Due to the wide existence of unlabeled graph-structured data (e.g., molecular structures), the graph-level clustering has recently attracted increasing attention, whose goal is to divide the input graphs into several disjoint groups. However, the existing methods habitually focus on learning the graphs embeddings with different graph reguralizations, and seldom refer to the obvious differences in data distributions of distinct graph-level datasets. How to characteristically consider multiple graph-level datasets in a general well-designed model without prior knowledge is still challenging. In view of this, we propose a novel Graph Prompt Clustering (GPC) method. Within this model, there are two main modules, i.e., graph model pretraining as well as prompt and finetuning. In the graph model pretraining module, the graph model is pretrained by a selected source graph-level dataset with mutual information maximization and self-supervised clustering regularization. In the prompt and finetuning module, the network parameters of the pretrained graph model are frozen, and a groups of learnable prompt vectors assigned to each graph-level representation are trained for adapting different target graph-level datasets with various data distributions. Experimental results across six benchmark datasets demonstrate the impressive generalization capability and effectiveness of GPC compared with the state-of-the-art methods.

Drug combination therapy with significant advantages is a well-established concept in cancer treatment. Some related efforts have been made with multiple artful deep learning techniques. However, they are usually based on data for drug synergy prediction, ignoring the professional characteristics of data and the systematic knowledge accumulation. Meanwhile, integrating the dispersed professional knowledge and effectively utilizing it in data remains a crucial technical challenge. In this study, we propose KSDDC, a novel model for knowledge-aware synergistic discovery of drug combinations from a large language model (LLM) perspective (i.e., from the continuously learnable and refined large database). Within this framework, three main modules are well-designed, i.e., knowledge-aware drug feature auto-encoding, knowledge-aware cell line feature encoding and drug-drug synergy prediction. Informative embeddings of samples are discovered and combined to make accurate drug synergy prediction. Overall, KSDDC is superior compared with the other shallow machine learning based methods and deep learning based methods on several synergistic prediction benchmarks, where about 19% F1-score improvements over the second best method on DrugComb_1 can be observed. Starting with drug synergy prediction, our studies with knowledge-enabled data mining offer valuable insights and serve as a reference method for future research in this field.

Attributed graph clustering, aiming to discover the underlying graph structure and partition the graph nodes into several disjoint categories, is a basic task in graph data analysis. Although recent efforts over graph contrastive clustering have achieved decent performances, most of them get accustomed to construct the positive neighbor set by the generated pseudo clustering information, directly ignoring the ready-made neighbor nodes and the underlying semantics of edges in a graph. How to well deal with the graph neighbor-specific information to facilitate the performance of graph contrastive clustering is still a challenging problem. Therefore, in this work, we propose a novel Homophily Induced Contrastive Attributed Graph Clustering (HomoCAGC) method, where the power of homophily is exploited in facilitating the performance of contrastive attributed graph clustering, while the pseudo homophily in a graph is also explored and distinguished. Especially, the node feature as reliable information guidance is used to compute the underlying feature-oriented pair-wise node similarity, based on which the positive node pairs in contrastive regularizer are adjusted for better node representation characterization. According to the refined node representations, a triplet self-supervised clustering objective is well-designed to ensure the output embedding is cluster-oriented, and suitable for the downstream clustering task. Extensive experiments on seven benchmarks are conducted to demonstrate the effectiveness of HomoCAGC.

Due to the collective decision-making nature of enterprises, the process of accepting recommendations is predominantly characterized by an analytical synthesis of objective requirements and cost-effectiveness, rather than being rooted in individual interests. This distinguishes enterprise recommendation scenarios from those tailored for individuals or groups formed by similar individuals, rendering traditional recommendation algorithms less applicable in the corporate context. To overcome the challenges, by taking the corporate volunteer as an example, which aims to recommend volunteer activities to enterprises, we propose a novel recommendation model calledAttributeKnowledgeGraphNeuralNetworks (AKGNN). Specifically, a novel comprehensive attribute knowledge graph is constructed for enterprises and volunteer activities, based on which we obtain the feature representation. Then we utilize anextendedVariationalAuto-Encoder (eVAE) model to learn the preferences representation and then we utilize a GNN model to learn the comprehensive representation with representation of the similar nodes. Finally, all the comprehensive representations are input to the prediction layer. Extensive experiments have been conducted on real datasets, confirming the advantages of the AKGNN model. We delineate the challenges faced by recommendation algorithms in Business-to-Business (B2B) platforms and introduces a novel research approach utilizing attribute knowledge graphs.

Word polysemy poses a formidable challenge in the semantic similarity task, especially for complex Chinese semantic information. However, most existing methods tend to emphasize information expansion, often overlooking the fact that the added information may be either irrelevant or only weakly correlated. In view of this, we propose a novel approach that fuses knowledge enhancement and context filtering to achieve self-selective semantic expansion. This approach, termed mutual-scenario-aware multimodal-enhanced representation learning (MuSAM), integrates information across multiple modalities. Specifically, we extend individual words within three modalities, and the extended information with weak correlation is filtered and denoised, to get the mutual-scenario extended information. The extended information with strong correlation in each modality will be fused to obtain the multimodal fusion representation vector of the word pair. Experimental evaluations conducted on five datasets underscore the superiority of the MuSAM model over state-of-the-art methods, showcasing a performance improvement ranging from a minimum of 4% to a maximum of 21%. Remarkably, our model is designed in a completely engineering manner, which can be applied to real scenarios directly without manual intervention.

Most existing recommendation research has been concentrated on unidirectional recommendation, i.e. only recommending items to users. However, in many real-world scenarios, the platform needs to achieve bi-directional recommendation. For example, in an online recruitment scenario, the recommender system not only needs to recommend positions to candidates, but also recommend candidates to enterprises. In this paper, we first formalize a new recommendation problem called bi-directional recommendation and contribute a new bidirectional recommendation model named BiROR (Bi-directional Recommendation for Online Recruitment). In BiROR, an encoder component is utilized to learn the text embeddings, and a graph learning component is designed to learn the graph embeddings. In addition, a multi-task learning framework is designed to achieve bi-directional recommendation. In the multi-task learning framework, we share the text embeddings and graph embeddings to alleviate the problems of data sparsity and data asymmetry in online recruitment. Extensive experiments in a real-world task show that BiROR outperforms the state-of-the-art methods, verifying the effectiveness of the designs of our model.