Abstract: Methods, systems, and apparatuses include receiving network data for nodes of a graph network of an online system. Logging data is received for entities associated with the nodes Weakly labeled data is generated by filtering the logging data using the network data. Training data is generated for a relationship scoring machine learning model. The relationship scoring machine learning model is trained to determine relationship scores for the nodes by using the training data. Input data is generated for the trained relationship scoring machine learning model. The trained relationship scoring machine learning model is coupled to an input of a recommendation system to provide a recommendation.

Abstract: Techniques for a social networking system involve analyzing members' interactions to enhance follow recommendations. The techniques include calculating the number of follows generated by a first member and the number of follows received by a second and third member. The platform then computes a weighted follow utility score for two member pairs: the first comprising the first and second members, and the second comprising the first and third members. These scores are determined by equally weighing the follows generated and received, along with a probability of the first member following the second or third member. While the probability suggests a preference for the second member, the ranking system places the third member pair higher. Consequently, the first member is advised to follow the third member, based on this ranking. Finally, this recommendation is displayed to the first member on an electronic device, guiding their social interactions on the platform.

Abstract: Techniques for a social networking system involve analyzing members' interactions to enhance follow recommendations. The techniques include calculating the number of follows generated by a first member and the number of follows received by a second and third member. The platform then computes a weighted follow utility score for two member pairs: the first comprising the first and second members, and the second comprising the first and third members. These scores are determined by equally weighing the follows generated and received, along with a probability of the first member following the second or third member. While the probability suggests a preference for the second member, the ranking system places the third member pair higher. Consequently, the first member is advised to follow the third member, based on this ranking. Finally, this recommendation is displayed to the first member on an electronic device, guiding their social interactions on the platform.