The rapid evolution of large language models (LLMs) has fuelled enthusiasm about their role in advancing scientific discovery, with studies exploring LLMs that autonomously generate and evaluate novel research ideas. However, little attention has been given to the possibility that such models could be exploited to produce harmful research by repurposing open science artefacts for malicious ends. We fill the gap by introducing an end-to-end pipeline that first bypasses LLM safeguards through persuasion-based jailbreaking, then reinterprets NLP papers to identify and repurpose their artefacts (datasets, methods, and tools) by exploiting their vulnerabilities, and finally assesses the safety of these proposals using our evaluation framework across three dimensions: harmfulness, feasibility of misuse, and soundness of technicality. Overall, our findings demonstrate that LLMs can generate harmful proposals by repurposing ethically designed open artefacts; however, we find that LLMs acting as evaluators strongly disagree with one another on evaluation outcomes: GPT-4.1 assigns higher scores (indicating greater potential harms, higher soundness and feasibility of misuse), Gemini-2.5-pro is markedly stricter, and Grok-3 falls between these extremes. This indicates that LLMs cannot yet serve as reliable judges in a malicious evaluation setup, making human evaluation essential for credible dual-use risk assessment.

Artificial Intelligence has become integral to intelligent drug discovery, with Graph Machine Learning (GML) emerging as a powerful structure-based method for modelling graph-structured biomedical data and investigating their properties. However, GML faces challenges such as limited interpretability and heavy dependency on abundant high-quality training data. On the other hand, knowledge-based methods leverage biomedical knowledge databases, e.g., Knowledge Graphs (KGs), to explore unknown knowledge. Nevertheless, KG construction is resource-intensive and often neglects crucial structural information in biomedical data. In response, recent studies have proposed integrating external biomedical knowledge into the GML pipeline to realise more precise and interpretable drug discovery with scarce training data. Nevertheless, a systematic definition for this burgeoning research direction is yet to be established. This survey formally summarises Knowledge-augmented Graph Machine Learning (KaGML) for drug discovery and organises collected KaGML works into four categories following a novel-defined taxonomy. We also present a comprehensive overview of long-standing drug discovery principles and provide the foundational concepts and cutting-edge techniques for graph-structured data and knowledge databases. To facilitate research in this promptly emerging field, we share collected practical resources that are valuable for intelligent drug discovery and provide an in-depth discussion of the potential avenues for future advancements.

Recent advancements in AI for biological research focus on integrating molecular data with natural language to accelerate drug discovery. However, the scarcity of high-quality annotations limits progress in this area. This paper introduces LA^3, a Language-based Automatic Annotation Augmentation framework that leverages large language models to augment existing datasets, thereby improving AI training. We demonstrate the effectiveness of LA^3 by creating an enhanced dataset, LaChEBI-20, where we systematically rewrite the annotations of molecules from an established dataset. These rewritten annotations preserve essential molecular information while providing more varied sentence structures and vocabulary. Using LaChEBI-20, we train LaMolT5 based on a benchmark architecture to learn the mapping between molecular representations and augmented annotations. Experimental results on text-based *de novo* molecule generation and molecule captioning demonstrate that LaMolT5 outperforms state-of-the-art models. Notably, incorporating LA^3 leads to improvements of up to 301 benchmark architecture. Furthermore, we validate the effectiveness of LA^3 notable applications in *image*, *text* and *graph* tasks, affirming its versatility and utility.

Network embedding (NE) approaches have emerged as a predominant technique to represent complex networks and have benefited numerous tasks. However, most NE approaches rely on a homophily assumption to learn embeddings with the guidance of supervisory signals, leaving the unsupervised heterophilous scenario relatively unexplored. This problem becomes especially relevant in fields where a scarcity of labels exists. Here, we formulate the unsupervised NE task as an r-ego network discrimination problem and develop the SELENE framework for learning on networks with homophily and heterophily. Specifically, we design a dual-channel feature embedding pipeline to discriminate r-ego networks using node attributes and structural information separately. We employ heterophily adapted self-supervised learning objective functions to optimise the framework to learn intrinsic node embeddings. We show that SELENE's components improve the quality of node embeddings, facilitating the discrimination of connected heterophilous nodes. Comprehensive empirical evaluations on both synthetic and real-world datasets with varying homophily ratios validate the effectiveness of SELENE in homophilous and heterophilous settings showing an up to 12.52% clustering accuracy gain.

Large Language Models (LLMs) stand at the forefront of a number of Natural Language Processing (NLP) tasks. Despite the widespread adoption of LLMs in NLP, much of their potential in broader fields remains largely unexplored, and significant limitations persist in their design and implementation. Notably, LLMs struggle with structured data, such as graphs, and often falter when tasked with answering domain-specific questions requiring deep expertise, such as those in biology and chemistry. In this paper, we explore a fundamental question: Can LLMs effectively handle molecule prediction tasks? Rather than pursuing top-tier performance, our goal is to assess how LLMs can contribute to diverse molecule tasks. We identify several classification and regression prediction tasks across six standard molecule datasets. Subsequently, we carefully design a set of prompts to query LLMs on these tasks and compare their performance with existing Machine Learning (ML) models, which include text-based models and those specifically designed for analysing the geometric structure of molecules. Our investigation reveals several key insights: Firstly, LLMs generally lag behind ML models in achieving competitive performance on molecule tasks, particularly when compared to models adept at capturing the geometric structure of molecules, highlighting the constrained ability of LLMs to comprehend graph data. Secondly, LLMs show promise in enhancing the performance of ML models when used collaboratively. Lastly, we engage in a discourse regarding the challenges and promising avenues to harness LLMs for molecule prediction tasks. The code and models are available at https://github.com/zhiqiangzhongddu/LLMaMol.

Large Language Models (LLMs) have shown remarkable capabilities in processing various data structures, including graphs. While previous research has focused on developing textual encoding methods for graph representation, the emergence of multimodal LLMs presents a new frontier for graph comprehension. These advanced models, capable of processing both text and images, offer potential improvements in graph understanding by incorporating visual representations alongside traditional textual data. This study investigates the impact of graph visualisations on LLM performance across a range of benchmark tasks at node, edge, and graph levels. Our experiments compare the effectiveness of multimodal approaches against purely textual graph representations. The results provide valuable insights into both the potential and limitations of leveraging visual graph modalities to enhance LLMs' graph structure comprehension abilities.

As Machine Learning (ML) models grow in size and demand higher-quality training data, the expenses associated with re-training and fine-tuning these models are escalating rapidly. Inspired by recent impressive achievements of Large Language Models (LLMs) in different fields, this paper delves into the question: can LLMs efficiently improve an ML's performance at a minimal cost? We show that, through our proposed training-free framework LlmCorr, an LLM can work as a post-hoc corrector to propose corrections for the predictions of an arbitrary ML model. In particular, we form a contextual knowledge database by incorporating the dataset's label information and the ML model's predictions on the validation dataset. Leveraging the in-context learning capability of LLMs, we ask the LLM to summarise the instances in which the ML model makes mistakes and the correlation between primary predictions and true labels. Following this, the LLM can transfer its acquired knowledge to suggest corrections for the ML model's predictions. Our experimental results on the challenging molecular predictions show that LlmCorr improves the performance of a number of models by up to 39%.

Predicting protein properties is paramount for biological and medical advancements. Current protein engineering mutates on a typical protein, called the wild-type, to construct a family of homologous proteins and study their properties. Yet, existing methods easily neglect subtle mutations, failing to capture the effect on the protein properties. To this end, we propose EvolMPNN, Evolution-aware Message Passing Neural Network, to learn evolution-aware protein embeddings. EvolMPNN samples sets of anchor proteins, computes evolutionary information by means of residues and employs a differentiable evolution-aware aggregation scheme over these sampled anchors. This way EvolMPNN can capture the mutation effect on proteins with respect to the anchor proteins. Afterwards, the aggregated evolution-aware embeddings are integrated with sequence embeddings to generate final comprehensive protein embeddings. Our model shows up to 6.4% better than state-of-the-art methods and attains 36X inference speedup in comparison with large pre-trained models. The code and models are available at https://anonymous.4open.science/r/EvolMPNN.

Graph Neural Networks (GNNs) have been predominant for graph learning tasks; however, recent studies showed that a well-known graph algorithm, Label Propagation (LP), combined with a shallow neural network can achieve comparable performance to GNNs in semi-supervised node classification on graphs with high homophily. In this paper, we show that this approach falls short on graphs with low homophily, where nodes often connect to the nodes of the opposite classes. To overcome this, we carefully design a combination of a base predictor with LP algorithm that enjoys a closed-form solution as well as convergence guarantees. Our algorithm first learns the class compatibility matrix and then aggregates label predictions using LP algorithm weighted by class compatibilities. On a wide variety of benchmarks, we show that our approach achieves the leading performance on graphs with various levels of homophily. Meanwhile, it has orders of magnitude fewer parameters and requires less execution time. Empirical evaluations demonstrate that simple adaptations of LP can be competitive in semi-supervised node classification in both homophily and heterophily regimes.

Predicting protein properties is paramount for biological and medical advancements. Current protein engineering mutates on a typical protein, called the wild-type, to construct a family of homologous proteins and study their properties. Yet, existing methods easily neglect subtle mutations, failing to capture the effect on the protein properties. To this end, we propose EvolMPNN, Evolution-aware Message Passing Neural Network, an efficient model to learn evolution-aware protein embeddings. EvolMPNN samples sets of anchor proteins, computes evolutionary information by means of residues and employs a differentiable evolution-aware aggregation scheme over these sampled anchors. This way, EvolMPNN can efficiently utilise a novel message-passing method to capture the mutation effect on proteins with respect to the anchor proteins. Afterwards, the aggregated evolution-aware embeddings are integrated with sequence embeddings to generate final comprehensive protein embeddings. Our model shows up to 6.4% better than state-of-the-art methods and attains 36× inference speedup in comparison with large pre-trained models. Code and models are available at https://github.com/zhiqiangzhongddu/EvolMPNN .

The outbreak of the COVID-19 pandemic triggered the perils of misinformation over social media. By amplifying the spreading speed and popularity of trustworthy information, influential social media users have been helping overcome the negative impacts of such flooding misinformation. In this article, we use the COVID-19 pandemic as a representative global health crisisand examine the impact of the COVID-19 pandemic on these influential users’ subjective well-being (SWB), one of the most important indicators of mental health. We leverage X (formerly known as Twitter) as a representative social media platform and conduct the analysis with our collection of 37,281,824 tweets spanning almost two years. To identify influential X users, we propose a new measurement called user bridging performance (UBM) to evaluate the speed and wideness gain of information transmission due to their sharing. With our tweet collection, we manage to reveal the more significant mental sufferings of influential users during the COVID-19 pandemic. According to this observation, through comprehensive hierarchical multiple regression analysis , we are the first to discover the strong relationship between individual social users’ subjective well-being and their bridging performance. We proceed to extend bridging performance from individuals to user subgroups. The new measurement allows us to conduct a subgroup analysis according to users’ multilingualism and confirm the bridging role of multilingual users in the COVID-19 information propagation. We also find that multilingual users not only suffer from a much lower SWB in the pandemic, but also experienced a more significant SWB drop.

Graph Neural Networks (GNNs) have emerged as a dominant paradigm in machine learning for graphs, and recently developed Recommendation System (RecSys) models have significantly benefited from them. However, recent research has highlighted a limitation in classical GNNs, revealing that their message-passing mechanism is inherently flat, making it unable to capture hierarchical semantics within the graph. Recognizing the potential richness of information in the hierarchical structure of user-item bipartite graphs for RecSys, this paper introduces a novel end-to-end GNN-based RecSys model called Hierarchical Bipartite Graph Convolutional Network (HierBGCN). Specifically, we devise a BiDiffPool layer capable of performing differentiable pooling operations on the bipartite graph while preserving crucial properties. Through the stacking of multiple BiDiffPool layers, the bipartite graph undergoes hierarchical coarsening, enabling the extraction of multi-level knowledge. This allows GNNs to operate at each level, capturing diverse, high-order user-item interactions. Ultimately, the information from each coarsening level is aggregated to generate final user/item representations, effectively encapsulating the hierarchical knowledge inherent in user-item interactions. Empirical experiments conducted on four established RecSys datasets consistently demonstrate the superior performance of the proposed HierBGCN compared to competing models.

Proposed as a solution to the inherent black-box limitations of graph neural networks (GNNs), post-hoc GNN explainers aim to provide precise and insightful explanations of the behaviours exhibited by trained GNNs. Despite their recent notable advancements in academic and industrial contexts, the robustness of post-hoc GNN explainers remains unexplored when confronted with label noise. To bridge this gap, we conduct a systematic empirical investigation to evaluate the efficacy of diverse post-hoc GNN explainers under varying degrees of label noise. Our results reveal several key insights: Firstly, post-hoc GNN explainers are susceptible to label perturbations. Secondly, even minor levels of label noise, inconsequential to GNN performance, harm the quality of generated explanations substantially. Lastly, we engage in a discourse regarding the progressive recovery of explanation effectiveness with escalating noise levels.

Self-explainable deep neural networks are a recent class of models that can output ante-hoc local explanations that are faithful to the model's reasoning, and as such represent a step forward toward filling the gap between expressiveness and interpretability. Self-explainable graph neural networks (GNNs) aim at achieving the same in the context of graph data. This begs the question: do these models fulfill their implicit guarantees in terms of faithfulness? In this extended abstract, we analyze the faithfulness of several self-explainable GNNs using different measures of faithfulness, identify several limitations -- both in the models themselves and in the evaluation metrics -- and outline possible ways forward.

We propose a new deep learning cascade prediction model CasSIM that can simultaneously achieve two most demanded objectives: popularity prediction and final adopter prediction . Compared to existing methods based on cascade representation, CasSIM simulates information diffusion processes by exploring users’ dual roles in information propagation with three basic factors: users’ susceptibilities , influences and message contents . With effective user profiling, we are the first to capture the topic-specific property of susceptibilities and influences. In addition, the use of graph neural networks allows CasSIM to capture the dynamics of susceptibilities and influences during information diffusion. We evaluate the effectiveness of CasSIM on three real-life datasets and the results show that CasSIM outperforms the state-of-the-art methods in popularity and final adopter prediction.

Graph Neural Networks (GNNs) are powerful techniques in representation learning for graphs and have been increasingly deployed in a multitude of different applications that involve node- and graph-wise tasks. Most existing studies solve either the node-wise task or the graph-wise task independently while they are inherently correlated. This work proposes a unified model, AdamGNN, to interactively learn node and graph representations in a mutual-optimisation manner. Compared with existing GNN models and graph pooling methods, AdamGNN enhances the node representation with the learned multi-grained semantics and avoids losing node features and graph structure information during pooling. Specifically, a differentiable pooling operator is proposed to adaptively generate a multi-grained structure that involves meso- and macro-level semantic information in the graph. We also devise the unpooling operator and the flyback aggregator in AdamGNN to better leverage the multi-grained semantics to enhance node representations. The updated node representations can further adjust the graph representation in the next iteration. Experiments on 14 real-world graph datasets show that AdamGNN can significantly outperform 17 competing models on both node- and graph-wise tasks. The ablation studies confirm the effectiveness of AdamGNN's components, and the last empirical analysis further reveals the ingenious ability of AdamGNN in capturing long-range interactions.

The integration of Artificial Intelligence (AI) into the field of drug discovery has been a growing area of interdisciplinary scientific research. However, conventional AI models are heavily limited in handling complex biomedical structures (such as 2D or 3D protein and molecule structures) and providing interpretations for outputs, which hinders their practical application. As of late, Graph Machine Learning (GML) has gained considerable attention for its exceptional ability to model graph-structured biomedical data and investigate their properties and functional relationships. Despite extensive efforts, GML methods still suffer from several deficiencies, such as the limited ability to handle supervision sparsity and provide interpretability in learning and inference processes, and their ineffectiveness in utilising relevant domain knowledge. In response, recent studies have proposed integrating external biomedical knowledge into the GML pipeline to realise more precise and interpretable drug discovery with limited training instances. However, a systematic definition for this burgeoning research direction is yet to be established. This survey presents a comprehensive overview of long-standing drug discovery principles, provides the foundational concepts and cutting-edge techniques for graph-structured data and knowledge databases, and formally summarises Knowledge-augmented Graph Machine Learning (KaGML) for drug discovery. we propose a thorough review of related KaGML works, collected following a carefully designed search methodology, and organise them into four categories following a novel-defined taxonomy. To facilitate research in this promptly emerging field, we also share collected practical resources that are valuable for intelligent drug discovery and provide an in-depth discussion of the potential avenues for future advancements.

The outbreak of the COVID-19 pandemic triggers infodemic over online social media, which significantly impacts public health around the world, both physically and psychologically. In this paper, we study the impact of the pandemic on the mental health of influential social media users, whose sharing behaviours significantly promote the diffusion of COVID-19 related information. Specifically, we focus on subjective well-being (SWB), and analyse whether SWB changes have a relationship with their bridging performance in information diffusion, which measures the speed and wideness gain of information transmission due to their sharing. We accurately capture users’ bridging performance by proposing a new measurement. Benefiting from deep-learning natural language processing models, we quantify social media users’ SWB from their textual posts. With the data collected from Twitter for almost two years, we reveal the greater mental suffering of influential users during the COVID-19 pandemic. Through comprehensive hierarchical multiple regression analysis, we are the first to discover the strong relationship between social users’ SWB and their bridging performance.

Recently, increasing attention has been paid to heterogeneous graph representation learning (HGRL), which aims to embed rich structural and semantic information in heterogeneous information networks (HINs) into low-dimensional node representations. To date, most HGRL models rely on hand-crafted meta-paths. However, the dependency on manually-defined meta-paths requires domain knowledge, which is difficult to obtain for complex HINs. More importantly, the pre-defined or generated meta-paths of all existing HGRL methods attached to each node type or node pair cannot be personalised to each individual node. To fully unleash the power of HGRL, we present a novel framework, Personalised Meta-path based Heterogeneous Graph Neural Networks (PM-HGNN), to jointly generate meta-paths that are personalised for each individual node in a HIN and learn node representations for the target downstream task like node classification. Precisely, PM-HGNN treats the meta-path generation as a Markov Decision Process and utilises a policy network to adaptively generate a meta-path for each individual node and simultaneously learn effective node representations. The policy network is trained with deep reinforcement learning by exploiting the performance improvement on a downstream task. We further propose an extension, PM-HGNN ++ , to better encode relational structure and accelerate the training during the meta-path generation. Experimental results reveal that both PM-HGNN and PM-HGNN ++ can significantly and consistently outperform 16 competing baselines and state-of-the-art methods in various settings of node classification. Qualitative analysis also shows that PM-HGNN ++ can identify meaningful meta-paths overlooked by human knowledge.

An information outbreak occurs on social media along with the COVID-19 pandemic and leads to an infodemic. Predicting the popularity of online content, known as cascade prediction, allows for not only catching in advance information that deserves attention, but also identifying false information that will widely spread and require quick response to mitigate its negative impact. Among the various information diffusion patterns leveraged in previous works, the spillover effect of the information exposed to users on their decisions to participate in diffusing certain information has not been studied. In this paper, we focus on the diffusion of information related to COVID-19 preventive measures due to its special role in consolidating public efforts to slow down the spread of the virus. Through our collected Twitter dataset, we validate the existence of the spillover effects. Building on this finding, we propose extensions to three cascade prediction methods based on Graph Neural Networks (GNNs). Experiments conducted on our dataset demonstrated that the use of the identified spillover effects significantly improves the state-of-the-art GNN methods in predicting the popularity of not only preventive measure messages, but also other COVID-19 messages.