Probabilistic linguistic term set (PLTS) has been proposed to tackle qualitative information efficiently in the decision-making process to achieve computing with expressions, which can be regarded as an advanced process of computing with words. The PLTS plays an important role in decision making by providing a comprehensive way for representing complex linguistic information. Owning to its usefulness and efficiency, the PLTS has attracted a lot of researchers’ attention, and fruitful research achievements regarding it has been published since it was introduced in 2016. As the probabilistic linguistic theory is still in its infancy, a survey of it contributes to understanding the previous topics and the current issues, and predicting the future research directions in this area. To implement these goals, this paper is organized by bibliometric analysis, definitions, multiple criteria decision-making methods, preference relations, and applications. Twelve future research directions related to the probabilistic linguistic decision-making theory are indicated. This paper provides some insights for researchers and practitioners who have interest in complex linguistic decision making.

A survey of decision-making methods with probabilistic linguistic information: bibliometrics, preliminaries, methodologies, applications and future directions

The emergence of Artificial Intelligence of Things (AIoT) has provided novel insights for many social computing applications such as group recommender systems. As the distances between people have been greatly shortened, there has been more general demand for the provision of personalized services aimed at groups instead of individuals. The existing methods for capturing group-level preference features from individuals have mostly been established via aggregation and face two challenges: secure data management workflows are absent, and implicit preference feedback is ignored. To tackle these current difficulties, this paper proposes secure AIoT for implicit group recommendations (SAIoT-GR). For the hardware module, a secure IoT structure is developed as the bottom support platform. For the software module, a collaborative Bayesian network model and noncooperative game are introduced as algorithms. This secure AIoT architecture is able to maximize the advantages of the two modules. In addition, a large number of experiments are carried out to evaluate the performance of SAIoT-GR in terms of efficiency and robustness.

Secure Artificial Intelligence of Things for Implicit Group Recommendations

The emergence of Artificial Intelligence of Things (AIoT) has provided novel insights for many social computing applications, such as group recommender systems. As the distances between people have been greatly shortened, there has been more general demand for the provision of personalized services aimed at groups instead of individuals. The existing methods for capturing group-level preference features from individuals have mostly been established via aggregation and face two challenges: 1) secure data management workflows are absent and 2) implicit preference feedback is ignored. To tackle these current difficulties, this article proposes secure AIoT for implicit group recommendations (SAIoT-GRs). For the hardware module, a secure Internet of Things structure is developed as the bottom support platform. For the software module, a collaborative Bayesian network model and noncooperative game are introduced as algorithms. This secure AIoT architecture is able to maximize the advantages of the two modules. In addition, a large number of experiments are carried out to evaluate the performance of SAIoT-GR in terms of efficiency and robustness. 

/pdf/secure-artificial-intelligence-of-things-for-implicit-group-1p0xj0pp.pdf

Distance-based multicriteria group decision-making approach with probabilistic linguistic term sets

This study aims to develop an integrated approach for solving probabilistic linguistic multi-criteria decision-making (MCDM) problems. This study first reveals the limitations in the existing metho...

Probabilistic linguistic multi-criteria decision-making based on evidential reasoning and combined ranking methods considering decision-makers’ psychological preferences

Personalized restaurant recommendation method combining group correlations and customer preferences

In a parallel-coupled dual-racetrack modulator, resonant light in two resonators can interfere with each other. In lieu of critical coupling, such interference is capable of producing high extinction ratios (ERs) for high-speed modulation. Experiments demonstrate ERs of over 9 dB at 50 Gb/s and 40-50% modulation depth enhancement compared with a single-resonator modulator at 50-56 Gb/s with a peak-to-peak driving voltage of 2.3 V. Furthermore, joint modulation of two racetracks offers the possibility to combine two separate bits of driving signals to generate four-level pulse-amplitude modulation (PAM-4) without an external digital-to-analog converter (DAC). To tackle the complex multi-variable transfer function of this modulator, a procedure for configuring PAM-4 states is theoretically developed. Finally, we demonstrate 100 Gb/s PAM-4 with an electro-optic modulation power consumption of < 40 fJ/bit for this device.

High-extinction-ratio low-voltage dual-racetrack modulator for low-power DAC-less PAM-4 modulation.

With the increase of content pages and interactive buttons in online services such as online-shopping and video-watching websites, industrial-scale recommender systems face challenges in multi-domain and multi-task recommendations. The core of multi-task and multi-domain recommendation is to accurately capture user interests in multiple scenarios given multiple user behaviors. In this paper, we propose a plug-and-play \textit{\textbf{P}arameter and \textbf{E}mbedding \textbf{P}ersonalized \textbf{Net}work (\textbf{PEPNet})} for multi-domain and multi-task recommendation. PEPNet takes personalized prior information as input and dynamically scales the bottom-level Embedding and top-level DNN hidden units through gate mechanisms. \textit{Embedding Personalized Network (EPNet)} performs personalized selection on Embedding to fuse features with different importance for different users in multiple domains. \textit{Parameter Personalized Network (PPNet)} executes personalized modification on DNN parameters to balance targets with different sparsity for different users in multiple tasks. We have made a series of special engineering optimizations combining the Kuaishou training framework and the online deployment environment. By infusing personalized selection of Embedding and personalized modification of DNN parameters, PEPNet tailored to the interests of each individual obtains significant performance gains, with online improvements exceeding 1\% in multiple task metrics across multiple domains. We have deployed PEPNet in Kuaishou apps, serving over 300 million users every day.

PEPNet: Parameter and Embedding Personalized Network for Infusing with Personalized Prior Information

Life-long user behavior modeling, i.e., extracting a user's hidden interests from rich historical behaviors in months or even years, plays a central role in modern CTR prediction systems. Conventional algorithms mostly follow two cascading stages: a simple General Search Unit (GSU) for fast and coarse search over tens of thousands of long-term behaviors and an Exact Search Unit (ESU) for effective Target Attention (TA) over the small number of finalists from GSU. Although efficient, existing algorithms mostly suffer from a crucial limitation: the \textit{inconsistent} target-behavior relevance metrics between GSU and ESU. As a result, their GSU usually misses highly relevant behaviors but retrieves ones considered irrelevant by ESU. In such case, the TA in ESU, no matter how attention is allocated, mostly deviates from the real user interests and thus degrades the overall CTR prediction accuracy. To address such inconsistency, we propose \textbf{TWo-stage Interest Network (TWIN)}, where our Consistency-Preserved GSU (CP-GSU) adopts the identical target-behavior relevance metric as the TA in ESU, making the two stages twins. Specifically, to break TA's computational bottleneck and extend it from ESU to GSU, or namely from behavior length $10^2$ to length $10^4-10^5$, we build a novel attention mechanism by behavior feature splitting. For the video inherent features of a behavior, we calculate their linear projection by efficient pre-computing \&caching strategies. And for the user-item cross features, we compress each into a one-dimentional bias term in the attention score calculation to save the computational cost. The consistency between two stages, together with the effective TA-based relevance metric in CP-GSU, contributes to significant performance gain in CTR prediction.

TWIN: TWo-stage Interest Network for Lifelong User Behavior Modeling in CTR Prediction at Kuaishou

Drug-target binding affinity prediction is a fundamental task for drug discovery and has been studied for decades. Most methods follow the canonical paradigm that processes the inputs of the protein (target) and the ligand (drug) separately and then combines them together. In this study we demonstrate, surprisingly, that a model is able to achieve even superior performance without access to any protein-sequence-related information. Instead, a protein is characterized completely by the ligands that it interacts. Specifically, we treat different proteins separately, which are jointly trained in a multi-head manner, so as to learn a robust and universal representation of ligands that is generalizable across proteins. Empirical evidences show that the novel paradigm outperforms its competitive sequence-based counterpart, with the Mean Squared Error (MSE) of 0.4261 versus 0.7612 and the R-Square of 0.7984 versus 0.6570 compared with DeepAffinity. We also investigate the transfer learning scenario where unseen proteins are encountered after the initial training, and the cross-dataset evaluation for prospective studies. The results reveals the robustness of the proposed model in generalizing to unseen proteins as well as in predicting future data. Source codes and data are available at https://github.com/huzqatpku/SAM-DTA.

Chenbin Zhang

Papers

Personalized restaurant recommendation method combining group correlations and customer preferences

High-extinction-ratio low-voltage dual-racetrack modulator for low-power DAC-less PAM-4 modulation.

PEPNet: Parameter and Embedding Personalized Network for Infusing with Personalized Prior Information

TWIN: TWo-stage Interest Network for Lifelong User Behavior Modeling in CTR Prediction at Kuaishou

SAM-DTA: a sequence-agnostic model for drug-target binding affinity prediction