Graph-Survival: A Survival Analysis Framework for Machine Learning on
Temporal Networks
- URL: http://arxiv.org/abs/2203.07260v2
- Date: Tue, 15 Mar 2022 13:05:13 GMT
- Title: Graph-Survival: A Survival Analysis Framework for Machine Learning on
Temporal Networks
- Authors: Rapha\"el Romero, Bo Kang, Tijl De Bie
- Abstract summary: We propose a framework for designing generative models for continuous time temporal networks.
We propose a fitting method for models within this framework, and an algorithm for simulating new temporal networks having desired properties.
- Score: 14.430635608400982
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Continuous time temporal networks are attracting increasing attention due
their omnipresence in real-world datasets and they manifold applications. While
static network models have been successful in capturing static topological
regularities, they often fail to model effects coming from the causal nature
that explain the generation of networks. Exploiting the temporal aspect of
networks has thus been the focus of various studies in the last decades.
We propose a framework for designing generative models for continuous time
temporal networks. Assuming a first order Markov assumption on the
edge-specific temporal point processes enables us to flexibly apply survival
analysis models directly on the waiting time between events, while using
time-varying history-based features as covariates for these predictions. This
approach links the well-documented field of temporal networks analysis through
multivariate point processes, with methodological tools adapted from survival
analysis. We propose a fitting method for models within this framework, and an
algorithm for simulating new temporal networks having desired properties. We
evaluate our method on a downstream future link prediction task, and provide a
qualitative assessment of the network simulations.
Related papers
- Continuous-time Graph Representation with Sequential Survival Process [0.17265013728931003]
We propose a process relying on survival functions to model the durations of links and their absences over time.
GraSSP: Graph Representation with Sequential Survival Process forms a generic new likelihood explicitly accounting for intermittent edge-persistent networks.
We quantitatively assess the developed framework in various downstream tasks, such as link prediction and network completion.
arXiv Detail & Related papers (2023-12-20T14:46:54Z) - Direct Embedding of Temporal Network Edges via Time-Decayed Line Graphs [51.51417735550026]
Methods for machine learning on temporal networks generally exhibit at least one of two limitations.
We present a simple method that avoids both shortcomings: construct the line graph of the network, which includes a node for each interaction, and weigh the edges of this graph based on the difference in time between interactions.
Empirical results on real-world networks demonstrate our method's efficacy and efficiency on both edge classification and temporal link prediction.
arXiv Detail & Related papers (2022-09-30T18:24:13Z) - Generating fine-grained surrogate temporal networks [12.7211231166069]
We propose a novel and simple method for generating surrogate temporal networks.
Our method decomposes the input network into star-like structures evolving in time.
Then those structures are used as building blocks to generate a surrogate temporal network.
arXiv Detail & Related papers (2022-05-18T09:38:22Z) - Spatio-temporal Modeling for Large-scale Vehicular Networks Using Graph
Convolutional Networks [110.80088437391379]
A graph-based framework called SMART is proposed to model and keep track of the statistics of vehicle-to-temporal (V2I) communication latency across a large geographical area.
We develop a graph reconstruction-based approach using a graph convolutional network integrated with a deep Q-networks algorithm.
Our results show that the proposed method can significantly improve both the accuracy and efficiency for modeling and the latency performance of large vehicular networks.
arXiv Detail & Related papers (2021-03-13T06:56:29Z) - Radflow: A Recurrent, Aggregated, and Decomposable Model for Networks of
Time Series [77.47313102926017]
Radflow is a novel model for networks of time series that influence each other.
It embodies three key ideas: a recurrent neural network to obtain node embeddings that depend on time, the aggregation of the flow of influence from neighboring nodes with multi-head attention, and the multi-layer decomposition of time series.
We show that Radflow can learn different trends and seasonal patterns, that it is robust to missing nodes and edges, and that correlated temporal patterns among network neighbors reflect influence strength.
arXiv Detail & Related papers (2021-02-15T00:57:28Z) - Synergetic Learning of Heterogeneous Temporal Sequences for
Multi-Horizon Probabilistic Forecasting [48.8617204809538]
We propose Variational Synergetic Multi-Horizon Network (VSMHN), a novel deep conditional generative model.
To learn complex correlations across heterogeneous sequences, a tailored encoder is devised to combine the advances in deep point processes models and variational recurrent neural networks.
Our model can be trained effectively using variational inference and generates predictions with Monte-Carlo simulation.
arXiv Detail & Related papers (2021-01-31T11:00:55Z) - PRESTO: Simple and Scalable Sampling Techniques for the Rigorous
Approximation of Temporal Motif Counts [7.025709586759655]
We present an efficient and scalable algorithm to obtain rigorous approximations of the count of temporal motifs.
Our algorithm is based on a simple but effective sampling approach, which renders our algorithm practical for very large datasets.
arXiv Detail & Related papers (2021-01-18T16:35:12Z) - EPNE: Evolutionary Pattern Preserving Network Embedding [26.06068388979255]
We propose EPNE, a temporal network embedding model preserving evolutionary patterns of the local structure of nodes.
With the adequate modeling of temporal information, our model is able to outperform other competitive methods in various prediction tasks.
arXiv Detail & Related papers (2020-09-24T06:31:14Z) - Online Estimation and Community Detection of Network Point Processes for
Event Streams [12.211623200731788]
A common goal in network modeling is to uncover the latent community structure present among nodes.
We propose a fast online variational inference algorithm for estimating the latent structure underlying dynamic event arrivals on a network.
We demonstrate that online inference can obtain comparable performance, in terms of community recovery, to non-online variants.
arXiv Detail & Related papers (2020-09-03T15:39:55Z) - Supporting Optimal Phase Space Reconstructions Using Neural Network
Architecture for Time Series Modeling [68.8204255655161]
We propose an artificial neural network with a mechanism to implicitly learn the phase spaces properties.
Our approach is either as competitive as or better than most state-of-the-art strategies.
arXiv Detail & Related papers (2020-06-19T21:04:47Z) - Liquid Time-constant Networks [117.57116214802504]
We introduce a new class of time-continuous recurrent neural network models.
Instead of declaring a learning system's dynamics by implicit nonlinearities, we construct networks of linear first-order dynamical systems.
These neural networks exhibit stable and bounded behavior, yield superior expressivity within the family of neural ordinary differential equations.
arXiv Detail & Related papers (2020-06-08T09:53:35Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.