Lifelong graph learning deals with the problem of continually adapting graph neural network (GNN) models to changes in evolving graphs. We address two critical challenges of lifelong graph learning in this work: dealing with new classes and tackling imbalanced class distributions. The combination of these two challenges is particularly relevant since newly emerging classes typically resemble only a tiny fraction of the data, adding to the already skewed class distribution. We make several contributions: First, we show that the amount of unlabeled data does not influence the results, which is an essential prerequisite for lifelong learning on a sequence of tasks. Second, we experiment with different label rates and show that our methods can perform well with only a tiny fraction of annotated nodes. Third, we propose the gDOC method to detect new classes under the constraint of having an imbalanced class distribution. The critical ingredient is a weighted binary cross-entropy loss function to account for the class imbalance. Moreover, we demonstrate combinations of gDOC with various base GNN models such as GraphSAGE, Simplified Graph Convolution, and Graph Attention Networks. Lastly, our k-neighborhood time difference measure provably normalizes the temporal changes across different graph datasets. With extensive experimentation, we find that the proposed gDOC method is consistently better than a naive adaption of DOC to graphs. Specifically, in experiments using the smallest history size, the out-of-distribution detection score of gDOC is 0.09 compared to 0.01 for DOC. Furthermore, gDOC achieves an Open-F1 score, a combined measure of in-distribution classification and out-of-distribution detection, of 0.33 compared to 0.25 of DOC (32% increase).

Availability of diagnostic codes in Electronic Health Records (EHRs) is crucial for patient care as well as reimbursement purposes. However, entering them in the EHR is tedious, and some clinical codes may be overlooked. Given an in-complete list of clinical codes, we investigate the performance of ML methods on predicting the complete ones, and assess the added predictive value of including other clinical patient data in this task. We used the MIMIC-III dataset and frame the task of completing the clinical codes as a recommendation problem. We con-sider various autoencoder approaches plus two strong baselines; item co-occurrence and Singular Value Decomposition (SVD). Inputs are 1) a record's known clinical codes, 2) the codes plus variables. The co-occurrence-based ap-proach performed slightly better (F1 score=0.26, Mean Average Precision [MAP]=0.19) than the SVD (F1=0.24, MAP=0.18). However, the adversarial autoencoder achieved the best performance when using the codes plus variables (F1=0.32, MAP=0.25). Adversarial autoencoders performed best in terms of F1 and were equal to vanilla and denoising autoencoders in term of MAP. Using clinical variables in addition to the incomplete codes list, improves the predictive performance of the models.

We investigate different natural language processing (NLP) approaches based on contextualised word representations for the problem of early prediction of lung cancer using free-text patient medical notes of Dutch primary care physicians. Because lung cancer has a low prevalence in primary care, we also address the problem of classification under highly imbalanced classes. Specifically, we use large Transformer-based pretrained language models (PLMs) and investigate: 1) how soft prompttuning--an NLP technique used to adapt PLMs using small amounts of training data--compares to standard model fine-tuning; 2) whether simpler static word embedding models (WEMs) can be more robust compared to PLMs in highly imbalanced settings; and 3) how models fare when trained on notes from a small number of patients. We find that 1) soft-prompt tuning is an efficient alternative to standard model fine-tuning; 2) PLMs show better discrimination but worse calibration compared to simpler static word embedding models as the classification problem becomes more imbalanced; and 3) results when training models on small number of patients are mixed and show no clear differences between PLMs and WEMs. All our code is available open source in https://bitbucket.org/aumc-kik/prompt

Current graph neural networks (GNNs) are promising, especially when the entire graph is known for training. However, it is not yet clear how to efficiently train GNNs on temporal graphs, where new vertices, edges, and even classes appear over time. We face two challenges: First, shifts in the label distribution (including the appearance of new labels), which require adapting the model. Second, the growth of the graph, which makes it, at some point, infeasible to train over all vertices and edges. We address these issues by applying a sliding window technique, i.e., we incrementally train GNNs on limited window sizes and analyze their performance. For our experiments, we have compiled three new temporal graph datasets based on scientific publications and evaluate isotropic and anisotropic GNN architectures. Our results show that both GNN types provide good results even for a window size of just 1 time step. With window sizes of 3 to 4 time steps, GNNs achieve at least 95% accuracy compared to using the entire timeline of the graph. With window sizes of 6 or 8, at least 99% accuracy could be retained. These discoveries have direct consequences for training GNNs over temporal graphs. We provide the code (https://github.com/Incremental-GNNs) and the newly compiled datasets (https://zenodo.org/record/3764770) for reproducibility and reuse.

We present multi-modal adversarial autoencoders for recommendation and evaluate them on two different tasks: citation recommendation and subject label recommendation. We analyze the effects of adversarial regularization, sparsity, and different input modalities. By conducting 408 experiments, we show that adversarial regularization consistently improves the performance of autoencoders for recommendation. We demonstrate, however, that the two tasks differ in the semantics of item co-occurrence in the sense that item co-occurrence resembles relatedness in case of citations, yet implies diversity in case of subject labels. Our results reveal that supplying the partial item set as input is only helpful, when item co-occurrence resembles relatedness. When facing a new recommendation task it is therefore crucial to consider the semantics of item co-occurrence for the choice of an appropriate model.

Large-scale graph data in real-world applications is often not static but dynamic, i. e., new nodes and edges appear over time. Current graph convolution approaches are promising, especially, when all the graph's nodes and edges are available during training. When unseen nodes and edges are inserted after training, it is not yet evaluated whether up-training or re-training from scratch is preferable. We construct an experimental setup, in which we insert previously unseen nodes and edges after training and conduct a limited amount of inference epochs. In this setup, we compare adapting pretrained graph neural networks against retraining from scratch. Our results show that pretrained models yield high accuracy scores on the unseen nodes and that pretraining is preferable over retraining from scratch. Our experiments represent a first step to evaluate and develop truly online variants of graph neural networks.