Multihop Neighbor Information Fusion Graph Convolutional Network for Text Classification

Table 4

Test accuracy on five text datasets. The benchmark results were reported by Yao et al. [15]. The accuracy values are the average result of 10 runs.

Method	R52	R8	20NG	Ohsumed	MR
CNN-rand [39]	85.37	94.02	76.93	43.87	74.98
CNN-pretrain [39]	87.59	95.71	82.15	58.44	77.75
PTE [46]	90.71	96.69	76.74	53.58	70.23
LSTM [2]	85.54	93.68	65.71	41.13	75.06
LSTM-pretrain [2]	90.48	96.09	75.43	51.10	77.33
fastText [47]	92.81	96.13	79.38	57.70	75.14
fastText-bigrams [47]	90.99	94.74	79.67	55.69	76.24
LEAM [48]	91.84	93.31	81.91	58.58	76.95
SWEM [49]	92.94	95.32	85.16	63.12	76.65
GCNN-S [23]	92.74	96.80	—	62.82	76.99
GCNN-F [50]	93.20	96.89	—	63.04	76.74
GCNN-C [10]	92.75	96.99	81.42	63.86	77.22
Text GCN [15]	93.56 ± 0.18	97.07 ± 0.10	86.34 ± 0.09	68.36 ± 0.56	76.74 ± 0.20
NMGC-2 (ours)	94.35 ± 0.06	97.31 ± 0.09	86.61 ± 0.06	69.21 ± 0.17	76.21 ± 0.25
NMGC-3 (ours)	93.83 ± 0.16	97.16 ± 0.10	86.68 ± 0.18	68.20 ± 0.35	76.36 ± 0.40