Conversational recommender system (CRS) enhances the recommender system by acquiring the latest user preference through dialogues, where an agent needs to decide “whether to ask or recommend”, “which attributes to ask”, and “which items to recommend” in each round. To explore these questions, reinforcement learning is adopted in most CRS frameworks. However, existing studies somewhat ignore to consider the connection between the previous rounds and the current round of the conversation, which might lead to the lack of prior knowledge and inaccurate decisions. In this view, we propose to facilitate the connections between different rounds of conversations in a dialogue session through deep transformer-based multi-channel meta-reinforcement learning, so that the CRS agent can decide each action/decision based on previous states, actions, and their rewards. Besides, to better utilize a user’s historical preferences, we propose a more dynamic and personalized graph structure to support the conversation module and the recommendation module. Experiment results on five real-world datasets and an online evaluation with real users in an industrial environment validate the improvement of our method over the state-of-the-art approaches and the effectiveness of our designs.

Airport ground handling (AGH) offers necessary operations to flights during their turnarounds and is of great importance to the efficiency of airport management and the economics of aviation. Such a problem involves the interplay among the operations that leads to NP-hard problems with complex constraints. Hence, existing methods for AGH are usually designed with massive domain knowledge but still fail to yield high-quality solutions efficiently. In this paper, we aim to enhance the solution quality and computation efficiency for solving AGH. Particularly, we first model AGH as a multiple-fleet vehicle routing problem (VRP) with miscellaneous constraints including precedence, time windows, and capacity. Then we propose a construction framework that decomposes AGH into sub-problems (i.e., VRPs) in fleets and present a neural method to construct the routing solutions to these sub-problems. In specific, we resort to deep learning and parameterize the construction heuristic policy with an attention-based neural network trained with reinforcement learning, which is shared across all sub-problems. Extensive experiments demonstrate that our method significantly outperforms classic meta-heuristics, construction heuristics and the specialized methods for AGH. Besides, we empirically verify that our neural method generalizes well to instances with large numbers of flights or varying parameters, and can be readily adapted to solve real-time AGH with stochastic flight arrivals. Our code is publicly available at:https://github.com/RoyalSkye/AGH.

The uncertain check-ins bring challenges for current static next point-of-interest (POI) recommendation methods. Fortunately, the conversation-based recommendation has been shown the merit of integrating immediate user preference for more accurate recommendations. We, therefore, propose a conversation-based adaptive relational translation (CART) approach for the next POI recommendation over uncertain check-ins. It is equipped with recommender and conversation modules to interactively acquire users' immediate preferences and make dynamic recommendations. Specifically, the recommender built upon the adaptive relational translation method performs location prediction via modeling both users' historical sequential behaviors and the immediate preference received from conversations; the conversation module aims to achieve successful recommendations in fewer conversation turns by learning a conversational strategy, whereby the recommender can be updated via the user response. Extensive experiments on four real-world datasets show the superiority of our proposed CART over the state of the arts.