Search

Click-through rate (CTR) prediction is one of the most central tasks in online advertising systems. Recent deep learning-based models that exploit feature embedding and high-order data nonlinearity have shown dramatic successes in CTR prediction. However, these models work poorly on cold-start ads with new IDs, whose embeddings are not well learned yet. In this paper, we propose Graph Meta Embedding (GME) models that can rapidly learn how to generate desirable initial embeddings for new ad IDs based on graph neural networks and meta learning. Previous works address this problem from the new ad itself, but ignore possibly useful information contained in existing old ads. In contrast, GMEs simultaneously consider two information sources: the new ad and existing old ads. For the new ad, GMEs exploit its associated attributes. For existing old ads, GMEs first build a graph to connect them with new ads, and then adaptively distill useful information. We propose three specific GMEs from different perspectives to explore what kind of information to use and how to distill information. In particular, GME-P uses Pre-trained neighbor ID embeddings, GME-G uses Generated neighbor ID embeddings and GME-A uses neighbor Attributes. Experimental results on three real-world datasets show that GMEs can significantly improve the prediction performance in both cold-start (i.e., no training data is available) and warm-up (i.e., a small number of training samples are collected) scenarios over five major deep learning-based CTR prediction models. GMEs can be applied to conversion rate (CVR) prediction as well., Comment: SIGIR 2021

Click-through rate (CTR) prediction is a critical task in online advertising systems. Existing works mainly address the single-domain CTR prediction problem and model aspects such as feature interaction, user behavior history and contextual information. Nevertheless, ads are usually displayed with natural content, which offers an opportunity for cross-domain CTR prediction. In this paper, we address this problem and leverage auxiliary data from a source domain to improve the CTR prediction performance of a target domain. Our study is based on UC Toutiao (a news feed service integrated with the UC Browser App, serving hundreds of millions of users daily), where the source domain is the news and the target domain is the ad. In order to effectively leverage news data for predicting CTRs of ads, we propose the Mixed Interest Network (MiNet) which jointly models three types of user interest: 1) long-term interest across domains, 2) short-term interest from the source domain and 3) short-term interest in the target domain. MiNet contains two levels of attentions, where the item-level attention can adaptively distill useful information from clicked news / ads and the interest-level attention can adaptively fuse different interest representations. Offline experiments show that MiNet outperforms several state-of-the-art methods for CTR prediction. We have deployed MiNet in UC Toutiao and the A/B test results show that the online CTR is also improved substantially. MiNet now serves the main ad traffic in UC Toutiao., Comment: CIKM 2020

Spirooxindoles bearing a 1-azabicyclo[5.3.0]decane moiety were synthesized in one step via direct functionalization of the azepane without a transition metal or oxidants. This is an efficient process for the synthesis of fused 7/5-heterobicyclic systems in one step. Furthermore, cycloaddition of the in situ generated azomethine ylide only proceeded for alkenyl sulfone dipolarophiles.

Click-through rate (CTR) prediction is a critical task in online advertising systems. A large body of research considers each ad independently, but ignores its relationship to other ads that may impact the CTR. In this paper, we investigate various types of auxiliary ads for improving the CTR prediction of the target ad. In particular, we explore auxiliary ads from two viewpoints: one is from the spatial domain, where we consider the contextual ads shown above the target ad on the same page; the other is from the temporal domain, where we consider historically clicked and unclicked ads of the user. The intuitions are that ads shown together may influence each other, clicked ads reflect a user's preferences, and unclicked ads may indicate what a user dislikes to certain extent. In order to effectively utilize these auxiliary data, we propose the Deep Spatio-Temporal neural Networks (DSTNs) for CTR prediction. Our model is able to learn the interactions between each type of auxiliary data and the target ad, to emphasize more important hidden information, and to fuse heterogeneous data in a unified framework. Offline experiments on one public dataset and two industrial datasets show that DSTNs outperform several state-of-the-art methods for CTR prediction. We have deployed the best-performing DSTN in Shenma Search, which is the second largest search engine in China. The A/B test results show that the online CTR is also significantly improved compared to our last serving model., Comment: Accepted by KDD 2019

Click-through rate (CTR) prediction is a critical task in online advertising systems. Models like Deep Neural Networks (DNNs) are simple but stateless. They consider each target ad independently and cannot directly extract useful information contained in users' historical ad impressions and clicks. In contrast, models like Recurrent Neural Networks (RNNs) are stateful but complex. They model temporal dependency between users' sequential behaviors and can achieve improved prediction performance than DNNs. However, both the offline training and online prediction process of RNNs are much more complex and time-consuming. In this paper, we propose Memory Augmented DNN (MA-DNN) for practical CTR prediction services. In particular, we create two external memory vectors for each user, memorizing high-level abstractions of what a user possibly likes and dislikes. The proposed MA-DNN achieves a good compromise between DNN and RNN. It is as simple as DNN, but has certain ability to exploit useful information contained in users' historical behaviors as RNN. Both offline and online experiments demonstrate the effectiveness of MA-DNN for practical CTR prediction services. Actually, the memory component can be augmented to other models as well (e.g., the Wide&Deep model)., Accepted by DLP-KDD 2019 (1st International Workshop on Deep Learning Practice for High-Dimensional Sparse Data; with KDD 2019). arXiv admin note: text overlap with arXiv:1906.04365, arXiv:1906.03776

Click-through rate (CTR) prediction is a critical task in online advertising systems. Most existing methods mainly model the feature-CTR relationship and suffer from the data sparsity issue. In this paper, we propose DeepMCP, which models other types of relationships in order to learn more informative and statistically reliable feature representations, and in consequence to improve the performance of CTR prediction. In particular, DeepMCP contains three parts: a matching subnet, a correlation subnet and a prediction subnet. These subnets model the user-ad, ad-ad and feature-CTR relationship respectively. When these subnets are jointly optimized under the supervision of the target labels, the learned feature representations have both good prediction powers and good representation abilities. Experiments on two large-scale datasets demonstrate that DeepMCP outperforms several state-of-the-art models for CTR prediction., Comment: Accepted by IJCAI 2019

A Cs2CO3-promoted Michael addition-[2,3]-sigmatropic rearrangement domino reaction between arenesulfonylindole and sulfur ylide has been developed. This reaction affords a facile method for the synthesis of 3-substituted indoles with a homoallyl sulfide moiety. In this domino sequence, two C−C bonds and one C−C bond cleavage were formed.

A catalyst-free domino reaction was developed for the synthesis of 3-(cyclopentenone)oxindoles. This method is the first example of a phosphine-ylide-initiated Wittig/Michael addition/Wittig domino sequence. The mild reaction conditions and broad functional groups tolerance make it highly valuable for synthesizing 3-(cyclopentenone)oxindoles.

Correction for 'Direct N-H/α,α,β,β-C(sp

A protocol for the direct functionalization of N-H/α,α,β,β-C(sp

A DABCO catalyzed domino reaction between 3-oxo-4-(2-oxoindolin-3-ylidene) butanoates and allenoates furnished 2,3,5-substituted tetrahydrofuran furan derivatives with oxindole moieties and two exocyclic double bonds in high yield. During this reaction, two carbon atoms and one oxygen atom of 3-oxo-4-(2-oxoindolin-3-ylidene) butanoates participated. Moreover, four isomers were synthesized and two of them can be isolated in this reaction.

A DABCO-catalyzed domino reaction between methyleneoxindoles and allenoates which enables the direct synthesis of spirooxindoles is reported. This is the first example of a non-substituted allenoate to act as a four-carbon synthon in a tertiary amine-catalyzed reaction.

We first reported an example of diverse synthesis of pyrano[2,3-b]indol and dihydropyrano[2,3-b]indol from the same starting materials. In these domino reactions, we can control the reaction conditions to give three new products: pyrano[2,3-b]indol, dihydropyrano[2,3-b]indol with E or Z exocyclic double bond. Using DABCO as catalyst in THF, dihydropyrano[2,3-b]indol with E exocyclic double bond and pyrano[2,3-b]indol were obtained at room temperature and 65 °C, respectively. In contrast, when DMAP was selected as catalyst, dihydropyrano[2,3-b]indol with Z exocyclic double bond was formed in toluene at 80 °C.

A DABCO-catalyzed domino reaction between methyleneoxindoles and allenoates which enables the direct synthesis of spirooxindoles is reported. This is the first example of a non-substituted allenoate to act as a four-carbon synthon in a tertiary amine-catalyzed reaction.

A catalyst-free domino reaction was developed for the synthesis of 3-(cyclopentenone)oxindoles. This method is the first example of a phosphine-ylide-initiated Wittig/Michael addition/Wittig domino sequence. The mild reaction conditions and broad functional groups tolerance make it highly valuable for synthesizing 3-(cyclopentenone)oxindoles.

A DABCO catalyzed domino reaction between 3-oxo-4-(2-oxoindolin-3-ylidene) butanoates and allenoates furnished 2,3,5-substituted tetrahydrofuran furan derivatives with oxindole moieties and two exocyclic double bonds in high yield. During this reaction, two carbon atoms and one oxygen atom of 3-oxo-4-(2-oxoindolin-3-ylidene) butanoates participated. Moreover, four isomers were synthesized and two of them can be isolated in this reaction.

Based on the difference of refractive index by different wavelengths in optical components, a novel method for measuring the optical homogeneity of optical components by using dual-wavelength phase-shifting digital holography has been proposed and verified by computer simulation. Meanwhile, this method could measure the surface shape of optical components accurately while we do not need to measure the front surface and rear surface of sample separately. Furthermore, the phase of reference wave and phase distortion caused by the object wave could be eliminated automatically, so the method has a function of automated optical wavefront distortion compensation, which can improve the measurement accuracy.

An optimized iterative algorithm for generalized phase-shifting interferometry is proposed. Using 1/4 plate as phase-shifter, we derive the phase distribution with the initial phase shift of π/2, then a more accurate phase shift can be obtained with the obtained phase distribution. The whole iteration includes the above two steps. The exact phase shift is near π/2, so fewer iterative steps are needed. And this method doesn't have the limitation that iterative time is apt to be influenced by iterative step length. Therefore, our algorithm improves the efficiency as well as the accuracy. Computer simulation and optical experiment verified the feasibility and superiority of this algorithm.