Recommendation algorithms have been extensively applied in multiple areas. However, user-level uncertainty in implicit feedback introduce false-positive signals, misaligning interactions with true preferences and introducing noise. This makes it challenging for traditional recommendation methods to achieve both robust and accurate performance. In this manuscript, we propose a semi-supervised co-training algorithm for denoising learning in the recommender system, which incorporates both supervised learning and semi-supervised learning in a cooperative way. We first adopt a Gaussian Mixture Model as a confidence estimation module to partition the implicit feedback into two disjoint datasets: a reliable dataset and an unreliable dataset, based on the intrinsic features of the feedback. To achieve doubly robust learning, we design an iterative cross co-training module that consists of two key components: a two-stage reliable learning process and a cross-sample transmission mechanism. The two-stage reliable learning process enables semi-supervised training on both the reliable and unreliable datasets. Meanwhile, the cross-sample transmission mechanism iteratively transfers hard yet clean samples between dual networks, enhancing robustness through mutual supervision during joint learning. Extensive experiments are conducted using clean test sets extracted from four real-world explicit feedback datasets to validate our denoising method, which demonstrates superior effectiveness across all datasets.

Point-of-interest (POI) retrieval that searches for relevant destination locations plays a significant role in on-demand ridehailing services. Existing solutions to POI retrieval mainly retrieve and rank POIs based on their semantic similarity scores. Although intuitive, quantifying the relevance of a Query-POI pair by single-field semantic similarity is subject to inherent limitations. In this paper, we propose a novel Query-POI relevance model for effective POI retrieval for ondemand ride-hailing services. Different from existing relevance models, we capture and represent multi-field and local&global semantic features of a Query-POI pair to measure the semantic similarity. Besides, we observe a hidden correlation between origin-destination locations in ride-hailing scenarios, and propose two location embeddings to characterize the specific correlation. By incorporating the geographic correlation with the semantic similarity, our model achieves better performance in POI ranking. Experimental results on two real-world click-through datasets demonstrate the improvements of our model over state-of-the-art methods.