Retrieving external knowledge to Augment Generations of downstream task solutions (RAGs) has become a standard practice in powering knowledge-intensive applications. However, real-world knowledge often manifests in heterogeneous yet distinctive structures (e.g., tabular schemas, social networks, and document trees), the effective modeling of which demands specialized modeling, practical engineering, and domain expertise. Meanwhile, adopting RAGs in high-stakes scenarios underscores rigorous safety considerations. Despite the importance of this structural perspective, the current landscape remains fragmented. Moreover, few approaches adequately consider how structured knowledge shapes RAG's safety. Against this backdrop, our tutorial offers a structural perspective on RAGs. We begin by overviewing structured RAGs across their full lifecycle, highlighting their canonical designs. We then examine how design principles can be specialized for different knowledge structures, showcasing their unique applications and security attack/defense strategies. The tutorial slide is available https://kindlab-fly.github.io/tutorials/WSDM26/

Link Prediction (LP) is a critical task in graph machine learning. While Graph Neural Networks (GNNs) have significantly advanced LP performance recently, existing methods face key challenges including limited supervision from sparse connectivity, sensitivity to initialization, and poor generalization under distribution shifts. We explore pretraining as a solution to address these challenges. Unlike node classification, LP is inherently a pairwise task, which requires the integration of both node- and edge-level information. In this work, we present the first systematic study on the transferability of these distinct modules and propose a late fusion strategy to effectively combine their outputs for improved performance. To handle the diversity of pretraining data and avoid negative transfer, we introduce a Mixture-of-Experts (MoE) framework that captures distinct patterns in separate experts, facilitating seamless application of the pretrained model on diverse downstream datasets. For fast adaptation, we develop a parameter-efficient tuning strategy that allows the pretrained model to adapt to unseen datasets with minimal computational overhead. Experiments on 16 datasets across two domains demonstrate the effectiveness of our approach, achieving state-of-the-art performance on low-resource link prediction while obtaining competitive results compared to end-to-end trained methods, with over 10,000x lower computational overhead.

Graphs, which encode pairwise relations between entities, serve as a fundamental data structure across real-world domains. Many critical applications can be formulated as graph-based tasks, and graph machine learning (GML), from the shallow embedding models to graph neural networks and further advanced to the most powerful graph transformers, has been well-established to automate knowledge discovery and decision-making on graphs. In parallel, the recent emergence of large foundational models has driven machine learning into a new era of Generative Artificial Intelligence (Gen-AI), and this revolution presents both unprecedented opportunities and profound challenges for the well-established GML paradigms. However, few investigations have analyzed and envisioned how GML should evolve to harness these opportunities, address these challenges, and embrace this new Gen-AI era. To fill in this gap, we organize the first international Workshop on Machine Learning on Graphs in the Era of Generative Artificial Intelligence (MLoG-GenAI), held in connection with the 31st ACM Conference on Knowledge Discovery and Data Mining, which provides a venue to gather academic researchers and industry practitioners to discuss and picture the development of GML in the new Gen-AI era.

State-of-the-art link prediction (LP) models demonstrate impressive benchmark results. However, popular benchmark datasets often assume that training, validation, and testing samples are represen- tative of the overall dataset distribution. In real-world situations, this assumption is often incorrect; uncontrolled factors lead new dataset samples to come from a different distribution than train- ing samples. Additionally, the majority of recent work with graph dataset shift focuses on node- and graph-level tasks, largely ignor- ing link-level tasks. To bridge this gap, we introduce a novel splitting strategy, known as LPShift, which utilizes structural properties to induce a controlled distribution shift. We verify LPShift's effect through empirical evaluation of SOTA LP models on 16 LPShift variants of original dataset splits, with results indicating drastic changes to model performance. Additional experiments demon- strate graph structure has a strong influence on the success of current generalization methods. The source code is available here https://github.com/revolins/LPShift.

Knowledge Graph Completion (KGC) attempts to predict missing facts in a Knowledge Graph (KG). Recently, there's been an increased focus on designing KGC methods that can excel in the inductive setting, where a portion or all of the entities and relations seen in inference are unobserved during training. Numerous benchmark datasets have been proposed for inductive KGC, all of which are subsets of existing KGs used for transductive KGC. However, we find that the current procedure for constructing inductive KGC datasets inadvertently creates a shortcut that can be exploited even while disregarding the relational information. Specifically, we observe that the Personalized PageRank (PPR) score can achieve strong or near SOTA performance on most datasets. In this paper, we study the root cause of this problem. Using these insights, we propose an alternative strategy for constructing inductive KGC datasets that helps mitigate the PPR shortcut. We then benchmark multiple popular methods using the newly constructed datasets and analyze their performance. The new benchmark datasets help promote a better understanding of the capabilities and challenges of inductive KGC by removing any shortcuts that obfuscate performance. The code and dataset and can be found https://github.com/HarryShomer/Better-Inductive-KGC.

Link prediction is a common task on graph-structured data that has seen applications in a variety of domains. Classically, hand-crafted heuristics were used for this task. Heuristic measures are chosen such that they correlate well with the underlying factors related to link formation. In recent years, a new class of methods has emerged that combines the advantages of message-passing neural networks (MPNN) and heuristics methods. These methods perform predictions by using the output of an MPNN in conjunction with a "pairwise encoding" that captures the relationship between nodes in the candidate link. They have been shown to achieve strong performance on numerous datasets. However, current pairwise encodings often contain a strong inductive bias, using the same underlying factors to classify all links. This limits the ability of existing methods to learn how to properly classify a variety of different links that may form from different factors. To address this limitation, we propose a new method, LPFormer, which attempts to adaptively learn the pairwise encodings for each link. LPFormer models the link factors via an attention module that learns the pairwise encoding that exists between nodes by modeling multiple factors integral to link prediction. Extensive experiments demonstrate that LPFormer can achieve SOTA performance on numerous datasets while maintaining efficiency. The code is available at The code is available at https://github.com/HarryShomer/LPFormer.

Knowledge graphs (KGs) have gained prominence for their ability to learn representations for uni-relational facts. Recently, research has focused on modeling hyper-relational facts, which move beyond the restriction of uni-relational facts and allow us to represent more complex and real-world information. However, existing approaches for learning representations on hyper-relational KGs majorly focus on enhancing the communication from qualifiers to base triples while overlooking the flow of information from base triple to qualifiers. This can lead to suboptimal qualifier representations, especially when a large amount of qualifiers are presented. It motivates us to design a framework that utilizes multiple aggregators to learn representations for hyper-relational facts: one from the perspective of the base triple and the other one from the perspective of the qualifiers. Experiments demonstrate the effectiveness of our framework for hyper-relational knowledge graph completion across multiple datasets. Furthermore, we conduct an ablation study that validates the importance of the various components in our framework.

Adversarial training has been proven to be one of the most effective techniques to defend against adversarial examples. The majority of existing adversarial training methods assume that every class in the training data is equally distributed. However, in reality, some classes often have a large number of training data while others only have a very limited amount. Recent studies have shown that the performance of adversarial training will degrade drastically if the training data is imbalanced. In this paper, we propose a simple yet effective framework to enhance the robustness of DNN models under imbalanced scenarios. Our framework, Imb-Mix, first augments the training dataset by generating multiple adversarial examples for samples in the minority classes. This is done by first adding random noise to the original adversarial examples created by one specific adversarial attack method. It then constructs Mixup-mimic mixed examples upon the augmented dataset used by adversarial training. In addition, we theoretically prove the regularization effect of our Mixup-mimic mixed examples generation technique in Imb-Mix. Extensive experiments on various imbalanced datasets verify the effectiveness of the proposed framework.

A fundamental task for knowledge graphs (KGs) is knowledge graph completion (KGC). It aims to predict unseen edges by learning representations for all the entities and relations in a KG. A common concern when learning representations on traditional graphs is degree bias. It can affect graph algorithms by learning poor representations for lower-degree nodes, often leading to low performance on such nodes. However, there has been limited research on whether there exists degree bias for embedding-based KGC and how such bias affects the performance of KGC. In this paper, we validate the existence of degree bias in embedding-based KGC and identify the key factor to degree bias. We then introduce a novel data augmentation method, KG-Mixup, to generate synthetic triples to mitigate such bias. Extensive experiments have demonstrated that our method can improve various embedding-based KGC methods and outperform other methods tackling the bias problem on multiple benchmark datasets. 1