measurement duration, while speckle ensemble methods can outperform by using simultaneous sampling channels to scale up NIO significantly. In the case of optical brain monitoring, the interplay of these factors favors speckle ensemble methods. We illustrate that this important engineering consideration is consistent with the previous research on blood pulsatile flow measurements, where a speckle ensemble method operating at 100-fold lower photon flux than a conventional temporal sampling system can achieve a comparable SNR.

physics.optics↗

arXiv2020

Efficient modeling of higher-order dependencies in networks: from algorithm to application for anomaly detection

Complex systems, represented as dynamic networks, comprise of components that influence each other via direct and/or indirect interactions. Recent research has shown the importance of using Higher-Order Networks (HONs) for modeling and analyzing such complex systems, as the typical Markovian assumption in developing the First Order Network (FON) can be limiting. This higher-order network representation not only creates a more accurate representation of the underlying complex system, but also leads to more accurate network analysis. In this paper, we first present a scalable and accurate model, BuildHON+, for higher-order network representation of data derived from a complex system with various orders of dependencies. Then, we show that this higher-order network representation modeled by BuildHON+ is significantly more accurate in identifying anomalies than FON, demonstrating a need for the higher-order network representation and modeling of complex systems for deriving meaningful conclusions.

cs.SI↗

arXiv2020

Uncovering the origin of the emitting states in Bi3+-activated CaMO3 (M = Zr, Sn, Ti) perovskites: metal-to-metal charge transfer versus s-p transitions

After more than a century of studies on the optical properties of Bi3+ ions, the assignment of the nature of the emissions and the bands of the absorption spectra remain ambiguous. Here, we report an insight into the spectroscopy of Bi3+-activated CaMO3 perovskites (M = Zr, Sn, and Ti), discussing the factors driving the metal-to-metal charge transfer and sp -> s2 transitions. With the aim to figure out the whole scenario, a combined experimental and theoretical approach is employed. The comparison between the temperature dependence of the photoluminescence emissions with the temperature dependence of the exciton energy of the systems has led to an unprecedented evidence of the chargetransfer character of the emitting states in Bi3+-activated phosphors. Low-temperature vacuum ultraviolet spectroscopy together with the design of the vacuum-referred binding energy diagram of the luminescent center is exploited to shed light on the origin of the absorption bands. In addition, the X-ray absorption near the edge structure unambiguously confirmed the stabilization of Bi3+ in the Ca2+ site in both CaSnO3 and CaZrO3 perovskites. This breakthrough into the understanding of the excited-state origin of Bi3+ could pave the way toward the design of a new generation of effective Bi3+-activated phosphors.

cond-mat.mtrl-sci↗

arXiv2020

Network analysis of ballast-mediated species transfer reveals important introduction and dispersal patterns in the Arctic

Rapid climate change has wide-ranging implications for the Arctic region, including sea ice loss, increased geopolitical attention, and expanding economic activity, including a dramatic increase in shipping activity. As a result, the risk of harmful non-native marine species being introduced into this critical region will increase unless policy and management steps are implemented in response. Using big data about shipping, ecoregions, and environmental conditions, we leverage network analysis and data mining techniques to assess, visualize, and project ballast water-mediated species introductions into the Arctic and dispersal of non-native species within the Arctic. We first identify high-risk connections between the Arctic and non-Arctic ports that could be sources of non-native species over 15 years (1997-2012) and observe the emergence of shipping hubs in the Arctic where the cumulative risk of non-native species introduction is increasing. We then consider how environmental conditions can constrain this Arctic introduction network for species with different physiological limits, thus providing a species-level tool for decision-makers. Next, we focus on within-Arctic ballast-mediated species dispersal where we use higher-order network analysis to identify critical shipping routes that may facilitate species dispersal within the Arctic. The risk assessment and projection framework we propose could inform risk-based assessment and management of ship-borne invasive species in the Arctic.

q-bio.PE↗

arXiv2020

Joint and Progressive Subspace Analysis (JPSA) with Spatial-Spectral Manifold Alignment for Semi-Supervised Hyperspectral Dimensionality Reduction

Conventional nonlinear subspace learning techniques (e.g., manifold learning) usually introduce some drawbacks in explainability (explicit mapping) and cost-effectiveness (linearization), generalization capability (out-of-sample), and representability (spatial-spectral discrimination). To overcome these shortcomings, a novel linearized subspace analysis technique with spatial-spectral manifold alignment is developed for a semi-supervised hyperspectral dimensionality reduction (HDR), called joint and progressive subspace analysis (JPSA). The JPSA learns a high-level, semantically meaningful, joint spatial-spectral feature representation from hyperspectral data by 1) jointly learning latent subspaces and a linear classifier to find an effective projection direction favorable for classification; 2) progressively searching several intermediate states of subspaces to approach an optimal mapping from the original space to a potential more discriminative subspace; 3) spatially and spectrally aligning manifold structure in each learned latent subspace in order to preserve the same or similar topological property between the compressed data and the original data. A simple but effective classifier, i.e., nearest neighbor (NN), is explored as a potential application for validating the algorithm performance of different HDR approaches. Extensive experiments are conducted to demonstrate the superiority and effectiveness of the proposed JPSA on two widely-used hyperspectral datasets: Indian Pines (92.98\%) and the University of Houston (86.09\%) in comparison with previous state-of-the-art HDR methods. The demo of this basic work (i.e., ECCV2018) is openly available at https://github.com/danfenghong/ECCV2018_J-Play.

cs.CV↗

arXiv2020

Learning to Infer User Hidden States for Online Sequential Advertising

To drive purchase in online advertising, it is of the advertiser's great interest to optimize the sequential advertising strategy whose performance and interpretability are both important. The lack of interpretability in existing deep reinforcement learning methods makes it not easy to understand, diagnose and further optimize the strategy. In this paper, we propose our Deep Intents Sequential Advertising (DISA) method to address these issues. The key part of interpretability is to understand a consumer's purchase intent which is, however, unobservable (called hidden states). In this paper, we model this intention as a latent variable and formulate the problem as a Partially Observable Markov Decision Process (POMDP) where the underlying intents are inferred based on the observable behaviors. Large-scale industrial offline and online experiments demonstrate our method's superior performance over several baselines. The inferred hidden states are analyzed, and the results prove the rationality of our inference.

cs.AI↗

arXiv2020

Real-Time Cardiac Cine MRI with Residual Convolutional Recurrent Neural Network

Real-time cardiac cine MRI does not require ECG gating in the data acquisition and is more useful for patients who can not hold their breaths or have abnormal heart rhythms. However, to achieve fast image acquisition, real-time cine commonly acquires highly undersampled data, which imposes a significant challenge for MRI image reconstruction. We propose a residual convolutional RNN for real-time cardiac cine reconstruction. To the best of our knowledge, this is the first work applying deep learning approach to Cartesian real-time cardiac cine reconstruction. Based on the evaluation from radiologists, our deep learning model shows superior performance than compressed sensing.

eess.IV↗