Search for: All records

Memory-based Temporal Graph Neural Networks are powerful tools in dynamic graph representation learning and have demonstrated superior performance in many real-world applications. However, their node memory favors smaller batch sizes to capture more dependencies in graph events and needs to be maintained synchronously across all trainers. As a result, existing frameworks suffer from accuracy loss when scaling to multiple GPUs. Even worse, the tremendous overhead of synchronizing the node memory makes it impractical to deploy the solution in GPU clusters. In this work, we propose DistTGL — an efficient and scalable solution to train memory-based TGNNs on distributed GPU clusters. DistTGL has three improvements over existing solutions: an enhanced TGNN model, a novel training algorithm, and an optimized system. In experiments, DistTGL achieves near-linear convergence speedup, outperforming the state-of-the-art single-machine method by 14.5% in accuracy and 10.17× in training throughput. 

Transparency and accountability have become major concerns for black-box machine learning (ML) models. Proper explanations for the model behavior increase model transparency and help researchers develop more accountable models. Graph neural networks (GNN) have recently shown superior performance in many graph ML problems than traditional methods, and explaining them has attracted increased interest. However, GNN explanation for link prediction (LP) is lacking in the literature. LP is an essential GNN task and corresponds to web applications like recommendation and sponsored search on web. Given existing GNN explanation methods only address node/graph-level tasks, we propose Path-based GNN Explanation for heterogeneous Link prediction (PaGE-Link) that generates explanations with connection interpretability, enjoys model scalability, and handles graph heterogeneity. Qualitatively, PaGE-Link can generate explanations as paths connecting a node pair, which naturally captures connections between the two nodes and easily transfer to human-interpretable explanations. Quantitatively, explanations generated by PaGE-Link improve AUC for recommendation on citation and user-item graphs by 9 - 35% and are chosen as better by 78.79% of responses in human evaluation. 

Vibrational modes in mechanical resonators provide a promising candidate to interface and manipulate classical and quantum information. The observation of coherent dynamics between distant mechanical resonators can be a key step toward scalable phonon-based applications. Here we report tunable coherent phonon dynamics with an architecture comprising three graphene mechanical resonators coupled in series, where all resonators can be manipulated by electrical signals on control gates. We demonstrate coherent Rabi oscillations between spatially separated resonators indirectly coupled via an intermediate resonator serving as a phonon cavity. The Rabi frequency fits well with the microwave burst power on the control gate. We also observe Ramsey interference, where the oscillation frequency corresponds to the indirect coupling strength between these resonators. Such coherent processes indicate that information encoded in vibrational modes can be transferred and stored between spatially separated resonators, which can open the venue of on-demand phonon-based information processing.