Shift Aggregate Extract Networks
We introduce an architecture based on deep hierarchical decompositions to learn effective representations of large graphs. Our framework extends classic R-decompositions used in kernel methods, enabling nested part-of-part relations. Unlike recursive neural networks, which unroll a template on input graphs directly, we unroll a neural network template over the decomposition hierarchy, allowing us to deal with the high degree variability that typically characterize social network graphs. Deep hierarchical decompositions are also amenable to domain compression, a technique that reduces both space and time complexity by exploiting symmetries. We show empirically that our approach is able to outperform current state-of-the-art graph classification methods on large social network datasets, while at the same time being competitive on small chemobiological benchmark datasets.
Code (0)
등록된 구현이 없습니다.
Tasks
General ClassificationGraph ClassificationSimilar Papers 제목 키워드 기반
Detecting Abnormal User Feedback Patterns through Temporal Sentiment Aggregation
In many real-world applications, such as customer feedback monitoring, brand reputation management, and product health tracking, understanding the temporal dynamics of user sentiment is crucial for early detection of ano…
Text ClassificationSentiment AnalysisAnomaly DetectionFederated Learning with Domain Shift Eraser
Federated learning (FL) is emerging as a promising technique for collaborative learning without local data leaving their devices. However, clients' data originating from diverse domains may degrade model performance due …
Federated LearningThe Asymmetric Harms of LLM Compression
Large language models (LLMs) compression reduces deployment costs, but standard aggregate metrics like perplexity and accuracy often mask underlying behavioral shifts. In this work, we systematically evaluate 3 LLMs acro…
Traffic4cast at NeurIPS 2021 -- Temporal and Spatial Few-Shot Transfer Learning in Gridded Geo-Spatial Processes
The IARAI Traffic4cast competitions at NeurIPS 2019 and 2020 showed that neural networks can successfully predict future traffic conditions 1 hour into the future on simply aggregated GPS probe data in time and space bin…
Transfer LearningRobust Federated Learning in the Face of Covariate Shift: A Magnitude Pruning with Hybrid Regularization Framework for Enhanced Model Aggregation
The development of highly sophisticated neural networks has allowed for fast progress in every field of computer vision, however, applications where annotated data is prohibited due to privacy or security concerns remain…
Federated Learning