Large language models (LLMs) have recently transformed both the academic and industrial landscapes due to their remarkable capacity to understand, analyze, and generate texts based on their vast knowledge and reasoning ability. Nevertheless, one major drawback of LLMs is their substantial computational cost for pre-training due to their unprecedented amounts of parameters. The disadvantage is exacerbated when new knowledge frequently needs to be introduced into the pre-trained model. Therefore, it is imperative to develop effective and efficient techniques to update pre-trained LLMs. Traditional methods encode new knowledge in pre-trained LLMs through direct fine-tuning. However, naively re-training LLMs can be computationally intensive and risks degenerating valuable pre-trained knowledge irrelevant to the update in the model. Recently, Knowledge-based Model Editing (KME) has attracted increasing attention, which aims to precisely modify the LLMs to incorporate specific knowledge, without negatively influencing other irrelevant knowledge. In this survey, we aim to provide a comprehensive and in-depth overview of recent advances in the field of KME. We first introduce a general formulation of KME to encompass different KME strategies. Afterward, we provide an innovative taxonomy of KME techniques based on how the new knowledge is introduced into pre-trained LLMs, and investigate existing KME strategies while analyzing key insights, advantages, and limitations of methods from each category. Moreover, representative metrics, datasets, and applications of KME are introduced accordingly. Finally, we provide an in-depth analysis regarding the practicality and remaining challenges of KME and suggest promising research directions for further advancement in this field.

Pretrained language models (PLMs) have made significant strides in various natural language processing tasks. However, the lack of interpretability due to their ``black-box'' nature poses challenges for responsible implementation. Although previous studies have attempted to improve interpretability by using, e.g., attention weights in self-attention layers, these weights often lack clarity, readability, and intuitiveness. In this research, we propose a novel approach to interpreting PLMs by employing high-level, meaningful concepts that are easily understandable for humans. For example, we learn the concept of ``Food'' and investigate how it influences the prediction of a model's sentiment towards a restaurant review. We introduce C$^3$M, which combines human-annotated and machine-generated concepts to extract hidden neurons designed to encapsulate semantically meaningful and task-specific concepts. Through empirical evaluations on real-world datasets, we manifest that our approach offers valuable insights to interpret PLM behavior, helps diagnose model failures, and enhances model robustness amidst noisy concept labels.

Graph Neural Networks (GNNs) have emerged as a prominent graph learning model in various graph-based tasks over the years. Nevertheless, due to the vulnerabilities of GNNs, it has been empirically proved that malicious attackers could easily corrupt the fairness level of their predictions by adding perturbations to the input graph data. In this paper, we take crucial steps to study a novel problem of certifiable defense on the fairness level of GNNs. Specifically, we propose a principled framework named ELEGANT and present a detailed theoretical certification analysis for the fairness of GNNs. ELEGANT takes any GNNs as its backbone, and the fairness level of such a backbone is theoretically impossible to be corrupted under certain perturbation budgets for attackers. Notably, ELEGANT does not have any assumption over the GNN structure or parameters, and does not require re-training the GNNs to realize certification. Hence it can serve as a plug-and-play framework for any optimized GNNs ready to be deployed. We verify the satisfactory effectiveness of ELEGANT in practice through extensive experiments on real-world datasets across different backbones of GNNs, where ELEGANT is also demonstrated to be beneficial for GNN debiasing. Graph Neural Networks (GNNs) have emerged to be one of the most popular models to handle learning tasks on graphs (Kipf & Welling, 2017; Veličković et al., 2018) and made remarkable achievements in various domains (Feng et al., 2022; Li et al., 2022; Jin et al., 2023). Nevertheless, as GNNs are increasingly deployed in real-world decision-making scenarios, there has been an increasing societal concern on the fairness of GNN predictions. A primary reason is that most traditional GNNs do not consider fairness, and thus could exhibit bias against certain demographic subgroups. Here the demographic subgroups are usually divided by certain sensitive attributes, such as gender and race. To prevent GNNs from exhibiting biased predictions, multiple recent studies proposed fairness-aware GNNs (Agarwal et al., 2021; Dai & Wang, 2021; Li et al., 2021; Kang et al., 2022a; Ju et al., 2023) such that potential bias could be mitigated.

Adopting a two-stage paradigm of pretraining followed by fine-tuning, Pretrained Language Models (PLMs) have achieved substantial advancements in the field of natural language processing. However, in real-world scenarios, data labels are often noisy due to the complex annotation process, making it essential to develop strategies for fine-tuning PLMs with such noisy labels. To this end, we introduce an innovative approach for fine-tuning PLMs using noisy labels, which incorporates the guidance of Large Language Models (LLMs) like ChatGPT. This guidance assists in accurately distinguishing between clean and noisy samples and provides supplementary information beyond the noisy labels, thereby boosting the learning process during fine-tuning PLMs. Extensive experiments on synthetic and real-world noisy datasets further demonstrate the superior advantages of our framework over the state-of-the-art baselines.

In social network, a person located at the periphery region (marginal node) is likely to be treated unfairly when compared with the persons at the center. While existing fairness works on graphs mainly focus on protecting sensitive attributes (e.g., age and gender), the fairness incurred by the graph structure should also be given attention. On the other hand, the information aggregation mechanism of graph neural networks amplifies such structure unfairness, as marginal nodes are often far away from other nodes. In this paper, we focus on novel fairness incurred by the graph structure on graph neural networks, named \emph{structure fairness}. Specifically, we first analyzed multiple graphs and observed that marginal nodes in graphs have a worse performance of downstream tasks than others in graph neural networks. Motivated by the observation, we propose \textbf{S}tructural \textbf{Fair} \textbf{G}raph \textbf{N}eural \textbf{N}etwork (SFairGNN), which combines neighborhood expansion based structure debiasing with hop-aware attentive information aggregation to achieve structure fairness. Our experiments show \SFairGNN can significantly improve structure fairness while maintaining overall performance in the downstream tasks.

Fairness-aware graph neural networks (GNNs) have gained a surge of attention as they can reduce the bias of predictions on any demographic group (e.g., female) in graph-based applications. Although these methods greatly improve the algorithmic fairness of GNNs, the fairness can be easily corrupted by carefully designed adversarial attacks. In this paper, we investigate the problem of adversarial attacks on fairness of GNNs and propose G-FairAttack, a general framework for attacking various types of fairness-aware GNNs in terms of fairness with an unnoticeable effect on prediction utility. In addition, we propose a fast computation technique to reduce the time complexity of G-FairAttack. The experimental study demonstrates that G-FairAttack successfully corrupts the fairness of different types of GNNs while keeping the attack unnoticeable. Our study on fairness attacks sheds light on potential vulnerabilities in fairness-aware GNNs and guides further research on the robustness of GNNs in terms of fairness. The open-source code is available at https://github.com/zhangbinchi/G-FairAttack.

Self-supervised learning with masked autoencoders has recently gained popularity for its ability to produce effective image or textual representations, which can be applied to various downstream tasks without retraining. However, we observe that the current masked autoencoder models lack good generalization ability on graph data. To tackle this issue, we propose a novel graph masked autoencoder framework called GiGaMAE. Different from existing masked autoencoders that learn node presentations by explicitly reconstructing the original graph components (e.g., features or edges), in this paper, we propose to collaboratively reconstruct informative and integrated latent embeddings. By considering embeddings encompassing graph topology and attribute information as reconstruction targets, our model could capture more generalized and comprehensive knowledge. Furthermore, we introduce a mutual information based reconstruction loss that enables the effective reconstruction of multiple targets. This learning objective allows us to differentiate between the exclusive knowledge learned from a single target and common knowledge shared by multiple targets. We evaluate our method on three downstream tasks with seven datasets as benchmarks. Extensive experiments demonstrate the superiority of GiGaMAE against state-of-the-art baselines. We hope our results will shed light on the design of foundation models on graph-structured data. Our code is available at: https://github.com/sycny/GiGaMAE.

Graph neural networks (GNNs) have shown prominent performance on attributed network embedding. However, existing efforts mainly focus on exploiting network structures, while the exploitation of node attributes is rather limited as they only serve as node features at the initial layer. This simple strategy impedes the potential of node attributes in augmenting node connections, leading to limited receptive field for inactive nodes with few or even no neighbors. Furthermore, the training objectives (i.e., reconstructing network structures) of most GNNs also do not include node attributes, although studies have shown that reconstructing node attributes is beneficial. Thus, it is encouraging to deeply involve node attributes in the key components of GNNs, including graph convolution operations and training objectives. However, this is a nontrivial task since an appropriate way of integration is required to maintain the merits of GNNs. To bridge the gap, in this paper, we propose COllaborative graph Neural Networks--CONN, a tailored GNN architecture for attribute network embedding. It improves model capacity by 1) selectively diffusing messages from neighboring nodes and involved attribute categories, and 2) jointly reconstructing node-to-node and node-to-attribute-category interactions via cross-correlation. Experiments on real-world networks demonstrate that CONN excels state-of-the-art embedding algorithms with a great margin.

Fairness-aware machine learning has attracted a surge of attention in many domains, such as online advertising, personalized recommendation, and social media analysis in web applications. Fairness-aware machine learning aims to eliminate biases of learning models against certain subgroups described by certain protected (sensitive) attributes such as race, gender, and age. Among many existing fairness notions, counterfactual fairness is a popular notion defined from a causal perspective. It measures the fairness of a predictor by comparing the prediction of each individual in the original world and that in the counterfactual worlds in which the value of the sensitive attribute is modified. A prerequisite for existing methods to achieve counterfactual fairness is the prior human knowledge of the causal model for the data. However, in real-world scenarios, the underlying causal model is often unknown, and acquiring such human knowledge could be very difficult. In these scenarios, it is risky to directly trust the causal models obtained from information sources with unknown reliability and even causal discovery methods, as incorrect causal models can consequently bring biases to the predictor and lead to unfair predictions. In this work, we address the problem of counterfactually fair prediction from observational data without given causal models by proposing a novel framework CLAIRE. Specifically, under certain general assumptions, CLAIRE effectively mitigates the biases from the sensitive attribute with a representation learning framework based on counterfactual data augmentation and an invariant penalty. Experiments conducted on both synthetic and real-world datasets validate the superiority of CLAIRE in both counterfactual fairness and prediction performance.

Methicillin-resistant Staphylococcus aureus (MRSA) is a type of bacteria resistant to certain antibiotics, making it difficult to prevent MRSA infections. Among decades of efforts to conquer infectious diseases caused by MRSA, many studies have been proposed to estimate the causal effects of close contact (treatment) on MRSA infection (outcome) from observational data. In this problem, the treatment assignment mechanism plays a key role as it determines the patterns of missing counterfactuals -- the fundamental challenge of causal effect estimation. Most existing observational studies for causal effect learning assume that the treatment is assigned individually for each unit. However, on many occasions, the treatments are pairwisely assigned for units that are connected in graphs, i.e., the treatments of different units are entangled. Neglecting the entangled treatments can impede the causal effect estimation. In this paper, we study the problem of causal effect estimation with treatment entangled in a graph. Despite a few explorations for entangled treatments, this problem still remains challenging due to the following challenges: (1) the entanglement brings difficulties in modeling and leveraging the unknown treatment assignment mechanism; (2) there may exist hidden confounders which lead to confounding biases in causal effect estimation; (3) the observational data is often time-varying. To tackle these challenges, we propose a novel method NEAT, which explicitly leverages the graph structure to model the treatment assignment mechanism, and mitigates confounding biases based on the treatment assignment modeling. We also extend our method into a dynamic setting to handle time-varying observational data. Experiments on both synthetic datasets and a real-world MRSA dataset validate the effectiveness of the proposed method, and provide insights for future applications.