Graph Lifelong Learning: A Survey

Febrinanto, Falih Gozi; Xia, Feng; Moore, Kristen; Thapa, Chandra; Aggarwal, Charu C.

doi:10.1109/mci.2022.3222049

Cited by 21 publications

(15 citation statements)

References 83 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Xu et al developed a simple and powerful graph learning method, the graph isomorphism network (GIN), and theoretically proved that the model has the maximum discriminant ability in GNNs . We utilize a GIN-based module to learn the node representations of the protein–ligand complex. ,− Given the adjacency matrix A of graph and the initial feature vectors x of all nodes in . First, the adjacency matrix A and the initial features x are fed into the GIN module; then, the representation vector for each node is updated by aggregating information from its neighboring nodes based on adjacency matrix A ; and finally, iterative message passing is employed to extract the latent representations of all nodes.…”

Section: Ss-gnnmentioning

confidence: 99%

SS-GNN: A Simple-Structured Graph Neural Network for Affinity Prediction

et al. 2023

View full text Add to dashboard Cite

Efficient and effective drug-target binding affinity (DTBA) prediction is a challenging task due to the limited computational resources in practical applications and is a crucial basis for drug screening. Inspired by the good representation ability of graph neural networks (GNNs), we propose a simple-structured GNN model named SS-GNN to accurately predict DTBA. By constructing a single undirected graph based on a distance threshold to represent protein–ligand interactions, the scale of the graph data is greatly reduced. Moreover, ignoring covalent bonds in the protein further reduces the computational cost of the model. The graph neural network-multilayer perceptron (GNN-MLP) module takes the latent feature extraction of atoms and edges in the graph as two mutually independent processes. We also develop an edge-based atom-pair feature aggregation method to represent complex interactions and a graph pooling-based method to predict the binding affinity of the complex. We achieve state-of-the-art prediction performance using a simple model (with only 0.6 M parameters) without introducing complicated geometric feature descriptions. SS-GNN achieves Pearson’s R p = 0.853 on the PDBbind v2016 core set, outperforming state-of-the-art GNN-based methods by 5.2%. Moreover, the simplified model structure and concise data processing procedure improve the prediction efficiency of the model. For a typical protein–ligand complex, affinity prediction takes only 0.2 ms. All codes are freely accessible at .

show abstract

Section: Ss-gnnmentioning

confidence: 99%

SS-GNN: A Simple-Structured Graph Neural Network for Affinity Prediction

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Lifelong machine learning [1], [2] is a growing research field [3]- [5], where the goal is to update a model to accommodate new data and tasks. Most of the research is done on image data [3], while some work has also been done in the graph domain [5].…”

Section: Introductionmentioning

confidence: 99%

Open-World Lifelong Graph Learning

Hoffmann

Galke

Scherp

2023

2023 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

We study the problem of lifelong graph learning in an open-world scenario, where a model needs to deal with new tasks and potentially unknown classes. We utilize Out-of-Distribution (OOD) detection methods to recognize new classes and adapt existing non-graph OOD detection methods to graph data. Crucially, we suggest performing new class detection by combining OOD detection methods with information aggregated from the graph neighborhood. Most OOD detection methods avoid determining a crisp threshold for deciding whether a vertex is OOD. To tackle this problem, we propose a Weaklysupervised Relevance Feedback (Open-WRF) method, which decreases the sensitivity to thresholds in OOD detection. We evaluate our approach on six benchmark datasets. Our results show that the proposed neighborhood aggregation method for OOD scores outperforms existing methods independent of the underlying graph neural network. Furthermore, we demonstrate that our Open-WRF method is more robust to threshold selection and analyze the influence of graph neighborhood on OOD detection. The aggregation and threshold methods are compatible with arbitrary graph neural networks and OOD detection methods, making our approach versatile and applicable to many real-world applications. The source code is available at https://github.com/Bobowner/Open-World-LGL.

show abstract

“…Moreover, this is one of the first works (along with a few others [FXM+22]) that studies lifelong learning on graph data. We designed an experimental framework and introduced three graph datasets to investigate the maintenance of a single model throughout the evolution of the graph.…”

Section: Future Workmentioning

confidence: 93%

“…The model can make use of implicit or explicit knowledge from previous tasks. Lifelong learning on graphs is a relatively new topic, investigated by a few other works [FXM+22].…”

Section: Advances and Challenges In Text And Graph Representation Lea...mentioning

confidence: 99%

See 1 more Smart Citation

Representation Learning for Texts and Graphs

Galke

View full text Add to dashboard Cite

[...] This thesis is situated between natural language processing and graph representation learning and investigates selected connections. First, we introduce matrix embeddings as an efficient text representation sensitive to word order. [...] Experiments with ten linguistic probing tasks, 11 supervised, and five unsupervised downstream tasks reveal that vector and matrix embeddings have complementary strengths and that a jointly trained hybrid model outperforms both. Second, a popular pretrained language model, BERT, is distilled into matrix embeddings. [...] The results on the GLUE benchmark show that these models are competitive with other recent contextualized language models while being more efficient in time and space. Third, we compare three model types for text classification: bag-of-words, sequence-, and graph-based models. Experiments on five datasets show that, surprisingly, a wide multilayer perceptron on top of a bag-of-words representation is competitive with recent graph-based approaches, questioning the necessity of graphs synthesized from the text. [...] Fourth, we investigate the connection between text and graph data in document-based recommender systems for citations and subject labels. Experiments on six datasets show that the title as side information improves the performance of autoencoder models. [...] We find that the meaning of item co-occurrence is crucial for the choice of input modalities and an appropriate model. Fifth, we introduce a generic framework for lifelong learning on evolving graphs in which new nodes, edges, and classes appear over time. [...] The results show that by reusing previous parameters in incremental training, it is possible to employ smaller history sizes with only a slight decrease in accuracy compared to training with complete history. Moreover, weighting the binary cross-entropy loss function is crucial to mitigate the problem of class imbalance when detecting newly emerging classes. [...]

show abstract

Graph Lifelong Learning: A Survey

Cited by 21 publications

References 83 publications

SS-GNN: A Simple-Structured Graph Neural Network for Affinity Prediction

SS-GNN: A Simple-Structured Graph Neural Network for Affinity Prediction

Open-World Lifelong Graph Learning

Representation Learning for Texts and Graphs

Contact Info

Product

Resources

About