As a critical component for online advertising and marking, click-through rate (CTR) prediction has draw lots of attentions from both industry and academia field. Recently, the deep learning has become the mainstream methodological choice for CTR. De
spite of sustainable efforts have been made, existing approaches still pose several challenges. On the one hand, high-order interaction between the features is under-explored. On the other hand, high-order interactions may neglect the semantic information from the low-order fields. In this paper, we proposed a novel prediction method, named FINT, that employs the Field-aware INTeraction layer which captures high-order feature interactions while retaining the low-order field information. To empirically investigate the effectiveness and robustness of the FINT, we perform extensive experiments on the three realistic databases: KDD2012, Criteo and Avazu. The obtained results demonstrate that the FINT can significantly improve the performance compared to the existing methods, without increasing the amount of computation required. Moreover, the proposed method brought about 2.72% increase to the advertising revenue of a big online video app through A/B testing. To better promote the research in CTR field, we released our code as well as reference implementation at: https://github.com/zhishan01/FINT.
Due to the development of graph neural network models, like graph convolutional network (GCN), graph-based representation learning methods have made great progress in recommender systems. However, the data sparsity is still a challenging problem that
graph-based methods are confronted with. Recent works try to solve this problem by utilizing the side information. In this paper, we introduce easily accessible textual information to alleviate the negative effects of data sparsity. Specifically, to incorporate with rich textual knowledge, we utilize a pre-trained context-awareness natural language processing model to initialize the embeddings of text nodes. By a GCN-based node information propagation on the constructed heterogeneous graph, the embeddings of users and items can finally be enriched by the textual knowledge. The matching function used by most graph-based representation learning methods is the inner product, this linear operation can not fit complex semantics well. We design a predictive network, which can combine the graph-based representation learning with the matching function learning, and demonstrate that this predictive architecture can gain significant improvements. Extensive experiments are conducted on three public datasets and the results verify the superior performance of our method over several baselines.
Throughout this paper, a persistence diagram ${cal P}$ is composed of a set $P$ of planar points (each corresponding to a topological feature) above the line $Y=X$, as well as the line $Y=X$ itself, i.e., ${cal P}=Pcup{(x,y)|y=x}$. Given a set of per
sistence diagrams ${cal P}_1,...,{cal P}_m$, for the data reduction purpose, one way to summarize their topological features is to compute the {em center} ${cal C}$ of them first under the bottleneck distance. We consider two discre
Plasmonic beam collimation effect has been thoroughly investigated based on the well-known nanometer-scale bulls eye structure formed by complex and high-cost fabrication processes. In this work, we report our effort for attaining beam collimation us
ing an anisotropic metamaterial (AMM) slab that consists of a stack of alternating metal/dielectric layers and an integrated top metal grating. The results show that AMM slab allows creating the beam collimation effect similar to that of the bulls eye structure, an enabling technology for practical application due to its simple architecture and cost benefits. The excitation of surface plasmons at the AMM/air interface is derived. The structure of the AMM slab and its impact on beaming performance were analyzed using the effective medium theory and Finite Element Method.
