Dynamic spiking graph neural networks

N Yin, M Wang, Z Chen, G De Masi, H **ong… - Proceedings of the AAAI …, 2024‏ - ojs.aaai.org
Abstract The integration of Spiking Neural Networks (SNNs) and Graph Neural Networks
(GNNs) is gradually attracting attention due to the low power consumption and high …

Messages are never propagated alone: Collaborative hypergraph neural network for time-series forecasting

N Yin, L Shen, H **ong, B Gu, C Chen… - … on Pattern Analysis …, 2023‏ - ieeexplore.ieee.org
This paper delves into the problem of correlated time-series forecasting in practical
applications, an area of growing interest in a multitude of fields such as stock price …

Dynamic hypergraph structure learning for traffic flow forecasting

Y Zhao, X Luo, W Ju, C Chen, XS Hua… - 2023 IEEE 39th …, 2023‏ - ieeexplore.ieee.org
This paper studies the problem of traffic flow forecasting, which aims to predict future traffic
conditions on the basis of road networks and traffic conditions in the past. The problem is …

S3GCL: Spectral, swift, spatial graph contrastive learning

G Wan, Y Tian, W Huang, NV Chawla… - Forty-first International …, 2024‏ - openreview.net
Graph Contrastive Learning (GCL) has emerged as a highly effective self-supervised
approach in graph representation learning. However, prevailing GCL methods confront two …

CoCo: A coupled contrastive framework for unsupervised domain adaptive graph classification

N Yin, L Shen, M Wang, L Lan, Z Ma… - International …, 2023‏ - proceedings.mlr.press
Although graph neural networks (GNNs) have achieved impressive achievements in graph
classification, they often need abundant task-specific labels, which could be extensively …

Revisiting multimodal emotion recognition in conversation from the perspective of graph spectrum

T Meng, F Zhang, Y Shou, W Ai, N Yin, K Li - arxiv preprint arxiv …, 2024‏ - arxiv.org
Efficiently capturing consistent and complementary semantic features in a multimodal
conversation context is crucial for Multimodal Emotion Recognition in Conversation (MERC) …

Sa-gda: Spectral augmentation for graph domain adaptation

J Pang, Z Wang, J Tang, M **ao, N Yin - Proceedings of the 31st ACM …, 2023‏ - dl.acm.org
Graph neural networks (GNNs) have achieved impressive impressions for graph-related
tasks. However, most GNNs are primarily studied under the cases of signal domain with …

Continuous spiking graph neural networks

N Yin, M Wan, L Shen, HL Patel, B Li, B Gu… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Continuous graph neural networks (CGNNs) have garnered significant attention due to their
ability to generalize existing discrete graph neural networks (GNNs) by introducing …

Robust fair clustering: A novel fairness attack and defense framework

A Chhabra, P Li, P Mohapatra, H Liu - arxiv preprint arxiv:2210.01953, 2022‏ - arxiv.org
Clustering algorithms are widely used in many societal resource allocation applications,
such as loan approvals and candidate recruitment, among others, and hence, biased or …

Hypergraph neural architecture search

W Lin, X Peng, Z Yu, T ** - Proceedings of the AAAI Conference on …, 2024‏ - ojs.aaai.org
In recent years, Hypergraph Neural Networks (HGNNs) have achieved considerable
success by manually designing architectures, which are capable of extracting effective …