The standard evaluation protocol for measuring the quality of Knowledge Graph Completion methods - the task of inferring new links to be added to a graph - typically involves a step which ranks every entity of a Knowledge Graph to assess their fit as a head or tail of a candidate link to be added. In Knowledge Graphs on a larger scale, this task rapidly becomes prohibitively heavy. Previous approaches mitigate this problem by using random sampling of entities to assess the quality of links predicted or suggested by a method. However, we show that this approach has serious limitations since the ranking metrics produced do not properly reflect true outcomes. In this paper, we present a thorough analysis of these effects along with the following findings. First, we empirically find and theoretically motivate why sampling uniformly at random vastly overestimates the ranking performance of a method. We show that this can be attributed to the effect of easy versus hard negatives. Second, we propose a framework that uses relational recommenders to guide the selection of candidates for evaluation. We provide both theoretical and empirical justification of our methodology, and find that simple and fast methods work extremely well, matching advanced neural approaches. Even when a large portion of the true candidates for a property are missed, the estimation of the ranking metrics on a downstream model barely deteriorates. With our proposed framework, we can reduce the time and computation needed similar to random sampling strategies while vastly improving the estimation; on ogbl-wikikg2, we show that accurate estimations of the full ranking can be obtained in 20 seconds instead of 30 minutes. We conclude that considerable computational effort can be saved by effective preprocessing and sampling methods and still reliably predict performance accurately of the true performance for the entire ranking procedure. We make our code available to the community¹. ¹Accessible at https://github.com/Filco306/are-we-wasting-time.

Graph Neural Networks (GNNs) have emerged as powerful tools for extracting insights from graph-structured data. However, GNNs often encounter challenges when aggregating information across distant and constrained connections, leading to performance degradation due to a phenomenon known as over-squashing. Previous solutions, such as static rewiring, address this issue by increasing graph density but compromise the inherent inductive bias of GNNs with respect to node distances. In this study, we introduce HopNet, a novel model designed to facilitate effective long-range information propagation through learnable rewiring. HopNet employs attention mechanisms to dynamically create targeted shortcuts, enabling efficient communication between distant nodes while maintaining a balance between local and global interactions. Extensive experiments across diverse tasks, including node classification, link prediction, graph regression, and graph classification, on established real-world benchmark datasets demonstrate HopNet’s ability to overcome GNN limitations, consistently achieving superior performance over state-of-the-art methods.

Deep learning (DL) models have significantly transformed machine learning (ML), particularly with their prowess in classification tasks. However, these models struggle to differentiate between in-distribution (ID) and out-of-distribution (OOD) data at the testing phase. This challenge has curtailed their deployment in sensitive fields like biotechnology, where misidentifying OOD data, such as unclear or unknown bacterial genomic sequences, as known ID classes could lead to dire consequences. To address this, we propose an approach to make DL models OOD-sensitive by exploiting the configuration of the logit space embeddings, into the model’s decision-making process. Leveraging the effect observed in recent studies that there is minimal overlap between the embeddings of ID and OOD data, we use a density estimator to model the ID logit distribution based on the training data. This allows us to reliably flag data that do not match the ID distribution as OOD. Our methodology is designed to be independent of the specific data or model architecture and can seamlessly augment existing trained models without the need to expose them to OOD data. Testing our method on widely recognized image datasets, we achieve leading-edge results, including a substantial 10% enhancement in the area under the receiver operating characteristic curve (AUCROC) on the Google genome dataset.

Link prediction is a crucial task in many downstream applications of graph machine learning. To this end, Graph Neural Network (GNN) is a widely used technique for link prediction, mainly in transductive settings, where the goal is to predict missing links between existing nodes. However, many real-life applications require an inductive setting that accommodates for new nodes, coming into an existing graph. Thus, recently inductive link prediction has attracted considerable attention, and a multi-layer perceptron (MLP) is the popular choice of most studies to learn node representations. However, these approaches have limited expressivity and do not fully capture the graph’s structural signal. Therefore, in this work we propose LEAP, an inductive link prediction method based on LEArnable toPology augmentation. Unlike previous methods, LEAP models the inductive bias from both the structure and node features, and hence is more expressive. To the best of our knowledge, this is the first attempt to provide structural contexts for new nodes via learnable augmentation in inductive settings. Extensive experiments on seven real-world homogeneous and heterogeneous graphs demonstrates that LEAP significantly surpasses SOTA methods. The improvements are up to 22% and 17% in terms of AUC and average precision, respectively. The code and datasets are available on GitHub (1https://github.com/AhmedESamy/LEAP/).

Decentralized Learning (DL) enables privacy-preserving collaboration among organizations or users to enhance the performance of local deep learning models. However, model aggregation becomes challenging when client data is heterogeneous, and identifying compatible collaborators without direct data exchange remains a pressing issue. In this paper, we investigate the effectiveness of various similarity metrics in DL for identifying peers for model merging, conducting an empirical analysis across multiple datasets with distribution shifts. Our research provides insights into the performance of these metrics, examining their role in facilitating effective collaboration. By exploring the strengths and limitations of these metrics, we contribute to the development of robust DL methods.

Wireless ray-tracing (RT) is emerging as a key tool for three-dimensional (3D) wireless channel modeling, driven by advances in graphical rendering. Current approaches struggle to accurately model beyond 5G (B5G) network signaling, which often operates at higher frequencies and is more susceptible to environmental conditions and changes. Existing online learning solutions require real-time interaction with radio environment during training, which is both costly and incompatible with GPU-based processing. In response, we propose a novel approach that redefines ray trajectory generation as a sequential decision-making problem, solved with the proposed Scene-Aware Neural Decision Wireless Channel Raytracing Hierarchy (SANDWICH) approach. The SANDWICH approach leverages a decision transformer to jointly learn the optical, physical, and signal properties within each designated environment in a fully differentiable approach, which can be trained entirely on GPUs. SANDWICH offers superior performance compared to existing online learning methods, and outperforms the baseline by 4e^-2 rad in RT accuracy. Furthermore, channel gain estimation w.r.t predicted trajectory only fades 0.5 dB away from using ground truth wireless RT result for channel gain estimation.²

Wireless ray-tracing (RT) is emerging as a key tool for three-dimensional (3D) wireless channel modeling, driven by advances in graphical rendering. Current approaches struggle to accurately model beyond 5G (B5G) network signaling, which often operates at higher frequencies and is more susceptible to environmental conditions and changes. Existing online learning solutions require real-time interaction with radio environment during training, which is both costly and incompatible with GPU-based processing. In response, we propose a novel approach that redefines ray trajectory generation as a sequential decision-making problem, solved with the proposed Scene-Aware Neural Decision Wireless Channel Raytracing Hierarchy (SANDWICH) approach. The SANDWICH approach leverages a decision transformer to jointly learn the optical, physical, and signal properties within each designated environment in a fully differentiable approach, which can be trained entirely on GPUs. SANDWICH offers superior performance compared to existing online learning methods, and outperforms the baseline by 4e-2 rad in RT accuracy. Furthermore, channel gain estimation w.r.t predicted trajectory only fades 0.5 dB away from using ground truth wireless RT result for channel gain estimation.2 Index Terms-Wireless Raytracing, RF Sensing, Channel Modeling, Channel Generation

In smart mobility, large networks of geographically distributed sensors produce vast amounts of high-frequency spatio-temporal data that must be processed in real time to avoid major disruptions. Traditional centralized approaches are increasingly unsuitable to this task, as they struggle to scale with expanding sensor networks, and reliability issues in central components can easily affect the whole deployment. To address these challenges, we explore and adapt semi-decentralized training techniques for Spatio-Temporal Graph Neural Networks (ST-GNNs) in the smart mobility domain. We implement a simulation framework where sensors are grouped by proximity into multiple cloudlets, each handling a subgraph of the traffic graph, fetching node features from other cloudlets to train its own local ST-GNN model, and exchanging model updates with other cloudlets to ensure consistency, enhancing scalability and removing reliance on a centralized aggregator. We perform extensive comparative evaluation of four different ST-GNN training setups - centralized, traditional FL, server-free FL, and Gossip Learning - on large-scale traffic datasets, the METR-LA and PeMS-BAY datasets, for short-, mid-, and long-term vehicle speed predictions. Experimental results show that semi-decentralized setups are comparable to centralized approaches in performance metrics, while offering advantages in terms of scalability and fault tolerance. In addition, we highlight often overlooked issues in existing literature for distributed ST-GNNs, such as the variation in model performance across different geographical areas due to region-specific traffic patterns, and the significant communication overhead and computational costs. However, due to the planar nature of graphs, per-cloudlet costs remain consistent as the network grows, unlike the growing costs in a centralized approach.

Spectral clustering is a widely adopted method capable of identifying complicated cluster boundaries. However, traditional spectral clustering requires the definition of a predefined similarity metric for constructing the Laplacian matrix, a requirement that limits flexibility and adaptability. Instead of predefining this metric upfront as a fixed parametric function, we introduce a novel approach that learns the optimal parameters of a similarity function through parameter optimization. This optimizes a similarity function to assign high similarity values to data pairs with shared discriminative features and low values to those without such features. Previous methods that adapt similarity measures typically treat their parameters as hyperparameters or rely on non-convex optimization strategies. However, these approaches are not well-suited for unsupervised scenarios, as they depend heavily on initial conditions and require labeled data for validation, which is unavailable in such settings. In contrast, our method employs convex optimization to learn the parameters of the similarity metrics directly, rather than treating them as hyperparameters. This enables robust and reliable unsupervised learning, making our approach particularly well-suited for spectral clustering. We validate the effectiveness and adaptability of our method on several benchmark datasets, demonstrating superior performance compared to existing techniques.

The sets of possible heads and tails for relations in a Knowledge Graph and a type taxonomy of participating entities are important aspects of a Knowledge Graph and constitute a large portion of a Knowledge Graph’s ontology. Making the ontology explicit helps to ensure consistency of the knowledge represented in the graph and allows for less costly maintenance and update of graph content. However, Knowledge Graphs are often conveniently formed without an explicitly described ontology, using only (head, relation, tail)-tuples. For such graphs without predefined structure, we propose learning an ontology and a hierarchical type taxonomy from the graph itself, taking advantage of the reciprocity of entity types and sets of possible heads (relational domains) and tails (relational ranges). Experiments on real-world datasets validate our approach and demonstrate the promise for leveraging machine learning methodologies to efficiently generate taxonomies and ontologies jointly for Knowledge Graphs (Our implementation can be found at https://tinyurl.com/5n6sw6yj).