Background: Infant feeding is a multidimensional and multi-risk factor practice with a vital role in ensuring optimal child health, growth and development. Maternal depression and other psychosocial factors have been shown to have adverse consequences on feeding practices. However, most of these findings were based on single infant feeding practice (IFP) dimension; for instance, early initiation of breastfeeding, exclusive breastfeeding or introduction of complementary foods. This study aims to explore the longitudinal relationship of maternal depressive symptoms and other selected psychosocial factors with IFPs in rural Ethiopia using summary IFP index. Methods: This study uses existing data from the ENGINE birth cohort study. The study had an open cohort design, with “rolling recruitment” procedure and follow up of pregnant women for a period of two years. It was conducted from March 2014 to March 2016 in three districts in the southwest of Ethiopia. A total of 4680 pregnant women were recruited between 12 and 32 weeks of gestation. Data were collected once during pregnancy for all women (twice for those in the first trimester), at birth, and then every three months until the child was 12 months old. Standardized questionnaire were used to collect data on IFPs, maternal depressive symptoms, household food insecurity, intimate partner violence, maternal social support, active social participation, and other socio-demographic variables. A composite measure of IFP index was computed using 14 WHO recommended infant and young child feeding (IYCF) practice indicators. Prenatal and postnatal maternal depressive symptoms were assessed using the patient health questionnaire (PHQ-9). Linear multilevel mixed effects model was fitted to assess longitudinal relationship of IFPs with maternal depression and other psychosocial factors. Results: Postnatal depressive symptoms (ß= -1.031, P=0.001) and intimate partner violence (ß= -0.208, P=0.001) were inversely and significantly associated with IFPs. However, prenatal maternal depressive symptoms was not significantly associated with IFPs (ß= -0.024, P=0.953). On the other hand, maternal social support (ß= 0.107, P=0.002) and maternal social participation (ß= 0.552, P<0.001) were positively associated with IFPs. Maternal education and gestational age at birth were other important factors positively associated with IFPs. Moreover, contrary to expected, moderate household food insecurity (ß= 0.836, P=0.003), severe household food insecurity (ß= 1.034, P=0.01) and infant morbidity episodes (ß= 0.625, P=0.013) were positively associated with IFPs. Conclusion: Early postnatal depressive symptoms and intimate partner violence were negative predictors of IFPs. On the other hand, maternal social support, social participation, maternal education and gestational age at birth were positive predictors of IFPs. Overall, we can conclude that multitude of factors are related to IFPs and hence coordinated, multi-sectoral and multi-stakeholder interventions including maternal depressive symptoms screening and management are needed to improve IFPs.