Conversational recommendation systems (CRS) aim to timely and proactively acquire user dynamic preferred attributes through conversations for item recommendation. In each turn of CRS, there naturally have two decision-making processes with different roles that influence each other: 1) director, which is to select the follow-up option (i.e., ask or recommend) that is more effective for reducing the action space and acquiring user preferences; and 2) actor, which is to accordingly choose primitive actions (i.e., asked attribute or recommended item) to estimate the effectiveness of the director’s option. However, existing methods heavily rely on a unified decision-making module or heuristic rules, while neglecting to distinguish the roles of different decision procedures, as well as the mutual influences between them. To address this, we propose a novel Director-Actor Hierarchical Conversational Recommender (DAHCR), where the director selects the most effective option, followed by the actor accordingly choosing primitive actions that satisfy user preferences. Specifically, we develop a dynamic hypergraph to model user preferences and introduce an intrinsic motivation to train from weak supervision over the director. Finally, to alleviate the bad effect of model bias on the mutual influence between the director and actor, we model the director’s option by sampling from a categorical distribution. Extensive experiments demonstrate that DAHCR outperforms state-of-the-art methods.

Endowing chatbots with a consistent personality plays a vital role for agents to deliver human-like interactions. However, existing personalized approaches commonly generate responses in light of static predefined personas depicted with textual description, which may severely restrict the interactivity of human and the chatbot, especially when the agent needs to answer the query excluded in the predefined personas, which is so-called out-of-predefined persona problem (named OOP for simplicity). To alleviate the problem, in this paper we propose a novel retrieval-to-prediction paradigm consisting of two subcomponents, namely, (1) Persona Retrieval Model (PRM), it retrieves a persona from a global collection based on a Natural Language Inference (NLI) model, the inferred persona is consistent with the predefined personas; and (2) Posterior-scored Transformer (PS-Transformer), it adopts a persona posterior distribution that further considers the actual personas used in the ground response, maximally mitigating the gap between training and inferring. Furthermore, we present a dataset called IT-ConvAI2 that first highlights the OOP problem in personalized dialogue. Extensive experiments on both IT-ConvAI2 and ConvAI2 demonstrate that our proposed model yields considerable improvements in both automatic metrics and human evaluations.

This article investigates the consensus control problem for second-order multiagent systems with switched dynamics, consisting of a continuous-time subsystem and a discrete-time subsystem. Under a fixed directed topology, two linear control protocols are proposed for achieving consensus. One is that two subsystems use different control inputs, where the continuous-time system uses continuous-time control, and the discrete-time system uses discrete-time control. In order to reach consensus for this kind of control protocol, some necessary and sufficient conditions are derived. The other is to use the same control algorithm for the two subsystems, which is a sampled-data control input. Similar consensus conditions are also obtained. Finally, a few simulation examples are given to verify the theoretical results.

The containment control problem in fractional-order multiagent systems over a directed graph is studied in this article. Two distributed control protocols with or without time delays are designed by utilizing the sampled position and velocity data. Then, based on the knowledge of the matrix theory and Laplace transform, some necessary and sufficient conditions to reach containment are derived. For the protocol with time delays, similar sufficient and necessary conditions are obtained. Finally, some simulation examples are designed to verify that the theorems are correct.

A consensus control issue is studied for general second-order multiagent systems via Q-learning method in this article. A novel second-order type with discrete-time dynamics is investigated to solve the corresponding consensus issues. Under fixed directed topology, in order to achieve general second-order consensus for the systems, a model-free Q-learning method is proposed, which can derive the coupling gains matrix without any information from the system dynamics. Moreover, applying the obtained coupling gains matrix, this general second-order multiagent systems can achieve consensus. Then, for undirected graphs, a similar corollary is obtained for this system to achieve general second-order consensus by means of the Q-learning method. Finally, the correctness of the new method is confirmed by several simulation examples.

This article studies the consensus control problem of second-order multiagent systems with switching dynamics, which consist of a continuous-time and a discrete-time subsystem. A novel control protocol is proposed for fixed digraphs by using the same control strategy for two subsystems so that the controller can keep the control strategy unchanged when systems switch. Moreover, this control strategy uses only sampled position data at the current sampling time and the previous sampling time to deal with this possible situation when speed information is difficult to be measured, which is also robustness and low cost. Some necessary and sufficient conditions to achieve consensus are derived about the network topology, structure and sampling period. At last, a few simulation examples are given.

The task of crowd counting is extremely challenging due to complicated difficulties, especially the huge variation in vision scale.Previous works tend to adopt a naive concatenation of multiscale information to tackle it, while the scale shifts between the feature maps are ignored.In this paper, we propose a novel Hierarchical Scale Recalibration Network (HSRNet), which addresses the above issues by modeling rich contextual dependencies and recalibrating multiple scale-associated information.Specifically, a Scale Focus Module (SFM) first integrates global context into local features by modeling the semantic inter-dependencies along channel and spatial dimensions sequentially.In order to reallocate channel-wise feature responses, a Scale Recalibration Module (SRM) adopts a step-bystep fusion to generate final density maps.Furthermore, we propose a novel Scale Consistency loss to constrain that the scale-associated outputs are coherent with groundtruth of different scales.With the proposed modules, our approach can ignore various noises selectively and focus on appropriate crowd scales automatically.Extensive experiments on crowd counting datasets (ShanghaiTech, MALL, WorldEXPO'10, and UCSD) show that our HSRNet can deliver superior results over all state-of-the-art approaches.More remarkably, we extend experiments on an extra vehicle dataset , whose results indicate that the proposed model is generalized to other applications.

In this paper, a second-order consensus for multiagent systems with a directed communication topology is studied. A novel consensus strategy is first proposed, where a periodic intermittent control strategy only with casual sampled position data is used, which not only decreases the operating time and the update rates of conditioners for every individual but also responds effectively to the case of missing velocity information. A necessary and sufficient consensus condition based on the coupling gains, the sampling period, the communication width, and the spectrum of the Laplacian matrix is established to reach the consensus, and the right intervals of the sampling period are given. Furthermore, a delay-induced consensus protocol is designed, and a necessary and sufficient condition is also given, by which the sampling period and the communication width can easily be chosen to achieve the consensus. At last, some simulation examples are given to verify the correctness of the theoretical results.