Existing online advertising systems employ separate models for each task and site, resulting in a large number of models that require significant computing power and human effort to train and deploy. Moreover, separate models have limitations in sharing cross-scenario information. To address these issues, we propose a unified sequential recommendation model called SCRIPT. It takes cross-scenario user behavior sequences as input and explicitly incorporates meta information that characterizes scenario features, such as domain, site, and behavior types. Inspired by the advances of the pretrain and prompt paradigm, we generate scenario-aware and personalized prompts based on the user profile and meta information of candidate items. This allows the model to leverage the knowledge learned during pre-training and adapt it to serve different downstream tasks. Extensive experiments on two public dataset and a production dataset demonstrate that our model achieves state-of-the-art performance on multiple downstream recommendation tasks.

Built on the WeChat social platform, WeChat Mini-Programs are widely used by more than 400 million users every day. Consequently, the reliability of Mini-Programs is particularly crucial. However, WeChat Mini-Programs suffer from various bugs related to execution environment, lifecycle management, asynchronous mechanism, etc. These bugs have seriously affected users' experience and caused serious impacts.

Hyperparameter optimization (HPO), aiming at automatically searching optimal hyperparameter configurations, has attracted increasing attention in the machine learning community. HPO generally suffers from high searching costs when dealing with large-scale real-world datasets since training the model with a certain hyperparameter configuration is time-consuming. Existing works suggest sampling subsets uniformly to represent the full dataset for HPO but ignoring the complex and dynamic distribution in real-world scenarios and the exploration of hyperparameter transfer. To tackle this problem, we propose a novel meta hyperparameter optimization model with an adversarial proxy subsets sampling strategy (Meta-HPO), which can transfer hyperparameters optimized on the sampled proxy subsets to the full dataset and further adapt to the new data in an out-of-sample updating manner. In particular, a perturbation-aware adversarial sampling strategy is designed to select the proxy subsets that significantly influence the model performance. With the searched hyperparameter configurations and corresponding performance scores on the proxy subsets, we propose a meta transfer framework, named "hp-learner'', to build the connection between the distribution of dataset and the optimal hyperparameter configuration. Our Meta-HPO provides a flexible and efficient hyperparameter optimization algorithm. Extensive experiments on real-world datasets validate the advantages of our proposed Meta-HPO model against existing state-of-the-art benchmarks.

Node.js has become a widely-used event-driven architecture for server-side and desktop applications. Node.js provides an effective asynchronous event-driven programming model, and supports asynchronous tasks and multi-priority event queues. Unexpected races among events and asynchronous tasks can cause severe consequences. Existing race detection approaches in Node.js applications mainly adopt random fuzzing technique, and can miss races due to large schedule space.In this paper, we propose a dynamic race detection approach NRace for Node.js applications. In NRace, we build precise happens-before relations among events and asynchronous tasks in Node.js applications, which also take multi-priority event queues into consideration. We further develop a predictive race detection technique based on these relations. We evaluate NRace on 10 realworld Node.js applications. The experimental result shows that NRace can precisely detect 6 races, and 5 of them have been confirmed by developers.

Online ad targeting can be formulated as a problem of learning the relevance ranking among possible audiences for a given ad. It has to deal with the massive number of negative,i.e., non-interacted, instances in impression data due to the nature of this service, and thus suffers from data imbalance problem. In this work, we tackle this problem by improving the quality of negative instances used in training the targeting model. We propose to enhance the generalization capability by introducing unobserved data as possible negative instances, and extract more reliable negative instances from the observed negatives in impression data. However, this idea is non-trivial to implement because of the limited learning signal and existing noise signal. To this end, we design a novel RNIG method (short for Representative Negative Instance Generator) to leverage feature matching technique. It aims to generate reliable negative instances that are similar to the observed negatives and further improves the representativeness of generated negatives by matching the most important feature. Extensive experiments on the real-world ad targeting dataset show that our RNIG model has achieved a relative improvement of more than 5%.

JavaScript is one of the most popular programming languages. WeChat Mini-Program is a large ecosystem of JavaScript applications that runs on the WeChat platform. Millions of Mini-Programs are accessed by WeChat users every week. Consequently, the performance and robustness of Mini-Programs are particularly important. Unfortunately, many Mini-Programs suffer from various defects and performance problems. Dynamic analysis is a useful technique to pinpoint application defects. However, due to the dynamic features of the JavaScript language and the complexity of the runtime environment, dynamic analysis techniques were rarely used to improve the quality of JavaScript applications running on industrial platforms such as WeChat Mini-Program previously. In this work, we report our experience of extending Jalangi, a dynamic analysis framework for JavaScript applications developed by academia, and applying the extended version, named WeJalangi, to diagnose defects in WeChat Mini-Programs. WeJalangi is compatible with existing dynamic analysis tools such as DLint, Smemory, and JITProf. We implemented a null pointer checker on WeJalangi and tested the tool's usability on 152 open-source Mini-Programs. We also conducted a case study in Tencent by applying WeJalangi on six popular commercial Mini-Programs. In the case study, WeJalangi accurately located six null pointer issues and three of them haven't been discovered previously. All of the reported defects have been confirmed by developers and testers.

A large number of new buyers are often acquired by merchants during promotions. However, many of the attracted buyers are one-time deal hunters, and the promotions may have little long-lasting impact on sales. It is important for merchants to identify who can be converted to regular loyal buyers and then target them to reduce promotion cost and increase the return on investment (ROI). At International Joint Conferences on Artificial Intelligence (IJCAI) 2015, Alibaba hosted an international competition for repeat buyer prediction based on the sales data of the ``Double 11" shopping event in 2014 at Tmall.com. We won the first place at stage 1 of the competition out of 753 teams. In this paper, we present our winning solution, which consists of comprehensive feature engineering and model training. We created profiles for users, merchants, brands, categories, items and their interactions via extensive feature engineering. These profiles are not only useful for this particular prediction task, but can also be used for other important tasks in e-commerce, such as customer segmentation, product recommendation, and customer base augmentation for brands. Feature engineering is often the most important factor for the success of a prediction task, but not much work can be found in the literature on feature engineering for prediction tasks in e-commerce. Our work provides some useful hints and insights for data science practitioners in e-commerce.

This paper offers a characterization of fundamental limits on the classification and reconstruction of high-dimensional signals from low-dimensional features, in the presence of side information. We consider a scenario where a decoder has access both to linear features of the signal of interest and to linear features of the side information signal; while the side information may be in a compressed form, the objective is recovery or classification of the primary signal, not the side information. The signal of interest and the side information are each assumed to have (distinct) latent discrete labels; conditioned on these two labels, the signal of interest and side information are drawn from a multivariate Gaussian distribution that correlates the two. With joint probabilities on the latent labels, the overall signal-(side information) representation is defined by a Gaussian mixture model. By considering bounds to the misclassification probability associated with the recovery of the underlying signal label, and bounds to the reconstruction error associated with the recovery of the signal of interest itself, we then provide sharp sufficient and/or necessary conditions for these quantities to approach zero when the covariance matrices of the Gaussians are nearly low rank. These conditions, which are reminiscent of the well-known Slepian-Wolf and Wyner-Ziv conditions, are the function of the number of linear features extracted from signal of interest, the number of linear features extracted from the side information signal, and the geometry of these signals and their interplay. Moreover, on assuming that the signal of interest and the side information obey such an approximately low-rank model, we derive the expansions of the reconstruction error as a function of the deviation from an exactly low-rank model; such expansions also allow the identification of operational regimes, where the impact of side information on signal reconstruction is most relevant. Our framework, which offers a principled mechanism to integrate side information in high-dimensional data problems, is also tested in the context of imaging applications. In particular, we report state-of-theart results in compressive hyperspectral imaging applications, where the accompanying side information is a conventional digital photograph.

This paper offers a characterization of performance limits for classification and reconstruction of high-dimensional signals from noisy compressive measurements, in the presence of side information. We assume the signal of interest and the side information signal are drawn from a correlated mixture of distributions/components, where each component associated with a specific class label follows a Gaussian mixture model (GMM). We provide sharp sufficient and/or necessary conditions for the phase transition of the misclassification probability and the reconstruction error in the low-noise regime. These conditions, which are reminiscent of the well-known Slepian-Wolf and Wyner-Ziv conditions, are a function of the number of measurements taken from the signal of interest, the number of measurements taken from the side information signal, and the geometry of these signals and their interplay.

Compressive sensing of signals drawn from a Gaussian mixture model (GMM) admits closed-form minimum mean squared error reconstruction from incomplete linear measurements. An accurate GMM signal model is usually not available a priori, because it is difficult to obtain training signals that match the statistics of the signals being sensed. We propose to solve that problem by learning the signal model in situ, based directly on the compressive measurements of the signals, without resorting to other signals to train a model. A key feature of our method is that the signals being sensed are treated as random variables and are integrated out in the likelihood. We derive a maximum marginal likelihood estimator (MMLE) that maximizes the likelihood of the GMM of the underlying signals given only their linear compressive measurements. We extend the MMLE to a GMM with dominantly low-rank covariance matrices, to gain computational speedup. We report extensive experimental results on image inpainting, compressive sensing of high-speed video, and compressive hyperspectral imaging (the latter two based on real compressive cameras). The results demonstrate that the proposed methods outperform state-of-the-art methods by significant margins.

A simple and inexpensive (low-power and low-bandwidth) modification is made to a conventional off-the-shelf color video camera, from which we recover multiple color frames for each of the original measured frames, and each of the recovered frames can be focused at a different depth. The recovery of multiple frames for each measured frame is made possible via high-speed coding, manifested via translation of a single coded aperture, the inexpensive translation is constituted by mounting the binary code on a piezoelectric device. To simultaneously recover depth information, a liquid lens is modulated at high speed, via a variable voltage. Consequently, during the aforementioned coding process, the liquid lens allows the camera to sweep the focus through multiple depths. In addition to designing and implementing the camera, fast recovery is achieved by an anytime algorithm exploiting the group-sparsity of wavelet/DCT coefficients.

A Gaussian mixture model (GMM)-based algorithm is proposed for video reconstruction from temporally compressed video measurements. The GMM is used to model spatio-temporal video patches, and the reconstruction can be efficiently computed based on analytic expressions. The GMM-based inversion method benefits from online adaptive learning and parallel computation. We demonstrate the efficacy of the proposed inversion method with videos reconstructed from simulated compressive video measurements, and from a real compressive video camera. We also use the GMM as a tool to investigate adaptive video compressive sensing, i.e., adaptive rate of temporal compression.

A Gaussian Mixture Model (GMM)-based algorithm is proposed for video reconstruction from temporal compressed measurements. The GMM is used to model spatio-temporal video patches, and the reconstruction can be efficiently computed based on analytic expressions. The developed GMM reconstruction method benefits from online adaptive learning and parallel computation. We demonstrate the efficacy of the proposed GMM with videos reconstructed from simulated compressive video measurements and from a real compressive video camera.

This paper introduces the concept of adaptive temporal compressive sensing (CS) for video. We propose a CS algorithm to adapt the compression ratio based on the scene's temporal complexity, computed from the compressed data, without compromising the quality of the reconstructed video. The temporal adaptivity is manifested by manipulating the integration time of the camera, opening the possibility to realtime implementation. The proposed algorithm is a generalized temporal CS approach that can be incorporated with a diverse set of existing hardware systems.

This paper describes an improved algorithm for the numerical solution to the support vector machine (SVM) classification problem for all values of the regularization parameter C . The algorithm is motivated by the work of Hastie and follows the main idea of tracking the optimality conditions of the SVM solution for ascending value of C . It differs from Hastie's approach in that the tracked path is not assumed to be 1-D. Instead, a multidimensional feasible space for the optimality condition is used to solve the tracking problem. Such a treatment allows the algorithm to properly handle data sets which Hastie's approach fails. These data sets are characterized by the presence of linearly dependent points (in the kernel space), duplicate points, or nearly duplicate points. Such data sets are quite common among many real-world data, especially those with nominal features. Other contributions of this paper include a unifying formulation of the tracking process in the form of a linear programming problem, update formula for the linear programs, considerations that guard against accumulation of errors resulting from the use of incremental updates, and routines to speed up the algorithm. The algorithm is implemented under the Matlab environment and is available for download. Experiments with several data sets including data set having up to several thousand data points are reported.