Time series anomaly detection is a technology that finds outliers in observed data over time, and is a significant research field associated with many applications or platforms. In this paper, we propose a method call...
详细信息
The paper proposed a secured and efficient data aggregation mechanism leveraging the edge computing paradigm and homomorphic data encryption technique. The paper used a unique combination of Paillier cryptosystem and ...
详细信息
Plant disease causes a highly significant impact on production due to its destructive characteristics. A variety of chemical techniques should be applied to agriculture at different stages of disease infestation to en...
详细信息
Off-axis digital holography plays a crucial role in high-precision three-dimensional imaging. However, high-resolution phase images are often affected by the limited pixel size of the sensor. To address this issue, th...
详细信息
作者：
Shim, HyungboASRI
Electrical and Computer Engineering Department Seoul National University Korea Republic of
A swarm of individuals often exhibits behaviors that are not possible for each individual. This phenomenon is called emergence, and this paper mathematically demonstrates that new dynamics can arise in swarm behavior ...
详细信息
In this paper we consider the motion planning problem in an n-dimensional Euclidean space, n ≥q 2, containing finitely many obstacles with boundaries possessing a smooth structure. Obstacle boundaries are assumed to ...
详细信息
Extracting text from an image using a Visual Question Answering (VQA) system is an application at the intersection of computer vision and Natural Language Processing (NLP) to help blind people better view and comprehe...
详细信息
Distance and size estimation of objects of interests is an inevitable task for many navigation and obstacle avoidance algorithms mainly used in autonomus and robotic systems. Stereo vision systems, inspired by human v...
详细信息
Machine learning algorithms can be used to detect Alzheimer disease with RMI-images. One of the challenges of these algorithms is to clearly extract image features that show small variants of brain cells changes, whic...
详细信息
Graph neural networks (GNNs) have gained increasing popularity, while usually suffering from unaffordable computations for real-world large-scale applications. Hence, pruning GNNs is of great need but largely unexplor...
详细信息
Graph neural networks (GNNs) have gained increasing popularity, while usually suffering from unaffordable computations for real-world large-scale applications. Hence, pruning GNNs is of great need but largely unexplored. The recent work Unified GNN Sparsification (UGS) studies lottery ticket learning for GNNs, aiming to find a subset of model parameters and graph structures that can best maintain the GNN performance. However, it is tailed for the transductive setting, failing to generalize to unseen graphs, which are common in inductive tasks like graph classification. In this work, we propose a simple and effective learning paradigm, Inductive Co-Pruning of GNNs (ICPG), to endow graph lottery tickets with inductive pruning capacity. To prune the input graphs, we design a predictive model to generate importance scores for each edge based on the input. To prune the model parameters, it views the weight’s magnitude as their importance scores. Then we design an iterative co-pruning strategy to trim the graph edges and GNN weights based on their importance scores. Although it might be strikingly simple, ICPG surpasses the existing pruning method and can be universally applicable in both inductive and transductive learning settings. On 10 graph-classification and two node-classification benchmarks, ICPG achieves the same performance level with 14.26%–43.12% sparsity for graphs and 48.80%–91.41% sparsity for the GNN model.
暂无评论