Graph-structured data is crucial for modeling complex real-world systems, but traditional machine learning struggles with
non-Euclidean relationships inherent in graphs. Graph embedding techniques address this by creating fixed-dimensional
vector representations of nodes, edges, or graphs, enabling diverse downstream tasks. However, existing approaches often focus on static graphs, limiting applicability in time-sensitive scenarios. To bridge this gap, our research proposes a novel node embedding method tailored for Discrete Time Dynamic Graphs (DTDGs). We introduce a framework for learning model parameters to generate embeddings at any time point inductively. Through extensive experiments, our model demonstrates superior performance over state-of-the-art static and dynamic embedding methods, highlighting its effectiveness and robustness. This advancement in dynamic graph representation learning holds promise for real-world applications, from biological proteinprotein interaction networks to large-scale human interaction networks. We provide publicly available code for reproducibility of our results https://github.com/khushnood/UnsupervisedInductiveNodeRepresentationForDynamicGraphs.