HIENet
Predictions
Convex hull distance prediction errors projected onto elements
1 H 0.25
2 He 0.00
3 Li 0.05
4 Be 0.09
5 B 0.11
6 C 0.10
7 N 0.13
8 O 0.14
9 F 0.17
10 Ne 0.00
11 Na 0.06
12 Mg 0.07
13 Al 0.10
14 Si 0.11
15 P 0.10
16 S 0.14
17 Cl 0.16
18 Ar 0.00
19 K 0.07
20 Ca 0.07
21 Sc 0.07
22 Ti 0.07
23 V 0.10
24 Cr 0.13
25 Mn 0.15
26 Fe 0.14
27 Co 0.09
28 Ni 0.08
29 Cu 0.07
30 Zn 0.07
31 Ga 0.10
32 Ge 0.10
33 As 0.09
34 Se 0.15
35 Br 0.15
36 Kr 0.00
37 Rb 0.07
38 Sr 0.07
39 Y 0.07
40 Zr 0.08
41 Nb 0.10
42 Mo 0.09
43 Tc 0.07
44 Ru 0.11
45 Rh 0.10
46 Pd 0.09
47 Ag 0.06
48 Cd 0.07
49 In 0.10
50 Sn 0.09
51 Sb 0.09
52 Te 0.16
53 I 0.14
54 Xe 0.06
55 Cs 0.08
56 Ba 0.06
57 La 0.06
58 Ce 0.07
59 Pr 0.06
60 Nd 0.06
61 Pm 0.06
62 Sm 0.06
63 Eu 0.08
64 Gd 0.07
65 Tb 0.06
66 Dy 0.07
67 Ho 0.06
68 Er 0.07
69 Tm 0.07
70 Yb 0.07
71 Lu 0.07
72 Hf 0.08
73 Ta 0.13
74 W 0.09
75 Re 0.09
76 Os 0.10
77 Ir 0.12
78 Pt 0.10
79 Au 0.10
80 Hg 0.06
81 Tl 0.07
82 Pb 0.09
83 Bi 0.07
84 Po 0.00
85 At 0.00
86 Rn 0.00
87 Fr 0.00
88 Ra 0.00
89 Ac 0.06
90 Th 0.09
91 Pa 0.10
92 U 0.10
93 Np 0.17
94 Pu 0.41
95 Am 0.00
96 Cm 0.00
97 Bk 0.00
98 Cf 0.00
99 Es 0.00
100 Fm 0.00
101 Md 0.00
102 No 0.00
103 Lr 0.00
104 Rf 0.00
105 Db 0.00
106 Sg 0.00
107 Bh 0.00
108 Hs 0.00
109 Mt 0.00
110 Ds 0.00
111 Rg 0.00
112 Cn 0.00
113 Nh 0.00
114 Fl 0.00
115 Mc 0.00
116 Lv 0.00
117 Ts 0.00
118 Og 0.00
57-71 La-Lu Lanthanides
89-103 Ac-Lr Actinides
Model Authors
Model Info
- Model Version v1.0.1
- Model Type UIP
- Targets EFSG
- Openness OSOD
- Train Task S2EFS
- Test Task IS2RE-SR
- Trained for Benchmark No
Training Set
MPtrj: 1.58M structures from 146k materials
Description
HIENet is a hybrid invariant-equivariant graph neural network interatomic potential that combines E(3) invariant and O(3) equivariant message passing layers for materials discovery. The model uses physics-informed gradient-based predictions to ensure all outputs satisfy key physical constraints including force conservation and rotational symmetries, enabling accurate prediction of energy, forces, and stress for crystalline materials.
Hyperparameters
- max_force:
0.05 - max_steps:
500 - ase_optimizer:
"FIRE" - cell_filter:
"FrechetCellFilter" - epochs:
200 - optimizer:
"AdamW" - loss:
"Huber - delta=0.01" - loss_weights:
{"energy":1,"force":1,"stress":0.01} - batch_size:
48 - initial_learning_rate:
0.01 - learning_rate_schedule:
"CosineWarmupLR - warmup_factor=0.2, warmup_epochs=0.1, lr_min_factor=0.0005" - weight_decay:
0.001 - lmax:
3 - num_invariant_conv:
1 - inv_features:
[384,384] - irreps:
"384x0e -> 512x0e+128x1e+64x2e -> 512x0e+128x1e+64x2e+32x3e -> 512x0e" - radial_basis:
"bessel" - n_radial_bessel_basis:
8 - cutoff_function:
"poly_cut - p_value=6" - activation_gate:
"silu/tanh" - activation_scalar:
"silu/tanh" - dropout:
0.04 - dropout_attention:
0.08 - conv_denominator:
35.989574 - ema_decay:
0.999 - forces_rms_scale:
0.799 - max_neighbors:
null - graph_construction_radius:
5