CEP3: Community Event Prediction with Neural Point Process on Graph

Many real world applications can be formulated as event forecasting on Continuous Time Dynamic Graphs (CTDGs) where the occurrence of a timed event between two entities is represented as an edge along with its occurrence timestamp in the graphs.However, most previous works approach the problem in compromised settings, either formulating it as a link prediction task on the graph given the event time or a time prediction problem given which event will happen next. In this paper, we propose a novel model combining Graph Neural Networks and Marked Temporal Point Process (MTPP) that jointly forecasts multiple link events and their timestamps on communities over a CTDG. Moreover, to scale our model to large graphs, we factorize the jointly event prediction problem into three easier conditional probability modeling problems.To evaluate the effectiveness of our model and the rationale behind such a decomposition, we establish a set of benchmarks and evaluation metrics for this event forecasting task. Our experiments demonstrate the superior performance of our model in terms of both model accuracy and training efficiency.

[1]  Hongyuan Zha,et al.  Modeling Event Propagation via Graph Biased Temporal Point Process , 2019, IEEE Transactions on Neural Networks and Learning Systems.

[2]  Xixun Lin,et al.  Deep Structural Point Process for Learning Temporal Interaction Networks , 2021, ECML/PKDD.

[3]  Clara Meister,et al.  Language Model Evaluation Beyond Perplexity , 2021, ACL.

[4]  Stephan Günnemann,et al.  Neural Temporal Point Processes: A Review , 2021, IJCAI.

[5]  Jure Leskovec,et al.  Inductive Representation Learning in Temporal Networks via Causal Anonymous Walks , 2021, ICLR.

[6]  H. Jaeger.  A tutorial on training recurrent neural networks, covering BPTT, RTRL, EKF and the "echo state network" approach , 2021 .

[7]  Ashis Kumar Das,et al.  Predicting CoVID-19 community mortality risk using machine learning and development of an online prognostic tool , 2020, PeerJ.

[8]  Davide Eynard,et al.  Temporal Graph Networks for Deep Learning on Dynamic Graphs , 2020, ArXiv.

[9]  Zhen Zhang,et al.  Learning Temporal Interaction Graph Embedding via Coupled Memory Networks , 2020, WWW.

[10]  Da Xu,et al.  Inductive Representation Learning on Temporal Graphs , 2020, ICLR.

[11]  Rémy Cazabet,et al.  Community Discovery in Dynamic Networks: a Survey , 2019 .

[12]  Philip S. Yu,et al.  Temporal Network Embedding with Micro- and Macro-dynamics , 2019, CIKM.

[13]  Alex Smola,et al.  Deep Graph Library: Towards Efficient and Scalable Deep Learning on Graphs , 2019, ArXiv.

[14]  Jure Leskovec,et al.  Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks , 2019, KDD.

[15]  Guihai Chen,et al.  Dual Sequential Prediction Models Linking Sequential Recommendation and Information Dissemination , 2019, KDD.

[16]  Hongyuan Zha,et al.  DyRep: Learning Representations over Dynamic Graphs , 2019, ICLR.

[17]  Pedro A. Szekely,et al.  Recurrent Event Network for Reasoning over Temporal Knowledge Graphs , 2019, ArXiv.

[18]  Philip S. Yu,et al.  A Comprehensive Survey on Graph Neural Networks , 2019, IEEE Transactions on Neural Networks and Learning Systems.

[19]  Le Song,et al.  Learning Temporal Point Processes via Reinforcement Learning , 2018, NeurIPS.

[20]  Junjie Wu,et al.  Embedding Temporal Network via Neighborhood Formation , 2018, KDD.

[21]  Ryan A. Rossi,et al.  Continuous-Time Dynamic Network Embeddings , 2018, WWW.

[22]  K. Nawata,et al.  Multi-step prediction for influenza outbreak by an adjusted long short-term memory , 2018, Epidemiology and Infection.

[23]  Cyrus Shahabi,et al.  Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting , 2017, ICLR.

[24]  Yupeng Gu,et al.  The Co-Evolution Model for Social Network Evolving and Opinion Migration , 2017, KDD.

[25]  Xueqi Cheng,et al.  Cascade Dynamics Modeling with Attention-based Recurrent Neural Network , 2017, IJCAI.

[26]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[27]  Le Song,et al.  Know-Evolve: Deep Temporal Reasoning for Dynamic Knowledge Graphs , 2017, ICML.

[28]  Le Song,et al.  Wasserstein Learning of Deep Generative Point Process Models , 2017, NIPS.

[29]  Hongyuan Zha,et al.  Modeling the Intensity Function of Point Process Via Recurrent Neural Networks , 2017, AAAI.

[30]  Jason Eisner,et al.  The Neural Hawkes Process: A Neurally Self-Modulating Multivariate Point Process , 2016, NIPS.

[31]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[32]  Hong Chen,et al.  Modeling Information Diffusion over Social Networks for Temporal Dynamic Prediction , 2013, IEEE Transactions on Knowledge and Data Engineering.

[33]  Xinghuo Yu,et al.  Detection of Money Laundering Groups: Supervised Learning on Small Networks , 2017, AAAI Workshops.

[34]  Utkarsh Upadhyay,et al.  Recurrent Marked Temporal Point Processes: Embedding Event History to Vector , 2016, KDD.

[35]  Rebecca Willett,et al.  Tracking Dynamic Point Processes on Networks , 2014, IEEE Transactions on Information Theory.

[36]  Ulrike Goldschmidt,et al.  An Introduction To The Theory Of Point Processes , 2016 .

[37]  Le Song,et al.  Coevolutionary Latent Feature Processes for Continuous-Time User-Item Interactions , 2016, NIPS.

[38]  Shuang Li,et al.  COEVOLVE: A Joint Point Process Model for Information Diffusion and Network Co-evolution , 2015, NIPS.

[39]  Quoc V. Le,et al.  Sequence to Sequence Learning with Neural Networks , 2014, NIPS.

[40]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[41]  Jennifer Mathieu,et al.  Developing a Tagalog Linguistic Inquiry and Word Count (LIWC) ‘Disaster’ Dictionary for Understanding Mixed Language Social Media: A Work-in-Progress Paper , 2014, LaTeCH@EACL.

[42]  Alex Pentland,et al.  Sensing the "Health State" of a Community , 2012, IEEE Pervasive Computing.

[43]  Yizhou Sun,et al.  On community outliers and their efficient detection in information networks , 2010, KDD.

[44]  Carlos Capistrán,et al.  Multi-horizon inflation forecasts using disaggregated data , 2010 .

[45]  S. Sulakshin.  A Quantitative Political Spectrum and Forecasting of Social Evolution , 2010 .

[46]  O. Aalen,et al.  Survival and Event History Analysis: A Process Point of View , 2008 .

[47]  Jean-Loup Guillaume,et al.  Fast unfolding of communities in large networks , 2008, 0803.0476.

[48]  Jeffrey D. Scargle,et al.  An Introduction to the Theory of Point Processes, Vol. I: Elementary Theory and Methods , 2004, Technometrics.

[49]  A. Hawkes.  Spectra of some self-exciting and mutually exciting point processes , 1971 .

[50]  E. Çinlar,et al.  On the Superposition of Point Processes , 1968 .