Skip to main content

Table 18 nDCG@K results on Yoochoose1/4, \(K=[1, 3, 5, 10, 15, 20]\)

From: Improving session-based recommendation with contrastive learning

Method Yoochoose1/4
nDCG@1 nDCG@3 nDCG@5 nDCG@10 nDCG@15 nDCG@20
STAMP 0.1766 0.2869 0.3289 0.3709 0.3889 0.3976
STAMP-CL 0.1774 0.2896 0.3302 0.3724 0.3895 0.3993
RepeatNet 0.1855 0.2932 0.3361 0.3792 0.3969 0.4063
RepeatNet-CL 0.1880 0.2959 0.3383 0.3804 0.3984 0.4086
SR-GNN 0.1889 0.2993 0.3410 0.3823 0.3994 0.4067
SR-GNN-CL 0.1901 0.3002 0.3416 0.3831 0.4002 0.4081
SR-IEM 0.1857 0.2962 0.3388 0.3803 0.3974 0.4059
SR-IEM-CL 0.1849 0.2963 0.3388 0.3808 0.3978 0.4071
PIE 0.1869 0.2958 0.3389 0.3782 0.3962 0.4068
PIE-CL 0.1876 0.2978 0.3410 0.3806 0.3994 0.4091