Estimating click-through rate (CTR) accurately has an essential impact on improving user experience and revenue in sponsored search. For CTR prediction model, it is necessary to make out user's real-time search intention. Most of the current work is to mine their intentions based on users' real-time behaviors. However, it is difficult to capture the intention when user behaviors are sparse, causing the behavior sparsity problem. Moreover, it is difficult for user to jump out of their specific historical behaviors for possible interest exploration, namely weak generalization problem. We propose a new approach Graph Intention Network (GIN) based on co-occurrence commodity graph to mine user intention. By adopting multi-layered graph diffusion, GIN enriches user behaviors to solve the behavior sparsity problem. By introducing co-occurrence relationship of commodities to explore the potential preferences, the weak generalization problem is also alleviated. To the best of our knowledge, the GIN method is the first to introduce graph learning for user intention mining in CTR prediction and propose end-to-end joint training of graph learning and CTR prediction tasks in sponsored search. At present, GIN has achieved excellent offline results on the real-world data of the e-commerce platform outperforming existing deep learning models, and has been running stable tests online and achieved significant CTR improvements. CCS CONCEPTS• Information systems → Sponsored search advertising; Recommender systems.

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, such features still suffer 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. CCS CONCEPTS• Information systems → Recommender systems.

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 realworld 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. CCS CONCEPTS• Information systems → Learning to rank.

The influence of optical parameters on the performance of closed-loop optical voltage sensors (OVSs) based on Pockels effect is analyzed and a control algorithm is proposed to suppress the nonlinearity caused by the unideal parameters of optical devices for optimizing the detection precision of OVSs. First, a quantified model of the feedback phase demonstrates how the optical parameters of optical devices (including light source, polarizer, 45° fusion point, Faraday rotator and half-wave plate) result in the nonlinearity of closed-loop OVSs. Then, the parameter indexes of different optical devices are put forward to instruct the manufacturing process of the optical system. Furthermore, a closed-loop control algorithm is investigated to improve the measurement accuracy of nonlinear OVSs considering the unideal parameters. The experiment results indicate that additional bias caused by undesirable optical parameters is obviously decreased so that the measurement accuracy of OVSs satisfies the demand of IEC60044-3 for 0.1 level measurement accuracy, which verifies the effectiveness and correctness of the methods for suppressing the impact of unideal optical parameters on OVSs.

No abstract

Learning accurate object detectors often requires large-scale training data with precise object bounding boxes. However, labeling such data is expensive and time-consuming. As the crowd-sourcing labeling process and the ambiguities of the objects may raise noisy bounding box annotations, the object detectors will suffer from the degenerated training data. In this work, we aim to address the challenge of learning robust object detectors with inaccurate bounding boxes. Inspired by the fact that localization precision suffers significantly from inaccurate bounding boxes while classification accuracy is less affected, we propose leveraging classification as a guidance signal for refining localization results. Specifically, by treating an object as a bag of instances, we introduce an Object-Aware Multiple Instance Learning approach (OA-MIL), featured with object-aware instance selection and object-aware instance extension. The former aims to select accurate instances for training, instead of directly using inaccurate box annotations. The latter focuses on generating high-quality instances for selection. Extensive experiments on synthetic noisy datasets (i.e., noisy PASCAL VOC and MS-COCO) and a real noisy wheat head dataset demonstrate the effectiveness of our OA-MIL. Code is available at https://github.com/cxliu0/OA-MIL.

Automatic image annotation plays a significant role in image understanding, retrieval, classification, and indexing. Today, it is becoming increasingly important in order to annotate large-scale social media images from content-sharing websites and social networks. These social images are usually annotated by user-provided low-quality tags. The topic model is considered as a promising method to describe these weak-labeling images by learning latent representations of training samples. The recent annotation methods based on topic models have two shortcomings. First, they are difficult to scale to a large-scale image dataset. Second, they can not be used to online image repository because of continuous addition of new images and new tags. In this paper, we propose a novel annotation method based on topic model, namely local learning-based probabilistic latent semantic analysis (LL-PLSA), to solve the above problems. The key idea is to train a weighted topic model for a given test image on its semantic neighborhood consisting of a fixed number of semantically and visually similar images. This method can scale to a large-scale image database, as training samples involved in modeling are a few nearest neighbors rather than the entire database. Moreover, this proposed topic model, online customized for the test image, naturally addresses the issue of continuous addition of new images and new tags in a database. Extensive experiments on three benchmark datasets demonstrate that the proposed method significantly outperforms the state-of-the-art especially in terms of overall metrics. INDEX TERMS Automatic image annotation, image retrieval, probabilistic latent semantic analysis, topic model.

No abstract