Robust cross-network node classification via constrained graph mutual information

Yang, Shuiqiao; Cai, Borui; Cai, Taotao; Song, Xiangyu; Jiang, Jiaojiao; Li, Bing; Li, Jianxin

doi:10.1016/j.knosys.2022.109852

Cited by 39 publications

(4 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A series of pretraining frameworks on 2D molecular graph representations have been developed so far. ,,− Recent work GEM studies large-scale pretraining for 3D geometry representations. Additionally, researchers also study to supplement 2D-graph-based pretraining with 3D conformation information. ,,, Note that apart from directly applying the pretrained model to downstream tasks, the molecular representations obtained from the pretrained model can also be combined with traditional machine learning methods. For example, blending various representations using random forest is one possible avenue …”

Section: Related Workmentioning

confidence: 99%

Molecular Contrastive Pretraining with Collaborative Featurizations

Zhu,

Chen,

et al. 2024

J. Chem. Inf. Model.

View full text Add to dashboard Cite

Molecular pretraining, which learns molecular representations over massive unlabeled data, has become a prominent paradigm to solve a variety of tasks in computational chemistry and drug discovery. Recently, prosperous progress has been made in molecular pretraining with different molecular featurizations, including 1D SMILES strings, 2D graphs, and 3D geometries. However, the role of molecular featurizations with their corresponding neural architectures in molecular pretraining remains largely unexamined. In this paper, through two case studies�chirality classification and aromatic ring counting�we first demonstrate that different featurization techniques convey chemical information differently. In light of this observation, we propose a simple and effective MOlecular pretraining framework with COllaborative featurizations (MOCO). MOCO comprehensively leverages multiple featurizations that complement each other and outperforms existing state-of-the-art models that solely rely on one or two featurizations on a wide range of molecular property prediction tasks.

show abstract

Section: Related Workmentioning

confidence: 99%

Molecular Contrastive Pretraining with Collaborative Featurizations

Zhu,

Chen,

et al. 2024

J. Chem. Inf. Model.

View full text Add to dashboard Cite

show abstract

“…Self-supervised learning [17] is an emerging paradigm in machine learning. With self-supervised learning, models make full use of relevant information to assist their main task.…”

Section: Self-supervised Learning For Recommendationmentioning

confidence: 99%

Popularity-Debiased Graph Self-Supervised for Recommendation

Li,

Hu,

Guo

et al. 2024

Electronics

View full text Add to dashboard Cite

The rise of graph neural networks has greatly contributed to the development of recommendation systems, and self-supervised learning has emerged as one of the most important approaches to address sparse interaction data. However, existing methods mostly focus on the recommendation’s accuracy while neglecting the role of recommended item diversity in enhancing user interest and merchant benefits. The reason for this phenomenon is mainly due to the bias of popular items, which makes the long-tail items (account for a large proportion) be neglected. How to mitigate the bias caused by item popularity has become one of the hot topics in current research. To address the above problems, we propose a Popularity-Debiased Graph Self-Supervised for Recommendation (PDGS). Specifically, we apply a penalty constraint on item popularity during the data enhancement process on the user–item interaction graph to eliminate the inherent popularity bias. We generate item similarity graphs with the popularity bias removed to construct a self-supervised learning task under multiple views, and we design model optimization strategies from the perspectives of popular items and long-tail items to generate recommendation lists. We conduct a large number of comparison experiments, as well as ablation experiments, on three public datasets to verify the effectiveness and the superiority of the model in balancing recommendation accuracy and diversity.

show abstract

“…Graph embedding maps graph data into low-dimensional vectors to represent the graph topology. This embedding facilitates further work, including node clustering [37], link prediction [38], node classification [39], and network visualization [40]. Classical graph embedding methods include Deepwalk [41], node-to-vector (Node2vec), and structural deep network embedding (SDNE) [42][43][44].…”

Section: Related Workmentioning

confidence: 99%

A Missing Traffic Data Imputation Method Based on a Diffusion Convolutional Neural Network–Generative Adversarial Network

Zhang,

Zhou,

Xiao

et al. 2023

Sensors

View full text Add to dashboard Cite

Traffic state data are key to the proper operation of intelligent transportation systems (ITS). However, traffic detectors often receive environmental factors that cause missing values in the collected traffic state data. Therefore, aiming at the above problem, a method for imputing missing traffic state data based on a Diffusion Convolutional Neural Network–Generative Adversarial Network (DCNN-GAN) is proposed in this paper. The proposed method uses a graph embedding algorithm to construct a road network structure based on spatial correlation instead of the original road network structure; through the use of a GAN for confrontation training, it is possible to generate missing traffic state data based on the known data of the road network. In the generator, the spatiotemporal features of the reconstructed road network are extracted by the DCNN to realize the imputation. Two real traffic datasets were used to verify the effectiveness of this method, with the results of the proposed model proving better than those of the other models used for comparison.

show abstract

Robust cross-network node classification via constrained graph mutual information

Cited by 39 publications

References 22 publications

Molecular Contrastive Pretraining with Collaborative Featurizations

Molecular Contrastive Pretraining with Collaborative Featurizations

Popularity-Debiased Graph Self-Supervised for Recommendation

A Missing Traffic Data Imputation Method Based on a Diffusion Convolutional Neural Network–Generative Adversarial Network

Contact Info

Product

Resources

About