Graph neural networks (GNNs) have shown strong performance in graph fairness learning, which aims to ensure that predictions are unbiased with respect to sensitive attributes. However, existing approaches usually assume that training and test data share the same distribution, which rarely holds in the real world. To tackle this challenge, we propose a novel approach named Dual Unbiased Expansion with Group-acquired Alignment (DANCE) for graph fairness learning under distribution shifts. The core idea of our DANCE is to synthesize challenging yet unbiased virtual graph data in both graph and hidden spaces, simulating distribution shifts from a data-centric view. Specifically, we introduce the unbiased Mixup in the hidden space, prioritizing minor groups to address the potential imbalance of sensitive attributes. Simultaneously, we conduct fairness-aware adversarial learning in the graph space to focus on challenging samples and improve model robustness. To further bridge the domain gap, we propose a group-acquired alignment objective that prioritizes negative pair groups with identical sensitive labels. Additionally, a representation disentanglement objective is adopted to decorrelate sensitive attributes and target representations for enhanced fairness. Extensive experiments demonstrate the superior effectiveness of the proposed DANCE.

Most existing Few-Shot Learning (FSL) works are based on the meta-learning framework, which uses tasks training models to obtain “meta-knowledge” and can quickly adapt to new tasks with limited data. The good performance of such works rely on a strict assumption that the training and testing tasks come from the same domain. However, domain shift is more common in practice. Therefore, Cross-Domain FewShot Learning (CD-FSL) has gradually become a research hotspot. To overcome the challenge of domain discrepancy, we propose a Diversified Task Augmentation with Redundancy Reduction (DTA-RR) approach. The DTA module is developed to expand the distribution of source domain tasks, which can bridge the domain gap by adapting biases from multiple enhanced versions of the same task and then extract domain-invariant information. In addition, we propose the RR module that can reduce redundant knowledge and make the obtained domain-invariant information more effective. We conduct extensive experiments on the BSCD-FSL benchmark. The results demonstrate the effectiveness of our model and outperform existing methods.

Few-shot knowledge graph completion (FKGC) aims to use a few-shot reference entity pairs to infer unknown facts and complete triple information. Typically, existing methods solely learn entity embeddings from their respective neighborhoods, resulting in inadequately differentiated entity pair representations. And they only use the updated entities to represent the relations, which leads to relation overfitting. To address the issues, we propose a FKGC model based on hierarchical neighborhood information interaction (HNII). Specifically, the model first considers the interaction between head and tail entities. It obtains enhanced entity embedding representations from the task-relation-level and entity-pair-level by using a hierarchical neighborhood entity encoder. Then, a bi-directional LSTM relation encoder is introduced to output the relation embedding representations. Finally, an attention mixed matching processor is used to compute the semantic similarity. This is conducive to fully exploring the deep semantic information of entities and relations. Extensive related experiments on two public datasets show that HNII performs excellent in the task of FKGC.

Recently, there has been increasing interest in Cross-Domain Few-Shot Learning (CD-FSL), which aims to solve the traditional Few-Shot Learning (FSL) problem across different domains. The core challenge of the CD-FSL is that the huge domain gap between the source and target domains often leads to poor generalization to the target new tasks. Although many existing methods have achieved certain accomplishments, none of them take into account the negative effects of redundant information during training. To overcome this problem, we propose a de-redundancy distillation (DRD) method that introduces a small amount of unlabeled target data to reduce domain differences. DRD utilizes a de-redundancy based self-supervised learning method to encourage the model to learn more concise and clear target-relevant features. And using a curriculum learning strategy to balance the learning of both source and target information. Moreover, it is common for models to excessively focus on some irrelevant information when generalizing. We propose a simple feature shift correction module (FSC) to allow it to focus on more useful generic target information, which further improves the quality of features. We conduct extensive experiments on the BSCD-FSL benchmark that includes four different target datasets. The experimental results demonstrate the effectiveness of our method.

Knowledge graph (KG) embedding is a fundamental task in natural language processing, and various methods have been proposed to explore semantic patterns in distinctive ways.In this paper, we propose to learn an ensemble by leveraging existing methods in a relation-aware manner.However, exploring these semantics using relation-aware ensemble leads to a much larger search space than general ensemble methods.To address this issue, we propose a dividesearch-combine algorithm RelEns-DSC that searches the relation-wise ensemble weights independently.This algorithm has the same computation cost as general ensemble methods but with much better performance.Experimental results on benchmark datasets demonstrate the effectiveness of the proposed method in efficiently searching relation-aware ensemble weights and achieving state-of-the-art embedding performance.The code is public at https: //github.com/LARS-research/RelEns. 1

Subjective cognitive decline (SCD) is the preclinical stage of Alzheimer's disease (AD) which happens even earlier than mild cognitive impairment (MCI). Progressive SCD will convert to MCI with the potential of further evolving to AD. Therefore, early identification of progressive SCD with neuroimaging techniques (e.g., structural MRI) is of great clinical value for early intervention of AD. However, existing MRI-based machine/deep learning methods usually suffer the small-sample-size problem and lack interpretability. To this end, we propose an interpretable autoencoder model with domain transfer learning (IADT) for progression prediction of SCD. Firstly, the proposed model can leverage MRIs from both the target domain (i.e., SCD) and auxiliary domains (e.g., AD and NC) for progressive SCD identification. Besides, it can automatically locate the disease-related brain regions of interest (defined in brain atlases) through an attention mechanism, which shows good interpretability. In addition, the IADT model is straightforward to train and test with only 5 ∼ 10 seconds on CPUs and is suitable for medical tasks with small datasets. Extensive experiments on the publicly available ADNI dataset and a private CLAS dataset have demonstrated the effectiveness of the proposed method.

A critical issue of drug risk-benefit evaluation is to determine the frequencies of drug side effects. Randomized controlled trail is the conventional method for obtaining the frequencies of side effects, while it is laborious and slow. Therefore, it is necessary to guide the trail by computational methods. Existing methods for predicting the frequencies of drug side effects focus on modeling drug-side effect interaction graph. The inherent disadvantage of these approaches is that their performance is closely linked to the density of interactions but which is highly sparse. More importantly, for a cold start drug that does not appear in the training data, such methods cannot learn the preference embedding of the drug because there is no link to the drug in the interaction graph. In this work, we propose a new method for predicting the frequencies of drug side effects, DSGAT, by using the drug molecular graph instead of the commonly used interaction graph. This leads to the ability to learn embeddings for cold start drugs with graph attention networks. The proposed novel loss function, i.e. weighted $\varepsilon$-insensitive loss function, could alleviate the sparsity problem. Experimental results on one benchmark dataset demonstrate that DSGAT yields significant improvement for cold start drugs and outperforms the state-of-the-art performance in the warm start scenario. Source code and datasets are available at https://github.com/xxy45/DSGAT.