Search

The personalized bundle generation problem, which aims to create a preferred bundle for user from numerous candidate items, receives increasing attention in recommendation. However, existing works ignore the order-invariant nature of the bundle and adopt sequential modeling methods as the solution, which might introduce inductive bias and cause a large latency in prediction. To address this problem, we propose to perform the bundle generation via non-autoregressive mechanism and design a novel encoder-decoder framework named BundleNAT, which can effectively output the targeted bundle in one-shot without relying on any inherent order. In detail, instead of learning sequential dependency, we propose to adopt pre-training techniques and graph neural network to fully embed user-based preference and item-based compatibility information, and use a self-attention based encoder to further extract global dependency pattern. We then design a permutation-equivariant decoding architecture that is able to directly output the desired bundle in a one-shot manner. Experiments on three real-world datasets from Youshu and Netease show the proposed BundleNAT significantly outperforms the current state-of-the-art methods in average by up to 35.92%, 10.97% and 23.67% absolute improvements in Precision, Precision+, and Recall, respectively., Comment: Submitted to Information Processing & Management

Machine learning (ML) has been increasingly used to aid aerodynamic shape optimization (ASO), thanks to the availability of aerodynamic data and continued developments in deep learning. We review the applications of ML in ASO to date and provide a perspective on the state-of-the-art and future directions. We first introduce conventional ASO and current challenges. Next, we introduce ML fundamentals and detail ML algorithms that have been successful in ASO. Then, we review ML applications to ASO addressing three aspects: compact geometric design space, fast aerodynamic analysis, and efficient optimization architecture. In addition to providing a comprehensive summary of the research, we comment on the practicality and effectiveness of the developed methods. We show how cutting-edge ML approaches can benefit ASO and address challenging demands, such as interactive design optimization. Practical large-scale design optimizations remain a challenge because of the high cost of ML training. Further research on coupling ML model construction with prior experience and knowledge, such as physics-informed ML, is recommended to solve large-scale ASO problems., Comment: 103 pages, 47 figures, published by Progress in Aerospace Sciences

This work studies the application of a reinforcement-learning-based (RL) flow control strategy to the flow past a cylinder confined between two walls in order to suppress vortex shedding. The control action is blowing and suction of two synthetic jets on the cylinder. The theme of this study is to investigate how to use and embed physical information of the flow in the RL-based control. First, global linear stability and sensitivity analyses based on the time-mean flow and the steady flow (which is a solution to the Navier-Stokes equations) are conducted in a range of blockage ratios and Reynolds numbers. It is found that the most sensitive region in the wake extends itself when either parameter increases in the parameter range we investigated here. Then, we utilise these physical results to help design RL-based control policies. We find that the controlled wake converges to the unstable steady base flow, where the vortex shedding can be successfully suppressed. A persistent oscillating control seems necessary to maintain this unstable state. The RL algorithm is able to outperform a gradient-based optimisation method (optimised in a certain period of time) in the long run. Furthermore, when the flow stability information is embedded in the reward function to penalise the instability, the controlled flow may become more stable. Finally, according to the sensitivity analyses, the control is most efficient when the probes are placed in the most sensitive region. The control can be successful even when few probes are properly placed in this manner., Comment: 35 pages, 22 figures, accepted by JFM

Throughout history, a relatively small number of individuals have made a profound and lasting impact on science and society. Despite long-standing, multi-disciplinary interests in understanding careers of elite scientists, there have been limited attempts for a quantitative, career-level analysis. Here, we leverage a comprehensive dataset we assembled, allowing us to trace the entire career histories of nearly all Nobel laureates in physics, chemistry, and physiology or medicine over the past century. We find that, although Nobel laureates were energetic producers from the outset, producing works that garner unusually high impact, their careers before winning the prize follow relatively similar patterns as ordinary scientists, being characterized by hot streaks and increasing reliance on collaborations. We also uncovered notable variations along their careers, often associated with the Nobel prize, including shifting coauthorship structure in the prize-winning work, and a significant but temporary dip in the impact of work they produce after winning the Nobel. Together, these results document quantitative patterns governing the careers of scientific elites, offering an empirical basis for a deeper understanding of the hallmarks of exceptional careers in science.