Search for: All records

Deep learning’s performance has been extensively recognized recently. Graph neural networks (GNNs) are designed to deal with graph-structural data that classical deep learning does not easily manage. Since most GNNs were created using distinct theories, direct comparisons are impossible. Prior research has primarily concentrated on categorizing existing models, with little attention paid to their intrinsic connections. The purpose of this study is to establish a unified framework that integrates GNNs based on spectral graph and approximation theory. The framework incorporates a strong integration between spatial- and spectral-based GNNs while tightly associating approaches that exist within each respective domain.

A critical issue is determining the factors that control the year-to-year variability in precipitation over southern Asia. In this study, we employ a cyclostationary linear inverse model (CS-LIM) to quantify the relative contribution of tropical Pacific and Indian Ocean sea surface temperature anomalies (SSTAs) to the interannual variability of the Asian monsoon, especially Indian summer monsoon rainfall (ISMR). Through a series of CS-LIM experiments, we isolate the impacts of the direct forcing from Pacific SSTAs, Indian Ocean SSTAs, and their interaction on Asian monsoon rainfall variability. Our results reveal distinct patterns of influence with the direct forcing from the Pacific (Indian) Ocean tending to enhance (reduce) the magnitude of precipitation variability, while the Indo-Pacific interaction acts to strongly damp the variability of Asian monsoon precipitation, especially over India. We further investigate these specific impacts on ISMR by analyzing the relationship between tropical Indo-Pacific SSTAs and the leading three empirical orthogonal functions (EOFs) of ISMR. The results from our CS-LIM experiments indicate that the direct forcing from El Niño–Southern Oscillation (ENSO) enhances the variability of the first and third EOFs, while the Indian Ocean SSTA opposes ENSO’s effects, which is consistent with previous studies. Our new results show that the tropical Indo-Pacific interaction strongly damps ISMR variability, which is due to the ENSO-induced Indian Ocean dipole (IOD) opposing the direct impacts from ENSO on ISMR. Additionally, reduced ENSO amplitude and duration associated with the Indo-Pacific interaction may also contribute to the damping effect on ISMR, but this requires further study to understand the relevant mechanisms.

Top-k frequent items detection is a fundamental task in data stream mining. Many promising solutions are proposed to improve memory efficiency while still maintaining high accuracy for detecting the Top-k items. Despite the memory efficiency concern, the users could suffer from privacy loss if participating in the task without proper protection, since their contributed local data streams may continually leak sensitive individual information. However, most existing works solely focus on addressing either the memory-efficiency problem or the privacy concerns but seldom jointly, which cannot achieve a satisfactory tradeoff between memory efficiency, privacy protection, and detection accuracy.

In this paper, we present a novel framework HG-LDP to achieve accurate Top-k item detection at bounded memory expense, while providing rigorous local differential privacy (LDP) protection. Specifically, we identify two key challenges naturally arising in the task, which reveal that directly applying existing LDP techniques will lead to an inferior accuracy-privacy-memory efficiency tradeoff. Therefore, we instantiate three advanced schemes under the framework by designing novel LDP randomization methods, which address the hurdles caused by the large size of the item domain and by the limited space of the memory. We conduct comprehensive experiments on both synthetic and real-world datasets to show that the proposed advanced schemes achieve a superior accuracy-privacy-memory efficiency tradeoff, saving 2300× memory over baseline methods when the item domain size is 41,270. Our code is anonymously open-sourced via the link.