… [Limitations] The analysis of interest drift evolution depends on historical user data. When
the data is too sparse, alternative user information is required for a cold start. [Conclusions] …

[目的] 聚焦图神经网络技术, 对会话推荐方法进行述评.[文献范围] 分别以“Session-Based
Recommendation”“Graph Neural Network”“会话推荐”“图神经网络” 为检索词, 在Web of Science, …

… much of the influence of biased attack profiles for model-… in regular cases, we first measure
the performance of algorithms … than the baseline collaborative filtering algorithm without the …

… -level gender-unbiased data set SlguSet containing 20,000 sentences… measure the degree
of gender bias in pre-trained language models, and evaluates the gender bias in five popular …

… Typical recommender systems are based on collaborative filtering, which is a technique
that can predict the preference of a given user by only collecting rating information from other …

… for data assets. These recommendations are based on user preferences, past search patterns,
collaborative filtering, … to ethical considerations regarding data usage, bias, and privacy. …

… First, we explore cross-site information in solving the data sparsity … traditional collaborative
filtering algorithms, 2) collaborative filtering … If we further remove the personal bias vector of ε …

… Second, we established a penalty scheme on popular tag and resource co-occurrence
with the help of IDF in TF-IDF. Finally,we re-defined the initial tensor on the triplets of user, tag …

… the collaborative filtering algorithm based on explicit feedbacks, aiming to address data sparsity
and user selection bias … Then, we measured the visibility of items along with user activity, …

… We also took into consideration popular definitions of blogs, incorporating means to measure
the purported defining characteristics of blogs as articulated by Blood (2002a) and other …