Time-Conditioned Dances with Simplicial Complexes: Zigzag Filtration Curve based Supra-Hodge Convolution Networks for Time-series Forecasting
Nov 28, 2022
Speakers
Yuzhou Chen
Speaker · 0 followers
H. Vincent Poor
Speaker · 0 followers
About
Graph neural networks (GNN) offer a new powerful alternative for multivariate time series forecasting, demonstrating remarkable success in a variety of spatio-temporal applications, from urban flow monitoring systems to health care informatics to financial analytics. Yet, such GNN models pre-dominantly capture only lower order interactions, that is, pairwise relations among nodes, and also largely ignore intrinsic time-conditioned information on the underlying topology of multivariate time series. To address these limitations, we propose a new time-aware GNN architecture which amplifies the power of the recently emerged simplicial neural networks with a time-conditioned topological knowledge representation in a form of zigzag persistence. That is, our new approach, Zigzag Filtration Curve based Supra-Hodge Convolution Networks (ZFC-SHCN) is built upon the two main components: (i) a new highly computationally efficient zigzag persistence curve which allows us to systematically encode time-conditioned topological information, and (ii) a new temporal multiplex graph representation module for learning higher-order network interactions. We discuss theoretical properties of the proposed time-conditioned topological knowledge representation and extensively validate the new time-aware ZFC-SHCN model in conjunction with time series forecasting on a broad range of synthetic and real world datasets: traffic flows, COVID-19 biosurveillance, Ethereum blockchain, surface air temperature, and vector autoregressions. Our experiments demonstrate that ZFC-SHCN achieves the state-of-the-art performance with lower requirements on computational costs.Graph neural networks (GNN) offer a new powerful alternative for multivariate time series forecasting, demonstrating remarkable success in a variety of spatio-temporal applications, from urban flow monitoring systems to health care informatics to financial analytics. Yet, such GNN models pre-dominantly capture only lower order interactions, that is, pairwise relations among nodes, and also largely ignore intrinsic time-conditioned information on the underlying topology of multivariate time serie…
Organizer
NeurIPS 2022
Account · 954 followers
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Learning in Observable POMDPs, without Computationally Intractable Oracles
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Personalized Federated Learning towards Communication Efficiency, Robustness and Fairness
Watch later
Shiyun Lin, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation
Watch later
Yufei Xu, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
ComGAN: Unsupervised Disentanglement and Segmentation via Image Composition
Watch later
Rui Ding, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Reinforcement Learning in a Birth and Death Process: Breaking the Dependence on the State Space
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Characteristics of Harmful Text: Translating Risks into Rigorous Evaluation Language Models
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%