Sequential recommendation, which aims to recommend next item that the user will likely interact in a near future, has become essential in various Internet applications. Existing methods usually consider the transition patterns between items, but ignore the transition patterns between features of items. We argue that only the item-level sequences cannot reveal the full sequential patterns, while explicit and implicit feature-level sequences can help extract the full sequential patterns. In this paper, we propose a novel method named Feature-level Deeper Self-Attention Network (FDSA) for sequential recommendation. Specifically, FDSA first integrates various heterogeneous features of items into feature sequences with different weights through a vanilla mechanism. After that, FDSA applies separated self-attention blocks on item-level sequences and feature-level sequences, respectively, to model item transition patterns and feature transition patterns. Then, we integrate the outputs of these two blocks to a fully-connected layer for next item recommendation. Finally, comprehensive experimental results demonstrate that considering the transition relationships between features can significantly improve the performance of sequential recommendation.

In a service-oriented online social network consisting of service providers and consumers as participants, a service consumer can search trustworthy service providers via the social network between them. This requires the evaluation of the trustworthiness of a service provider along a potentially very large number of social trust paths from the service consumer to the service provider. Thus, a challenging problem is how to identify K optimal social trust paths that can yield the K most trustworthy evaluation results based on service consumers' evaluation criteria. In this paper, we first present a complex social network structure and a concept, Quality of Trust (QoT). We then model the K optimal social trust paths selection with multiple end-to-end QoT constraints as the Multiple Constrained K Optimal Paths (MCOP-K) selection problem, which is NP-Complete. For solving this challenging problem, based on Dijkstra's shortest path algorithm and our optimization strategies, we propose a heuristic algorithm H-OSTP-K with the time complexity of O(m + Knlogn). The results of our experiments conducted on a real dataset of online social networks illustrate that H-OSTP-K outperforms existing methods in the quality of identified social trust paths.

No abstract

No abstract