Table 3 Details of hyperparameters for DR-A based on the experimental results in Table 2. We carried out the experiments using the Rosenberg-156 k, Zheng-73 k, Zheng-68 k, Macosko-44 k, and Zeisel-3 k datasets. The DR-A algorithm was investigated with (a) 2 latent dimensions (K = 2), (b) 10 latent dimensions (K = 10), and (c) 20 latent dimensions (K = 20). G denotes a generative model and D denotes a discriminative model
Dataset | Batch size | Hidden layer | Hidden unit | Learning rate |
|---|---|---|---|---|
(a) K = 2 | ||||
 Rosenberg-156 k | 128 | 4 | G: 1024/512/512/256 D: 32/16/16/8 | 7 × 10−5 |
 Zheng-73 k | 128 | 3 | G: 512/512/512 D: 32/32/32 | 6 × 10−5 |
 Zheng-68 k | 128 | 4 | G: 256/256/256/256 D: 32/32/16/16 | 0.0001 |
 Macosko-44 k | 128 | 3 | G: 256/128/64 D: 64/64/64 | 0.0001 |
 Zeisel-3 k | 128 | 4 | G: 512/512/512/512 D: 32/32/32/32 | 8 × 10−4 |
(b) K = 10 | ||||
 Rosenberg-156 k | 128 | 4 | G: 512/256/128/64 D: 256/128/64/32 | 6 × 10−5 |
 Zheng-73 k | 128 | 4 | G: 1024/512/512/256 D: 32/32/32/32 | 2 × 10−5 |
 Zheng-68 k | 128 | 4 | G: 256/256/256/256 D: 32/32/16/16 | 7 × 10−5 |
 Macosko-44 k | 128 | 4 | G: 512/256/256/128 D: 256/128/128/64 | 7 × 10−5 |
 Zeisel-3 k | 128 | 1 | G: 512 D: 512 | 7 × 10−4 |
(c) K = 20 | ||||
 Rosenberg-156 k | 128 | 4 | G: 1024/1024/1024/1024 D: 64/64/64/64 | 6 × 10−5 |
 Zheng-73 k | 128 | 4 | G: 1024/512/512/256 D: 64/32/32/16 | 1 × 10−5 |
 Zheng-68 k | 128 | 1 | G: 256 D: 256 | 2 × 10−5 |
 Macosko-44 k | 128 | 1 | G: 256 D: 256 | 7 × 10−5 |
 Zeisel-3 k | 128 | 1 | G: 512 D: 512 | 7 × 10−4 |