Top-one recommendation with anonymous user behaviors, also known as session-based recommendation (SBR), faces challenges of top-one ranking and short anonymous sequences. To this end, we propose a novel objective that combines (1) a reciprocal rank loss to directly optimize the benchmark metric of top-one recommendation, with (2) a listwise contrastive loss to handle short sequences through listwise augmented consistency regularization. Empirical studies demonstrate that optimizing the proposed objective significantly improves the performance of existing SBR baselines.

Knowledge Graph Embedding (KGE) methods have achieved great success in predicting missing links in knowledge graphs, a task also known as Knowledge Graph Completion (KGC). Under this task, the Reciprocal Rank (RR) of ground-truth items serve as a key indicator for evaluating the method’s performance. However, most existing studies have overlooked the inconsistency between the ranking metric, RR, and the optimization objective functions, resulting in sub-optimal KGC performance. To address this issue, we propose a KGC framework called KGCRR by designing a novel upper bound function named CRR. By introducing the parameter-pressure ρ to shift the sigmoid function, CRR achieves a better approximation to RR compared with existing objective functions. We theoretically proved that by adjusting ρ, CRR can achieve a more effective approximation to RR. By narrowing the discrepancy with RR and alleviating the gradient vanishing issue associated with the direct optimization of RR loss, CRR demonstrates an advantage in optimizing RR. CRR serves as a plug-and-play objective, capable of seamless integration into various KGE methods. Through extensive experiments conducted on FB15k-237 and WN18RR datasets, we have obtained promising results, with an average improvement of 19.06% in MRR, indicating that CRR significantly enhances the performance of existing methods.

Review-aware Rating Regression (RaRR) suffers the severe challenge of extreme data sparsity as the multi-modality interactions of ratings accompanied by reviews are costly to obtain. Although some studies of semi-supervised rating regression are proposed to mitigate the impact of sparse data, they bear the risk of learning from noisy pseudo-labeled data. In this article, we propose a simple yet effective paradigm, called co-training-teaching ( CoT 2 ), for integrating the merits of both co-training and co-teaching toward robust semi-supervised RaRR. CoT 2 employs two predictors trained with different feature sets of textual reviews, each of which functions as both “labeler” and “validator.” Specifically, one predictor (labeler) first labels unlabeled data for its peer predictor (validator); after that, the validator samples reliable instances from the noisy pseudo-labeled data it received and sends them back to the labeler for updating. By exchanging and validating pseudo-labeled instances, the two predictors are reinforced by each other in an iterative learning process. The final prediction is made by averaging the outputs of both the refined predictors. Extensive experiments show that our CoT 2 considerably outperforms the state-of-the-art recommendation techniques in the RaRR task, especially when the training data is severely insufficient.

Semi-supervised learning is a promising solution to mitigate data sparsity in review-aware rating regression (RaRR), but it bears the risk of learning with noisy pseudo-labelled data. In this paper, we propose a paradigm called co-training-teaching (CoT2), which integrates the merits of both co-training and co-teaching towards the robust semi-supervised RaRR. Concretely, CoT2 employs two predictors and each of them alternately plays the roles of "labeler" and "validator" to generate and validate pseudo-labelled instances. Extensive experiments show that CoT2 considerably outperforms state-of-the-art RaRR techniques, especially when training data is severely insufficient.

Next item recommendation is a crucial task of session-based recommendation. However, the gap between the optimization objective (Binary Cross Entropy) and the ranking metric (Mean Reciprocal Rank) has not been well-explored, resulting in sub-optimal recommendations. In this paper, we propose a novel objective function, namely Adjusted-RR, to directly optimize Mean Reciprocal Rank. Specifically, Adjusted-RR adopts Bayesian Average to adjust Reciprocal Rank loss with Normal Rank loss by creating position-aware weights between them. Adjusted-RR is a plug-and-play objective that is compatible with various models. We apply Adjusted-RR on two base models and two datasets, and experimental results show that it makes a significant improvement in the next item recommendation.

In the scenarios of low-resource natural language applications, Semi-supervised Relation Extraction (SRE) plays a key role in mitigating the scarcity of labelled sentences by harnessing a large amount of unlabeled corpus. Current SRE methods are mainly designed based on the paradigm of Self-Training with Validation (STV), which employs two learners and each of them plays the single role of annotator or validator. However, such a single role setting under-utilizes the potential of learners in promoting new labelled instances from unlabeled corpus. In this paper, we propose a generic SRE paradigm, called Co-Training with Validation (CTV), for making full use of learners to benefit more from unlabeled corpus. In CTV, each learner alternately plays the roles of annotator and validator to generate and validate pseudo-labelled instances. Thus, more high-quality instances are exploited and two learners can be reinforced by each other during the learning process. Experimental results on two public datasets show that our CTV considerably outperforms the state-of-the-art SRE techniques, and works well with different kinds of learners for relation extraction.

Two-tower neural networks are popularly used in review-aware recommender systems, in which two encoders are separately employed to learn representations for users and items from reviews. However, such an architecture isolates the information exchange between two encoders, resulting in suboptimal recommendation accuracy. To this end, we propose a novel two-tower style Neural Recommendation with Cross-modality Mutual Attention (NRCMA), which bridges user encoder and item encoder crossing reviews and ratings, in order to select informative words and reviews to learn better representation for users and items. Extensive experiments on three benchmark datasets demonstrate that the cross-modality mutual attention is beneficial to two-tower neural networks, and NRCMA consistently outperforms state-of-the-art review-aware item recommendation techniques.