EasyDGL: Encode, Train and Interpret for Continuous-time Dynamic Graph Learning
Dynamic graphs arise in various real-world applications, and it is often welcomed to model the dynamics directly in continuous time domain for its flexibility. This paper aims to design an easy-to-use pipeline (termed as EasyDGL which is also due to its implementation by DGL toolkit) composed of three key modules with both strong fitting ability and interpretability. Specifically the proposed pipeline which involves encoding, training and interpreting: i) a temporal point process (TPP) modulated attention architecture to endow the continuous-time resolution with the coupled spatiotemporal dynamics of the observed graph with edge-addition events; ii) a principled loss composed of task-agnostic TPP posterior maximization based on observed events on the graph, and a task-aware loss with a masking strategy over dynamic graph, where the covered tasks include dynamic link prediction, dynamic node classification and node traffic forecasting; iii) interpretation of the model outputs (e.g., representations and predictions) with scalable perturbation-based quantitative analysis in the graph Fourier domain, which could more comprehensively reflect the behavior of the learned model. Extensive experimental results on public benchmarks show the superior performance of our EasyDGL for time-conditioned predictive tasks, and in particular demonstrate that EasyDGL can effectively quantify the predictive power of frequency content that a model learn from the evolving graph data.
Code (1)
Tasks
Dynamic Link PredictionDynamic Node ClassificationFraud DetectionGraph LearningLink PredictionNode ClassificationSequential RecommendationTraffic PredictionSimilar Papers 제목 키워드 기반
SELDON: Supernova Explosions Learned by Deep ODE Networks
The discovery rate of optical transients will explode to 10 million public alerts per night once the Vera C. Rubin Observatory's Legacy Survey of Space and Time comes online, overwhelming the traditional physics-based in…
Binary Sparse Coding for Interpretability
Sparse autoencoders (SAEs) are used to decompose neural network activations into sparsely activating features, but many SAE features are only interpretable at high activation strengths. To address this issue we propose t…
Learning Disentangled Joint Continuous and Discrete Representations
We present a framework for learning disentangled and interpretable jointly continuous and discrete representations in an unsupervised manner. By augmenting the continuous latent distribution of variational autoencoders w…
Continuous Interpretive Steering for Scalar Diversity
Pragmatic inference is inherently graded. Different lexical items give rise to pragmatic enrichment to different degrees. Scalar implicature exemplifies this property through scalar diversity, where implicature strength …
Explainable Multi-modal Time Series Prediction with LLM-in-the-Loop
Time series analysis provides essential insights for real-world system dynamics and informs downstream decision-making, yet most existing methods often overlook the rich contextual signals present in auxiliary modalities…
PredictionTime SeriesTime Series AnalysisTime Series Prediction