Large language models (LLMs) have been widely applied in recommender systems, achieving remarkable success. However, LLM-based recommendation (LR) suffers from more severe popularity bias than conventional recommendation (CR), stemming from both training and inference stages. In this paper, we propose a novel debiasing method for LR, which performs debiasing in such two stages, so termed as Dual Debiasing in LR (D²LR). Concretely, in the training stage, we conduct token-wise inverse propensity score weighting to force the LLM to pay more attention on unpopular tokens. In the inference stage, we train a more biased CR model by increasing the weights of popular items, which adjusts the generation probability of corresponding tokens according to its scores for items, hoping to suppress the excessive generation of popular tokens. Experiments conducted on three real-world datasets validate the effectiveness of our D²LR in mitigating popularity bias in LR.

Prompt learning plays a key role in aligning the task of news recommendation (NR) with the Pre-trained Language Models (PLMs). However, current prompt-based NR methods utilize fixed templates and answer words, ignoring the personalization of user's demand and the diversity between news topics. To this end, we propose an Automatic Prompt based NR (AutoPNR) scheme, which automatically generates individual templates for users according to their potential interests, and customized answer words w.r.t. the topics of candidate news. Concretely, such an individual template utilizes several specific tokens to encode a user's interest extracted from her/his reading history, while a pair of customized answer words are retrieved from a large vocabulary (often existing alongside PLMs) based on the topic of candidate news. Through extensive experiments on the real-world datasets, we show that our AutoPNR works well with different PLMs, and considerably outperforms state-of-the-art NR techniques.

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.

To perform online inference efficiently, hashing techniques, devoted to encoding model parameters as binary codes, play a key role in reducing the computational cost of content-aware recommendation (CAR), particularly on devices with limited computation resource. However, current hashing methods for CAR fail to align their learning objectives (e.g., squared loss) with the ranking-based metrics (e.g., Normalized Discounted Cumulative Gain (NDCG)), resulting in suboptimal recommendation accuracy. In this article, we propose a novel ranking-based CAR hashing method based on Factorization Machine (FM), called Discrete Listwise FM (DLFM), for fast and accurate recommendation. Concretely, our DLFM is to optimize NDCG in the Hamming space for preserving the listwise user-item relationships. We devise an efficient algorithm to resolve the challenging DLFM problem, which can directly learn binary parameters in a relaxed continuous solution space, without additional quantization. Particularly, our theoretical analysis shows that the optimal solution to the relaxed continuous optimization problem is approximately the same as that of the original discrete optimization problem. Through extensive experiments on two real-world datasets, we show that DLFM consistently outperforms state-of-the-art hashing-based recommendation techniques.

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 recommender systems (RSs), inverse propensity score (IPS) has been a key technique to mitigate popularity bias by decreasing the contribution of popular items in modeling user-item interactions. However, conventional IPS treats all users equally, which tends to over-debias the popularity-insensitive (PI) users and under-debias the popularity-sensitive (PS) users. Furthermore, in such a treatment, IPS only performs slightly well on the debiased test while does not work on the normal biased test. To this end, we propose a user-dependent IPS (UDIPS in short) method, which adaptively conducts propensity estimation for each user-item pair based on the user's sensitivity to item popularity. Like IPS, our theoretical analysis validates the unbiasedness of UDIPS. Remarkably, our solution is model-agnostic and can be easily used to upgrade current unbiased recommenders. We implemented it in four state-of-the-art models for unbiased recommendation, and experimental results on two benchmark datasets demonstrate the effectiveness of our method in both unbiased and normal biased test.

Federated recommender system (FRS), which enables many local devices to train a shared model jointly without transmitting local raw data, has become a prevalent recommendation paradigm with privacy-preserving advantages. However, previous work on FRS performs similarity search via inner product in continuous embedding space, which causes an efficiency bottleneck when the scale of items is extremely large. We argue that such a scheme in federated settings ignores the limited capacities in resource-constrained user devices ( i.e. , storage space, computational overhead, and communication bandwidth), and makes it harder to be deployed in large-scale recommender systems. Besides, it has been shown that transmitting local gradients in real-valued form between server and clients may leak users’ private information. To this end, we propose a lightweight federated recommendation framework with privacy-preserving matrix factorization, LightFR , that is able to generate high-quality binary codes by exploiting learning to hash technique under federated settings, and thus enjoys both fast online inference and economic memory consumption. Moreover, we devise an efficient federated discrete optimization algorithm to collaboratively train model parameters between the server and clients, which can effectively prevent real-valued gradient attacks from malicious parties. Through extensive experiments on four real-world datasets, we show that our LightFR model outperforms several state-of-the-art FRS methods in terms of recommendation accuracy, inference efficiency and data privacy.

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.

Deep neural networks (DNNs) have been a key technique for click-through rate (CTR) estimation, yet existing DNNs-based CTR models neglect the inconsistency between their optimization objectives (e.g., Binary Cross Entropy, BCE) and CTR ranking metrics (e.g., Area Under the ROC Curve, AUC). It is noteworthy that directly optimizing AUC by gradient-descent methods is difficult due to the non-differentiable Heaviside function built-in AUC. To this end, we propose a smooth approximation of AUC, called smooth-AUC (SAUC), towards the rank-based CTR prediction. Specifically, SAUC relaxes the Heaviside function via sigmoid with a temperature coefficient (aiming at controlling the function sharpness) in order to facilitate the gradient-based optimization. Furthermore, SAUC is a plug-and-play objective that can be used in any DNNs-based CTR model. Experimental results on two real-world datasets demonstrate that SAUC consistently improves the recommendation accuracy of current DNNs-based CTR models.

It is significant to accurately predict the epidemic trend of COVID-19 due to its detrimental impact on the global health and economy. Although machine learning based approaches have been applied to predict epidemic trend, standard models have shown low accuracy for long-term prediction due to a high level of uncertainty and lack of essential training data. This paper proposes an improved machine learning framework employing Generative Adversarial Network (GAN) and Long Short-Term Memory (LSTM) for adversarial training to forecast the potential threat of COVID-19 in countries where COVID-19 is rapidly spreading. It also investigates the most updated COVID-19 epidemiological data before October 18, 2020 and model the epidemic trend as time series that can be fed into the proposed model for data augmentation and trend prediction of the epidemic. The proposed model is trained to predict daily numbers of cumulative confirmed cases of COVID-19 in Italy, USA, China, Germany, UK, and across the world. Paper further analyzes and suggests which populations are at risk of contracting COVID-19.

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.