Recommender systems filter out information that meets user interests. However, users may be tired of the recommendations that are too similar to the content they have been exposed to in a short historical period, which is the so-called user fatigue. Despite the significance for a better user experience, user fatigue is seldom explored by existing recommenders. In fact, there are three main challenges to be addressed for modeling user fatigue, including what features support it, how it influences user interests, and how its explicit signals are obtained. In this paper, we propose to model user Fatigue in interest learning for sequential Recommendations (FRec). To address the first challenge, based on a multi-interest framework, we connect the target item with historical items and construct an interest-aware similarity matrix as features to support fatigue modeling. Regarding the second challenge, built upon feature cross, we propose a fatigue-enhanced multi-interest fusion to capture long-term interest. In addition, we develop a fatigue-gated recurrent unit for short-term interest learning, with temporal fatigue representations as important inputs for constructing update and reset gates. For the last challenge, we propose a novel sequence augmentation to obtain explicit fatigue signals for contrastive learning. We conduct extensive experiments on real-world datasets, including two public datasets and one large-scale industrial dataset. Experimental results show that FRec can improve AUC and GAUC up to 0.026 and 0.019 compared with state-of-the-art models, respectively. Moreover, large-scale online experiments demonstrate the effectiveness of FRec for fatigue reduction. Our codes are released at https://github.com/tsinghua-fib-lab/SIGIR24-FRec.
In this paper, the method that measuring dataset of knitted yarns is clustered using improving fuzzy kernel c-Means (FKCM) clustering algorithm is proposed. In FKCM clustering algorithm, the data of low dimension input space is mapped to high dimension feature space, FCM clustering algorithm is performed in feature space, then the constraint optimization distance matrix and membership matrix of testing samples are computed by utilizing iterative algorithm, and the clustering result can be acquired according maximum membership principle. Subsequently, the Kernel F cluster validity index is designed for seeking the fitness cluster number and the corresponding relationship model of clusters sequence number and quality grades is constructed. Improving FKCM clustering algorithm is more efficient than other clustering algorithms, and clustering result can provide the training samples for constructing quality grades and clusters recognition function of new samples. The combination of improving FKCM and KF index provides an efficient data analysis method for multi-index dataset.