Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- keynoteAugust 2024
AI for Nature: From Science to Impact
KDD '24: Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data MiningPage 2https://doi.org/10.1145/3637528.3672192Computation has fundamentally changed the way we study nature. New data collection technologies, such as GPS, high-definition cameras, autonomous vehicles under water, on the ground, and in the air, genotyping, acoustic sensors, and crowdsourcing, are ...
- research-articleAugust 2024
Masked LoGoNet: Fast and Accurate 3D Image Analysis for Medical Domain
- Amin Karimi Monsefi,
- Payam Karisani,
- Mengxi Zhou,
- Stacey Choi,
- Nathan Doble,
- Heng Ji,
- Srinivasan Parthasarathy,
- Rajiv Ramnath
KDD '24: Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data MiningPages 1348–1359https://doi.org/10.1145/3637528.3672069Standard modern machine-learning-based imaging methods have faced challenges in medical applications due to the high cost of dataset construction and, thereby, the limited labeled training data available. Additionally, upon deployment, these methods are ...
- research-articleAugust 2024
MacroHFT: Memory Augmented Context-aware Reinforcement Learning On High Frequency Trading
KDD '24: Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data MiningPages 4712–4721https://doi.org/10.1145/3637528.3672064High-frequency trading (HFT) that executes algorithmic trading in short time scales, has recently occupied the majority of cryptocurrency market. Besides traditional quantitative trading methods, reinforcement learning (RL) has become another appealing ...
- research-articleAugust 2024
Conformalized Link Prediction on Graph Neural Networks
KDD '24: Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data MiningPages 4490–4499https://doi.org/10.1145/3637528.3672061Graph Neural Networks (GNNs) excel in diverse tasks, yet their applications in high-stakes domains are often hampered by unreliable predictions. Although numerous uncertainty quantification methods have been proposed to address this limitation, they ...
- research-articleAugust 2024
MemMap: An Adaptive and Latent Memory Structure for Dynamic Graph Learning
KDD '24: Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data MiningPages 1257–1268https://doi.org/10.1145/3637528.3672060Dynamic graph learning has attracted much attention in recent years due to the fact that most of the real-world graphs are dynamic and evolutionary. As a result, many dynamic learning methods have been proposed to cope with the changes of node states ...
-
- research-articleAugust 2024
AutoXPCR: Automated Multi-Objective Model Selection for Time Series Forecasting
KDD '24: Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data MiningPages 806–815https://doi.org/10.1145/3637528.3672057Automated machine learning (AutoML) streamlines the creation of ML models, but few specialized methods have approached the challenging domain of time series forecasting. Deep neural networks (DNNs) often deliver state-of-the-art predictive performance ...
- research-articleAugust 2024
Hierarchical Neural Constructive Solver for Real-world TSP Scenarios
KDD '24: Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data MiningPages 884–895https://doi.org/10.1145/3637528.3672053Existing neural constructive solvers for routing problems have predominantly employed transformer architectures, conceptualizing the route construction as a set-to-sequence learning task. However, their efficacy has primarily been demonstrated on ...
- research-articleAugust 2024
DPHGNN: A Dual Perspective Hypergraph Neural Networks
KDD '24: Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data MiningPages 2548–2559https://doi.org/10.1145/3637528.3672047Message passing on hypergraphs has been a standard framework for learning higher-order correlations between hypernodes. Recently-proposed hypergraph neural networks (HGNNs) can be categorized into spatial and spectral methods based on their design ...
- research-articleAugust 2024
Global Human-guided Counterfactual Explanations for Molecular Properties via Reinforcement Learning
- Danqing Wang,
- Antonis Antoniades,
- Kha-Dinh Luong,
- Edwin Zhang,
- Mert Kosan,
- Jiachen Li,
- Ambuj Singh,
- William Yang Wang,
- Lei Li
KDD '24: Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data MiningPages 2991–3000https://doi.org/10.1145/3637528.3672045Counterfactual explanations of Graph Neural Networks (GNNs) offer a powerful way to understand data that can naturally be represented by a graph structure. Furthermore, in many domains, it is highly desirable to derive data-driven global explanations or ...
- research-articleAugust 2024
Graph Mamba: Towards Learning on Graphs with State Space Models
KDD '24: Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data MiningPages 119–130https://doi.org/10.1145/3637528.3672044Graph Neural Networks (GNNs) have shown promising potential in graph representation learning. The majority of GNNs define a local message-passing mechanism, propagating information over the graph by stacking multiple layers. These methods, however, are ...
- research-articleAugust 2024
FedNLR: Federated Learning with Neuron-wise Learning Rates
KDD '24: Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data MiningPages 3069–3080https://doi.org/10.1145/3637528.3672042Federated Learning (FL) suffers from severe performance degradation due to the data heterogeneity among clients. Some existing work suggests that the fundamental reason is that data heterogeneity can cause local model drift, and therefore proposes to ...
- research-articleAugust 2024
Multi-Task Learning for Routing Problem with Cross-Problem Zero-Shot Generalization
KDD '24: Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data MiningPages 1898–1908https://doi.org/10.1145/3637528.3672040Vehicle routing problems (VRP) are very important in many real-world applications and has been studied for several decades. Recently, neural combinatorial optimization (NCO) has attracted growing research effort. NCO is to train a neural network model to ...
- research-articleAugust 2024
BitLINK: Temporal Linkage of Address Clusters in Bitcoin Blockchain
KDD '24: Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data MiningPages 4583–4594https://doi.org/10.1145/3637528.3672037In the Bitcoin blockchain, an entity (e.g., a gambling service) may control multiple distinct address clusters. Links (i.e., trust relationships) between these disjoint address clusters can be established when one cluster is abandoned, and a new one is ...
- research-articleAugust 2024
DipDNN: Preserving Inverse Consistency and Approximation Efficiency for Invertible Learning
KDD '24: Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data MiningPages 4071–4082https://doi.org/10.1145/3637528.3672036Consistent bi-directional inferences are the key for many machine learning applications. Without consistency, inverse learning-based inferences can cause fuzzy images, erroneous control signals, and cascading failure in SCADA systems. Since standard deep ...
- research-articleAugust 2024
GAugLLM: Improving Graph Contrastive Learning for Text-Attributed Graphs with Large Language Models
KDD '24: Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data MiningPages 747–758https://doi.org/10.1145/3637528.3672035This work studies self-supervised graph learning for text-attributed graphs (TAGs) where nodes are represented by textual attributes. Unlike traditional graph contrastive methods that perturb the numerical feature space and alter the graph's topological ...
- research-articleAugust 2024
One Fits All: Learning Fair Graph Neural Networks for Various Sensitive Attributes
KDD '24: Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data MiningPages 4688–4699https://doi.org/10.1145/3637528.3672029Recent studies have highlighted fairness issues in Graph Neural Networks (GNNs), where they produce discriminatory predictions against specific protected groups categorized by sensitive attributes such as race and age. While various efforts to enhance ...
- research-articleAugust 2024
Efficient and Effective Implicit Dynamic Graph Neural Network
KDD '24: Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data MiningPages 4595–4606https://doi.org/10.1145/3637528.3672026Implicit graph neural networks have gained popularity in recent years as they capture long-range dependencies while improving predictive performance in static graphs. Despite the tussle between performance degradation due to the oversmoothing of learned ...
- research-articleAugust 2024
LPFormer: An Adaptive Graph Transformer for Link Prediction
KDD '24: Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data MiningPages 2686–2698https://doi.org/10.1145/3637528.3672025Link prediction is a common task on graph-structured data that has seen applications in a variety of domains. Classically, hand-crafted heuristics were used for this task. Heuristic measures are chosen such that they correlate well with the underlying ...
- research-articleAugust 2024
CAT: Interpretable Concept-based Taylor Additive Models
KDD '24: Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data MiningPages 723–734https://doi.org/10.1145/3637528.3672020As an emerging interpretable technique, Generalized Additive Models (GAMs) adopt neural networks to individually learn non-linear functions for each feature, which are then combined through a linear model for final predictions. Although GAMs can explain ...
- research-articleAugust 2024
Uplift Modelling via Gradient Boosting
KDD '24: Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data MiningPages 1177–1187https://doi.org/10.1145/3637528.3672019The Gradient Boosting machine learning ensemble algorithm, well-known for its proficiency and superior performance in intricate machine learning tasks, has encountered limited success in the realm of uplift modeling. Uplift modeling is a challenging task ...