Conversational Recommender Systems (CRS) have recently attracted significant attention. Despite existing GNN-based CRS methods have been proven to be effective in exploiting knowledge graphs (KGs), we note that these methods are not suitable for modeling scenarios with geographic positional information, which encompass the two key issues that have not been adequately solved: 1) Data noise is ubiquitous in the real world due to a variety of factors, and existing methods are prone to amplifying data noise, which can lead to a deterioration in downstream tasks; 2) Existing CRS models are designed solely in Euclidean space without considering space curvature, which implies that they may suffer from significant distortion when representing real-world graph structures, leading to a decrease in the accuracy and reliability of geographical POIs. To this end, we propose a Light POI-Guided Conversational Recommender based on Adaptive Space, namely PCRA, aiming to address the above problems by enhancing both embedding spaces and graph structures. Specifically, PCRA introduces the unified space to obtain high-quality embeddings compatible with hyperbolic space, Euclidean space, and spherical space. On the other hand, to extract the most valuable neighbors, we adopt a graph denoising module to eliminate noisy entities and ensure light information propagation. Finally, we further fuse the embeddings of utterances and entities to bridge the semantic gap of recommendation and conversation. Extensive experiments on MultiWOZ 2.0 and MultiWOZ 2.1 datasets demonstrate that our proposed PCRA has a significant improvement over the state-of-the-art CRS methods.

Embedding-based methods currently achieved impressive success in recommender systems. However, such methods are more likely to suffer from bias in data distribution, especially the attribute bias problem. For example, when a certain type of user, like the elderly, occupies the mainstream, the recommendation results of minority users would be seriously affected by the mainstream users’ attributes. To address this problem, most existing methods are proposed from the perspective of fairness, which focuses on eliminating unfairness but deteriorates the recommendation performance. Unlike these methods, in this paper, we focus on improving the recommendation performance for minority users of biased attributes. Along this line, we propose a novel attribute-aware Counterfactual Augmentation framework for Minority Users(CAMUS). Specifically, the CAMUS consists of a counterfactual augmenter, a confidence estimator, and a recommender. The counterfactual augmenter conducts data augmentation for the minority group by utilizing the interactions of mainstream users based on a universal counterfactual assumption. Besides, a tri-training-based confidence estimator is applied to ensure the effectiveness of augmentation. Extensive experiments on three real-world datasets have demonstrated the superior performance of the proposed methods. Further case studies verify the universality of the proposed CAMUS framework on different data sparsity, attributes, and models.