More Like this

1. Generating Evolving Property Graphs with Attribute-Aware Preferential Attachment

   https://doi.org/10.1145/3209950.3209954  

   Aghasadeghi, Amir; Stoyanovich, Julia (June 2017, DBTest'18 Proceedings of the Workshop on Testing Database Systems)

   In recent years there has been significant interest in evolutionary analysis of large-scale networks. Researchers study network evolution rate and mechanisms, the impact of specific events on evolution, and spatial and spatio-temporal patterns. To support data scientists who are studying network evolution, there is a need to develop scalable and generalizable systems. Tangible systems progress in turn depends on the availability of standardized datasets on which performance can be tested. In this work, we make progress towards a data generator for evolving property graphs, which represent evolution of graph topology, and of vertex and edge attributes. We propose an attribute-based model of preferential attachment, and instantiate this model on a co-authorship network derived from DBLP, with attributes representing publication venues of the authors. We show that this attribute-based model predicts which edges are created more accurately than a structure-only model. Finally, we demonstrate that synthetic graphs are indeed useful for evaluating performance of evolving graph query primitives. 

   more » « less
2. DyExplainer: Self-explainable Dynamic Graph Neural Network with Sparse Attentions

   https://doi.org/10.1145/3729173  

   Wang, Tianchun; Luo, Dongsheng; Cheng, Wei; Chen, Haifeng; Zhang, Xiang (May 2025, ACM Transactions on Knowledge Discovery from Data)

   Graph Neural Networks (GNNs) resurge as a trending research subject owing to their impressive ability to capture representations from graph-structured data. However, the black-box nature of GNNs presents a significant challenge in terms of comprehending and trusting these models, thereby limiting their practical applications in mission-critical scenarios. Although there has been substantial progress in the field of explaining GNNs in recent years, the majority of these studies are centered on static graphs, leaving the explanation of dynamic GNNs less explored. Dynamic GNNs, with their ever-evolving graph structures, pose a unique challenge and require additional efforts to effectively capture temporal dependencies and structural relationships. To address this challenge, we present DyExplainer, a novel approach to explaining dynamic GNNs on the fly. DyExplainer trains a dynamic GNN backbone to extract representations of the graph at each snapshot, while simultaneously exploring structural relationships and temporal dependencies through a sparse attention technique. To preserve the desired properties of the explanation, such as structural consistency and temporal continuity, we augment our approach with contrastive learning techniques to providea priori-guided regularization. To model longer-term temporal dependencies, we develop a buffer-based live-updating scheme for training. The results of our extensive experiments on various datasets demonstrate the superiority of DyExplainer, not only providing faithful explainability of the model predictions but also significantly improving the model prediction accuracy, as evidenced in the link prediction task. 

   more » « less
3. DYREP: Learning Representations Over Dynamic Graphs

   Trivedi, Rakshit; Farajtabar, Mehrdad; Biswal, Prasenjeet; Zha, Hongyuan (January 2019, International Conference on Learning Representation)

   Representation Learning over graph structured data has received significant attention recently due to its ubiquitous applicability. However, most advancements have been made in static graph settings while efforts for jointly learning dynamic of the graph and dynamic on the graph are still in an infant stage. Two fundamental questions arise in learning over dynamic graphs: (i) How to elegantly model dynamical processes over graphs? (ii) How to leverage such a model to effectively encode evolving graph information into low-dimensional representations? We present DyRep - a novel modeling framework for dynamic graphs that posits representation learning as a latent mediation process bridging two observed processes namely – dynamics of the network (realized as topological evolution) and dynamics on the network (realized as activities between nodes). Concretely, we propose a two-time scale deep temporal point process model that captures the interleaved dynamics of the observed processes. This model is further parameterized by a temporal-attentive representation network that encodes temporally evolving structural information into node representations which in turn drives the nonlinear evolution of the observed graph dynamics. Our unified framework is trained using an efficient unsupervised procedure and has capability to generalize over unseen nodes. We demonstrate that DyRep outperforms state-of-the-art baselines for dynamic link prediction and time prediction tasks and present extensive qualitative insights into our framework. 

   more » « less
4. DyRep: Learning Representations over Dynamic Graphs

   Trivedi, Rakshit; Farajtabar, Mehrdad; Biswal, Prasenjeet; Zha, Hongyuan (April 2019, International Conference on Learning Representations)

   Representation Learning over graph structured data has received significant atten- tion recently due to its ubiquitous applicability. However, most advancements have been made in static graph settings while efforts for jointly learning dynamic of the graph and dynamic on the graph are still in an infant stage. Two fundamental questions arise in learning over dynamic graphs: (i) How to elegantly model dynamical processes over graphs? (ii) How to leverage such a model to effectively encode evolving graph information into low-dimensional representations? We present DyRep - a novel modeling framework for dynamic graphs that posits representation learning as a latent mediation process bridging two observed processes namely – dynamics of the network (realized as topological evolution) and dynamics on the network (realized as activities between nodes). Concretely, we propose a two-time scale deep temporal point process model that captures the interleaved dynamics of the observed processes. This model is further parameterized by a temporal-attentive representation network that encodes temporally evolving structural information into node representations which in turn drives the nonlinear evolution of the observed graph dynamics. Our unified framework is trained using an efficient unsupervised procedure and has capability to generalize over unseen nodes. We demonstrate that DyRep outperforms state-of-the-art baselines for dynamic link prediction and time prediction tasks and present extensive qualitative insights into our framework. 

   more » « less
5. DyRep: Learning Representations over Dynamic Graphs

   Trivedi, Rakshit; Farajtabar, Mehrdad; Biswal, Prasenjeet; Zha, Hongyuan (May 2019, International Conference on Learning Representations)

   Representation Learning over graph structured data has received significant attention recently due to its ubiquitous applicability. However, most advancements have been made in static graph settings while efforts for jointly learning dynamic of the graph and dynamic on the graph are still in an infant stage. Two fundamental questions arise in learning over dynamic graphs: (i) How to elegantly model dynamical processes over graphs? (ii) How to leverage such a model to effectively encode evolving graph information into low-dimensional representations? We present DyRep - a novel modeling framework for dynamic graphs that posits representation learning as a latent mediation process bridging two observed processes namely -- dynamics of the network (realized as topological evolution) and dynamics on the network (realized as activities between nodes). Concretely, we propose a two-time scale deep temporal point process model that captures the interleaved dynamics of the observed processes. This model is further parameterized by a temporal-attentive representation network that encodes temporally evolving structural information into node representations which in turn drives the nonlinear evolution of the observed graph dynamics. Our unified framework is trained using an efficient unsupervised procedure and has capability to generalize over unseen nodes. We demonstrate that DyRep outperforms state-of-the-art baselines for dynamic link prediction and time prediction tasks and present extensive qualitative insights into our framework. 

   more » « less