簡述
將用戶的session序列構建成有向圖,通過考慮item之間的轉移關係, 更好的學習item emb及用戶的向量表達.
related work
一些流行的GNN演變.
word2vec, DeepWalk, LINE, node2vec.
結構及解讀
網絡結構
nodes connection
is defined as the concatenation of two adjacency matrices. directed edges have normalized weight.
gated recurrent units
session emb
, where
experiment
- baselines. GRU4REC, STAMP, etc.
- dataset.
YooChoose
from RecSys Chanllenge 2015. - P@20=71.36, evaluation metric , identical to recall@20.
參考
- paper,AAAI,2019, Session-based Recommendation with Graph Neural Networks
- corresponding official code,SR-GNN