76 Hits in 2.0 sec

DyRep: Learning Representations over Dynamic Graphs

Rakshit Trivedi, Mehrdad Farajtabar, Prasenjeet Biswal, Hongyuan Zha
2019 International Conference on Learning Representations  
Two fundamental questions arise in learning over dynamic graphs: (i) How to elegantly model dynamical processes over graphs?  ...  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  ...  We focus on two pertinent questions fundamental to representation learning over dynamic graphs: (i) What can serve as an elegant model for dynamic processes over graphs?  ... 
dblp:conf/iclr/TrivediFBZ19 fatcat:z6og4ca52rawpmj2bnubg7vdfq

Representation Learning over Dynamic Graphs [article]

Rakshit Trivedi, Mehrdad Farajtabar, Prasenjeet Biswal, Hongyuan Zha
2018 arXiv   pre-print
How can we effectively encode evolving information over dynamic graphs into low-dimensional representations?  ...  In this paper, we propose DyRep, an inductive deep representation learning framework that learns a set of functions to efficiently produce low-dimensional node embeddings that evolves over time.  ...  learning over dynamic graph structured data.  ... 
arXiv:1803.04051v2 fatcat:gcgfprjh6fhpbhgcegbou4aiee

Subset Node Representation Learning over Large Dynamic Graphs [article]

Xingzhi Guo, Baojian Zhou, Steven Skiena
2021 arXiv   pre-print
Dynamic graph representation learning is a task to learn node embeddings over dynamic networks, and has many important applications, including knowledge graphs, citation networks to social networks.  ...  In this paper, we propose a new method, namely Dynamic Personalized PageRank Embedding (DynamicPPE) for learning a target subset of node representations over large-scale dynamic networks.  ...  In this paper, we propose a dynamic personalized PageRank embedding (DynamicPPE) method for learning a subset of node representations over large-sale dynamic networks.  ... 
arXiv:2106.01570v1 fatcat:iegarl2fsbhutb4sesspfab6he

Learning temporal attention in dynamic graphs with bilinear interactions

Boris Knyazev, Carolyn Augusta, Graham W Taylor
2021 PLoS ONE  
Reasoning about graphs evolving over time is a challenging concept in many domains, such as bioinformatics, physics, and social networks.  ...  Moreover, our learned attention is semantically interpretable and infers connections similar to actual graphs.  ...  This approach is similar to DyRep, since it also relies on the temporal point processes and uses a neural network to learn dynamic representation.  ... 
doi:10.1371/journal.pone.0247936 pmid:33661968 pmcid:PMC7932168 fatcat:lrqxxoio3jaz5kwzpjf6hnjvaq

Learning Temporal Attention in Dynamic Graphs with Bilinear Interactions [article]

Boris Knyazev, Carolyn Augusta, Graham W. Taylor
2020 arXiv   pre-print
Reasoning about graphs evolving over time is a challenging concept in many domains, such as bioinformatics, physics, and social networks.  ...  Moreover, our learned attention is semantically interpretable and infers connections similar to actual graphs.  ...  DyRep [14] is a method that has been proposed for learning from dynamic graphs based on temporal point processes [35] .  ... 
arXiv:1909.10367v2 fatcat:uno6dykq7bckrb35liuakxdbmi

Robust Knowledge Adaptation for Dynamic Graph Neural Networks [article]

Hanjie Li, Changsheng Li, Kaituo Feng, Ye Yuan, Guoren Wang, Hongyuan Zha
2022 arXiv   pre-print
In this paper, we propose AdaNet: a robust knowledge Adaptation framework via reinforcement learning for dynamic graph neural Networks.  ...  By this means, we can adaptively propagate knowledge to other nodes for learning robust node embedding representations.  ...  It could capture the temporal information as the dynamic graph evolves. • DyRep [31] is a representation learning method based on temporal point process for dynamic graph. • CTDNE [54] is a transductive  ... 
arXiv:2207.10839v1 fatcat:hj6rmxcbxzfmrdbmzr4jiiwzc4

Adaptive Data Augmentation on Temporal Graphs

Yiwei Wang, Yujun Cai, Yuxuan Liang, Henghui Ding, Changhu Wang, Siddharth Bhatia, Bryan Hooi
2021 Neural Information Processing Systems  
Temporal Graph Networks (TGNs) are powerful on modeling temporal graph data based on their increased complexity.  ...  To address this issue, our idea is to transform the temporal graphs using data augmentation (DA) with adaptive magnitudes, so as to effectively augment the input features and preserve the essential semantic  ...  Related Work Although many methods have been proposed for representation learning on static graphs [24, 9, 14, 15, 10, 29, 27, 18, 32, 34, 36] , the work on representation learning in temporal graphs  ... 
dblp:conf/nips/WangCLDWBH21 fatcat:ua7bysgvgzhppjkrpb3dfk6qwe

Temporal Graph Network Embedding with Causal Anonymous Walks Representations [article]

Ilya Makarov, Andrey Savchenko, Arseny Korovko, Leonid Sherstyuk, Nikita Severin, Aleksandr Mikheev, Dmitrii Babaev
2021 arXiv   pre-print
In this paper, we propose a novel approach for dynamic network representation learning based on Temporal Graph Network by using a highly custom message generating function by extracting Causal Anonymous  ...  Many tasks in graph machine learning, such as link prediction and node classification, are typically solved by using representation learning, in which each node or edge in the network is encoded via an  ...  Dynamic graph in general is a graph, which structure and node/edge attributes change over time.  ... 
arXiv:2108.08754v2 fatcat:p77az7gfsvenfepsinudt7isni

Towards Better Evaluation for Dynamic Link Prediction [article]

Farimah Poursafaei, Shenyang Huang, Kellin Pelrine, Reihaneh Rabbany
2022 arXiv   pre-print
There has been recent success in learning from static graphs, but despite their prevalence, learning from time-evolving graphs remains challenging.  ...  Lastly, we introduce five new dynamic graph datasets from a diverse set of domains missing from current benchmarks, providing new challenges and opportunities for future research.  ...  Dynamic Graph Representation Learning. Recently there is a surge of interest towards temporal networks. Kazemi et al. [14] present a survey of advances in representation learning on dynamic graphs.  ... 
arXiv:2207.10128v1 fatcat:rswm7eqztnhq5flmmmq5q6zglu

Inductive Representation Learning in Temporal Networks via Causal Anonymous Walks [article]

Yanbang Wang, Yen-Yu Chang, Yunyu Liu, Jure Leskovec, Pan Li
2021 arXiv   pre-print
Inductive representation learning of temporal networks should be able to capture such laws and further be applied to systems that follow the same laws but have not been unseen during the training stage  ...  Temporal networks serve as abstractions of many real-world dynamic systems.  ...  Dyrep: Learning representations over dynamic graphs. In International Conference on Learning Representation, 2019.  ... 
arXiv:2101.05974v4 fatcat:cw2vpjrqpzgc7exzkvtncduhau

CEP3: Community Event Prediction with Neural Point Process on Graph [article]

Xuhong Wang, Sirui Chen, Yixuan He, Minjie Wang, Quan Gan, Yupu Yang, Junchi Yan
2022 arXiv   pre-print
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  ...  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  ...  Continuous Temporal Dynamic Graph (CTDG) is a common representation paradigm for organizing dynamic interaction events over time, with edges and nodes denoting the events and the pairwise involved entities  ... 
arXiv:2205.10624v1 fatcat:w56wj2zm4bh5veun2jupcjil64

Continuous Temporal Graph Networks for Event-Based Graph Data [article]

Jin Guo, Zhen Han, Zhou Su, Jiliang Li, Volker Tresp, Yuyi Wang
2022 arXiv   pre-print
The key idea is to use neural ordinary differential equations (ODE) to characterize the continuous dynamics of node representations over dynamic graphs.  ...  Previous methods encode time-evolving relational information into a low-dimensional representation by specifying discrete layers of neural networks, while real-world dynamic graphs often vary continuously  ...  Learning the node representation on dynamic graphs is a very challenging task.  ... 
arXiv:2205.15924v1 fatcat:wdowouoz65a73jaandx63lmspu

Temporal Graph Networks for Deep Learning on Dynamic Graphs [article]

Emanuele Rossi, Ben Chamberlain, Fabrizio Frasca, Davide Eynard, Federico Monti, Michael Bronstein
2020 arXiv   pre-print
or connectivity over time).  ...  In this paper, we present Temporal Graph Networks (TGNs), a generic, efficient framework for deep learning on dynamic graphs represented as sequences of timed events.  ...  RELATED WORK Early models for learning on dynamic graphs focused on DTDGs.  ... 
arXiv:2006.10637v3 fatcat:dwapy3wsffgs7l63c24pltom7e

ConTIG: Continuous Representation Learning on Temporal Interaction Graphs [article]

Xu Yan, Xiaoliang Fan, Peizhen Yang, Zonghan Wu, Shirui Pan, Longbiao Chen, Yu Zang, Cheng Wang
2021 arXiv   pre-print
Representation learning on temporal interaction graphs (TIG) is to model complex networks with the dynamic evolution of interactions arising in a broad spectrum of problems.  ...  In this paper, we propose a two-module framework named ConTIG, a continuous representation method that captures the continuous dynamic evolution of node embedding trajectories.  ...  For temporal graphs, [49] learns the evolution of the temporal knowledge graph dynamics over time using ODEs as a tool.  ... 
arXiv:2110.06088v1 fatcat:3zrmlzmmsrd6zkfz24culky2fa

Inductive Representation Learning in Temporal Networks via Mining Neighborhood and Community Influences [article]

Meng Liu, Yong Liu
2021 arXiv   pre-print
Network representation learning aims to generate an embedding for each node in a network, which facilitates downstream machine learning tasks such as node classification and link prediction.  ...  Therefore, we propose a new inductive network representation learning method called MNCI by mining neighborhood and community influences in temporal networks.  ...  Unlike transductive learning, inductive learning attempts to learn a model that can dynamically update node embeddings over time.  ... 
arXiv:2110.00267v2 fatcat:okqk5ucnyzh3ffptnpgsp4f4d4
« Previous Showing results 1 — 15 out of 76 results