Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- abstractAugust 2022
Deep Learning on Graphs: Methods and Applications (DLG-KDD2022)
KDD '22: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data MiningPages 4906–4907https://doi.org/10.1145/3534678.3542907Deep Learning models are at the core of research in Artificial Intelligence research today. A tide in research for deep learning on graphs or graph neural networks. This wave of research at the intersection of graph theory and deep learning has also ...
- abstractAugust 2022
8th SIGKDD International Workshop on Mining and Learning from Time Series -- Deep Forecasting: Models, Interpretability, and Applications
- Sanjay Purushotham,
- Jun Huan,
- Cong Shen,
- Dongjin Song,
- Yuyang Wang,
- Jan Gasthaus,
- Hilaf Hasson,
- Youngsuk Park,
- Sungyong Seo,
- Yuriy Nevmyvaka
KDD '22: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data MiningPages 4896–4897https://doi.org/10.1145/3534678.3542889Time series data are ubiquitous, and is one of the fastest growing and richest types of data. Recent advances in sensing technologies has resulted in a rapid growth in the size and complexity of time series archives. This demands development of new tools ...
- abstractAugust 2022
Classifying Multimodal Data Using Transformers
KDD '22: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data MiningPages 4780–4781https://doi.org/10.1145/3534678.3542634The increasing prevalence of multimodal data in our society has led to the increased need for machines to make sense of such data holistically. However, data scientists and machine learning engineers aspiring to work on such data face challenges fusing ...
- abstractAugust 2022
Deep Search Relevance Ranking in Practice
KDD '22: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data MiningPages 4810–4811https://doi.org/10.1145/3534678.3542632Machine learning techniques for developing industry-scale search engines have long been a prominent part of most domains and their online products. Search relevance algorithms are key components of products across different fields, including e-commerce, ...
- abstractAugust 2022
Graph Neural Networks in Life Sciences: Opportunities and Solutions
KDD '22: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data MiningPages 4834–4835https://doi.org/10.1145/3534678.3542628Graphs (or networks) are ubiquitous representation in life sciences and medicine, from molecular interactions maps, signaling transduction pathways, to graphs of scientific knowledge and patient- disease-intervention relationships derived from population ...
-
- abstractAugust 2022
Anomaly Detection for Spatiotemporal Data in Action
KDD '22: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data MiningPages 4844–4845https://doi.org/10.1145/3534678.3542626Anomaly detection is becoming important in modern society as everything goes digital. Consumers are spending a lot more time online, and various digital sensors are placed into physical/chemical equipment for health monitoring. Such monitoring data is ...
- abstractAugust 2022
Frontiers of Graph Neural Networks with DIG
KDD '22: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data MiningPages 4796–4797https://doi.org/10.1145/3534678.3542624This tutorial is proposed based upon the recently released open-source library Dive into Graphs (DIG) along with hands-on code examples. DIG is a turnkey library that considers four frontiers in graph deep learning, including self-supervised learning of ...
- abstractAugust 2022
Graph Neural Networks: Foundation, Frontiers and Applications
KDD '22: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data MiningPages 4840–4841https://doi.org/10.1145/3534678.3542609The field of graph neural networks (GNNs) has seen rapid and incredible strides over the recent years. Graph neural networks, also known as deep learning on graphs, graph representation learning, or geometric deep learning, have become one of the fastest-...
- abstractAugust 2022
Towards Adversarial Learning: From Evasion Attacks to Poisoning Attacks
KDD '22: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data MiningPages 4830–4831https://doi.org/10.1145/3534678.3542608Although deep neural networks (DNNs) have been successfully deployed in various real-world application scenarios, recent studies demonstrated that DNNs are extremely vulnerable to adversarial attacks. By introducing visually imperceptible perturbations ...
- research-articleAugust 2022
UD-GNN: Uncertainty-aware Debiased Training on Semi-Homophilous Graphs
KDD '22: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data MiningPages 1131–1140https://doi.org/10.1145/3534678.3539483Recent studies on Graph Neural Networks (GNNs) point out that most GNNs depend on the homophily assumption but fail to generalize to graphs with heterophily where dissimilar nodes connect. The concept of homophily or heterophily defined previously is a ...
- research-articleAugust 2022
In Defense of Core-set: A Density-aware Core-set Selection for Active Learning
KDD '22: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data MiningPages 804–812https://doi.org/10.1145/3534678.3539476Active learning enables the efficient construction of a labeled dataset by labeling informative samples from an unlabeled dataset. In a real-world active learning scenario, the use of diversity-based sampling is indispensable because there are many ...
- research-articleAugust 2022
Non-stationary Time-aware Kernelized Attention for Temporal Event Prediction
KDD '22: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data MiningPages 1224–1232https://doi.org/10.1145/3534678.3539470Modeling sequential data is essential to many applications such as natural language processing, recommendation systems, time series predictions, anomaly detection, etc. When processing sequential data, one of the critical issues is how to capture the ...
- research-articleAugust 2022
Beyond Point Prediction: Capturing Zero-Inflated & Heavy-Tailed Spatiotemporal Data with Deep Extreme Mixture Models
KDD '22: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data MiningPages 2020–2028https://doi.org/10.1145/3534678.3539464Zero-inflated, heavy-tailed spatiotemporal data is common across science and engineering, from climate science to meteorology and seismology. A central modeling objective in such settings is to forecast the intensity, frequency, and timing of extreme and ...
- research-articleAugust 2022
State Dependent Parallel Neural Hawkes Process for Limit Order Book Event Stream Prediction and Simulation
KDD '22: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data MiningPages 1607–1615https://doi.org/10.1145/3534678.3539462The majority of trading in financial markets is executed through a limit order book (LOB). The LOB is an event-based continuously-updating system that records contemporaneous demand (`bids' to buy) and supply (`asks' to sell) for a financial asset. ...
- research-articleAugust 2022
Learning on Graphs with Out-of-Distribution Nodes
KDD '22: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data MiningPages 1635–1645https://doi.org/10.1145/3534678.3539457Graph Neural Networks (GNNs) are state-of-the-art models for performing prediction tasks on graphs. While existing GNNs have shown great performance on various tasks related to graphs, little attention has been paid to the scenario where out-of-...
- research-articleAugust 2022
Variational Flow Graphical Model
KDD '22: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data MiningPages 1493–1503https://doi.org/10.1145/3534678.3539450This paper introduces a novel approach embedding flow-based models in hierarchical structures. The proposed model learns the representation of high-dimensional data via a message-passing scheme by integrating flow-based functions through variational ...
- research-articleAugust 2022
Feature Overcorrelation in Deep Graph Neural Networks: A New Perspective
KDD '22: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data MiningPages 709–719https://doi.org/10.1145/3534678.3539445Recent years have witnessed remarkable success achieved by graph neural networks (GNNs) in many real-world applications such as recommendation and drug discovery. Despite the success, oversmoothing has been identified as one of the key issues which limit ...
- research-articleAugust 2022
GBPNet: Universal Geometric Representation Learning on Protein Structures
KDD '22: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data MiningPages 4–14https://doi.org/10.1145/3534678.3539441Representation learning of protein 3D structures is challenging and essential for applications, e.g., computational protein design or protein engineering. Recently, geometric deep learning has achieved great success in non-Euclidean domains. Although ...
- research-articleAugust 2022
Physics-infused Machine Learning for Crowd Simulation
KDD '22: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data MiningPages 2439–2449https://doi.org/10.1145/3534678.3539440Crowd simulation acts as the basic component in traffic management, urban planning, and emergency management. Most existing approaches use physics-based models due to their robustness and strong generalizability, yet they fall short in fidelity since ...
- research-articleAugust 2022
Robust Tensor Graph Convolutional Networks via T-SVD based Graph Augmentation
KDD '22: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data MiningPages 2090–2099https://doi.org/10.1145/3534678.3539436Graph Neural Networks (GNNs) have exhibited their powerful ability of tackling nontrivial problems on graphs. However, as an extension of deep learning models to graphs, GNNs are vulnerable to noise or adversarial attacks due to the underlying ...