Semi-supervised Network Embedding with Differentiable Deep Quantisation
This work addresses storage and efficiency challenges for large-scale network analytics, offering a practical solution with incremental improvements over prior semi-supervised embedding methods.
The paper tackles the problem of large storage requirements for network embeddings by developing d-SNEQ, a differentiable quantisation method that compresses embeddings, reducing storage by up to 32 times and improving retrieval speed while outperforming state-of-the-art methods in tasks like link prediction and node classification.
Learning accurate low-dimensional embeddings for a network is a crucial task as it facilitates many downstream network analytics tasks. For large networks, the trained embeddings often require a significant amount of space to store, making storage and processing a challenge. Building on our previous work on semi-supervised network embedding, we develop d-SNEQ, a differentiable DNN-based quantisation method for network embedding. d-SNEQ incorporates a rank loss to equip the learned quantisation codes with rich high-order information and is able to substantially compress the size of trained embeddings, thus reducing storage footprint and accelerating retrieval speed. We also propose a new evaluation metric, path prediction, to fairly and more directly evaluate model performance on the preservation of high-order information. Our evaluation on four real-world networks of diverse characteristics shows that d-SNEQ outperforms a number of state-of-the-art embedding methods in link prediction, path prediction, node classification, and node recommendation while being far more space- and time-efficient.