Click-Through Rate (CTR) prediction plays an important role in many industrial applications, such as online advertising and recommender systems. How to capture users' dynamic and evolving interests from their behavior sequences remains a continuous research topic in the CTR prediction. However, most existing studies overlook the intrinsic structure of the sequences: the sequences are composed of sessions, where sessions are user behaviors separated by their occurring time. We observe that user behaviors are highly homogeneous in each session, and heterogeneous cross sessions. Based on this observation, we propose a novel CTR model named Deep Session Interest Network (DSIN) that leverages users' multiple historical sessions in their behavior sequences. We first use self-attention mechanism with bias encoding to extract users' interests in each session. Then we apply Bi-LSTM to model how users' interests evolve and interact among sessions. Finally, we employ the local activation unit to adaptively learn the influences of various session interests on the target item. Experiments are conducted on both advertising and production recommender datasets and DSIN outperforms other stateof-the-art models on both datasets.
We explore end-to-end trained differentiable models that integrate natural logic with neural networks, aiming to keep the backbone of natural language reasoning based on the natural logic formalism while introducing subsymbolic vector representations and neural components. The proposed model adapts module networks to model natural logic operations, which is enhanced with a memory component to model contextual information. Experiments show that the proposed framework can effectively model monotonicity-based reasoning, compared to the baseline neural network models without built-in inductive bias for monotonicity-based reasoning. Our proposed model shows to be robust when transferred from upward to downward inference. We perform further analyses on the performance of the proposed model on aggregation, showing the effectiveness of the proposed subcomponents on helping achieve better intermediate aggregation performance.
Ru/BC multilayer mirrors are used for hard X-ray monochromators with moderate spectral resolution and high integral flux. To overcome the problem of large compressive stress inherent in Ru/BC multilayers, a reactive sputtering technique using a mixture working gas of argon and nitrogen with different partial pressures was tested, and the fabricated multilayers had a period of 3 nm. The intrinsic stress was essentially reduced after nitridation and relaxed to zero value at approximately 15% partial pressure of nitrogen in the working gas. Interface roughness was slightly increased which can be caused by the polycrystalline structure inside the nitridated samples. More importantly, the nitridated multilayers showed an enhanced reflectance (67% at 8.04 keV photon energy) as compared with the one fabricated with pure Ar (54%). The structure analysis with transmission electron microscopy and X-ray photoelectron spectroscopy demonstrated that nitrogen incorporated into a multilayer structure was mostly located in the BC layers forming BN compounds, which suppressed the diffusion of boron, stabilized the interfaces and enhanced the reflectance.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.