Skip to main content

Table 4 Effectiveness different components of APP-TGN in terms of ACC(%)

From: Enhancing academic performance prediction with temporal graph networks for massive open online courses

Methods

GS

LTL

TGN

TGN1

GRU

Pass/Fail

Pass/Withdrawn

APP-GS

\(\times\)

\(\times\)

\(\checkmark\)

\(\times\)

\(\times\)

82.15(-1.07)

75.74(-1.32)

APP-LTL

\(\checkmark\)

\(\times\)

\(\checkmark\)

\(\times\)

\(\times\)

82.68(-0.54)

76.08(-0.98)

APP-GRU

\(\checkmark\)

\(\checkmark\)

\(\times\)

\(\times\)

\(\checkmark\)

81.11(-2.11)

74.21(-2.85)

APP-TGN1

\(\checkmark\)

\(\checkmark\)

\(\times\)

\(\checkmark\)

\(\times\)

82.76(-0.46)

75.63(-1.43)

APP-TGN

\(\checkmark\)

\(\checkmark\)

\(\checkmark\)

\(\times\)

\(\times\)

83.22(-0.00)

77.06(-0.00)