Session-Based Recommendation with Graph Neural Networks

Abstract

The problem of session-based recommendation aims to predict user actions based on anonymous sessions. Previous methods model a session as a sequence and estimate user representations besides item representations to make recommendations. Though achieved promising results, they are insufficient to obtain accurate user vectors in sessions and neglect complex transitions of items. To obtain accurate item embedding and take complex transitions of items into account, we propose a novel method, i.e. Session-based Recommendation with Graph Neural Networks, SR-GNN for brevity. In the proposed method, session sequences are modeled as graphstructured data. Based on the session graph, GNN can capture complex transitions of items, which are difficult to be revealed by previous conventional sequential methods. Each session is then represented as the composition of the global preference and the current interest of that session using an attention network. Extensive experiments conducted on two real datasets show that SR-GNN evidently outperforms the state-of-the-art session-based recommendation methods consistently.

ragamAI: A Network Based Recommender System to Arrange a Indian Classical Music Concert

“…The proposed ragamAI framework relies on the influence of two separate models: 1. a deep attention model to capture the importance of sequence of ragams, and 2. an embedding model to capture the importance of hand picked features to train. Unlike other methods, which predict next event or item in a given sequence [6], [9], [17]- [19], the proposed model(s) Figure 1 A. Raaga network Networks or graphs have been considered as a promising framework to study variety of applications like influence modeling [20], community detection [21], and recommender systems [22]. Their organization of nodes and edges help to study the structural organization and positional values of entities (nodes and communities).…”

Beyond Clicks: Modeling Multi-Relational Item Graph for Session-Based Target Behavior Prediction

“…We consider the top-100 ranked predictions as recommended items. Following [29,30], we adopt HR@100 (H@100), MRR@100 (M@100), and NDCG@100 (N@100) to evaluate the recommendation performance of all models after obtaining their recommendation lists. Table 2 shows the performance comparison between our model and the adopted baselines.…”

“…In the domain of single-session based behavior prediction, some studies [14,22,25] adopt attention mechanism [1,28] and outperform the pioneering RNN based methods [8]. Recent advances in graph neural networks (GNN) [3,7] further boost the performance of session-based behavior prediction by modeling each sessionbased behavior sequence as a graph to achieve the state-of-the-art performance [29,30]. However, existing studies in this regard still suffer from several limitations.…”

Sequential Recommender Systems: Challenges, Progress and Prospects

“…Typically a directed graph is first built on the sequence data by taking each interaction as a node in the graph while each sequence is mapped to a path. Then, the embeddings of users or items are learned on the graph to embed more complex relations over the whole graph [22]. Such an approach makes full use of the advantage of GNN to capture the complex relations in structured relation datasets.…”