paper-with-me

홈 › Papers

Learning Conjoint Attentions for Graph Neural Nets

2021-02-05 · NeurIPS 2021 12 · Tiantian He, Yew-Soon Ong, Lu Bai

In this paper, we present Conjoint Attentions (CAs), a class of novel learning-to-attend strategies for graph neural networks (GNNs). Besides considering the layer-wise node features propagated within the GNN, CAs can additionally incorporate various structural interventions, such as node cluster embedding, and higher-order structural correlations that can be learned outside of GNN, when computing attention scores. The node features that are regarded as significant by the conjoint criteria are therefore more likely to be propagated in the GNN. Given the novel Conjoint Attention strategies, we then propose Graph conjoint attention networks (CATs) that can learn representations embedded with significant latent features deemed by the Conjoint Attentions. Besides, we theoretically validate the discriminative capacity of CATs. CATs utilizing the proposed Conjoint Attention strategies have been extensively tested in well-established benchmarking datasets and comprehensively compared with state-of-the-art baselines. The obtained notable performance demonstrates the effectiveness of the proposed Conjoint Attentions.

📄 PDF Abstract BibTeX arXiv:2102.03147

Code (1)

he-tiantian/cats 공식 구현 pytorch

Tasks

BenchmarkingGraph Attention

Similar Papers 제목 키워드 기반

Learning Deep Matrix Representations

2017-03-04 · Kien Do, Truyen Tran, Svetha Venkatesh

We present a new distributed representation in deep neural nets wherein the information is represented in native form as a matrix. This differs from current neural architectures that rely on vector representations. We co…

EEGElectroencephalogram (EEG)Face ReconstructionGeneral Classification+1

COOL: A Conjoint Perspective on Spatio-Temporal Graph Neural Network for Traffic Forecasting

2024-03-02 · Wei Ju, Yusheng Zhao, Yifang Qin, Siyu Yi 외

This paper investigates traffic forecasting, which attempts to forecast the future state of traffic based on historical situations. This problem has received ever-increasing attention in various scenarios and facilitated…

DecoderDiversityGraph Neural Network

Are Powerful Graph Neural Nets Necessary? A Dissection on Graph Classification

2019-05-11 · Ting Chen, Song Bian, Yizhou Sun

Graph Neural Nets (GNNs) have received increasing attentions, partially due to their superior performance in many node and graph classification tasks. However, there is a lack of understanding on what they are learning a…

ClassificationGeneral ClassificationGraph Classification

Using Machine Learning to Test Causal Hypotheses in Conjoint Analysis

2022-01-20 · Dae Woong Ham, Kosuke Imai, Lucas Janson

Conjoint analysis is a popular experimental design used to measure multidimensional preferences. Researchers examine how varying a factor of interest, while controlling for other relevant factors, influences decision-mak…

BIG-bench Machine LearningDecision MakingExperimental Design

Can LLMs Capture Human Preferences?

2023-05-04 · Ali Goli, Amandeep Singh

We explore the viability of Large Language Models (LLMs), specifically OpenAI's GPT-3.5 and GPT-4, in emulating human survey respondents and eliciting preferences, with a focus on intertemporal choices. Leveraging the ex…

Benchmarking