Link prediction is a fundamental task in graph machine learning with applications ranging from social recommendation to knowledge graph completion. Fairness in this setting is critical, as biased predictions can exacerbate societal inequalities. Prior work adopts a dyadic definition of fairness, enforcing fairness through demographic parity between intra-group and inter-group link predictions. However, we show that this dyadic framing can obscure underlying disparities across subgroups, allowing systemic biases to go undetected. Moreover, we argue that demographic parity does not meet the desired properties for fairness assessment in ranking-based tasks such as link prediction. We formalize the limitations of existing fairness evaluations and propose a framework that enables a more expressive assessment. Additionally, we propose a lightweight post-processing method combined with decoupled link predictors that effectively mitigates bias and achieves state-of-the-art fairness–utility trade-offs.

Graph Neural Networks (GNNs) have achieved state-of-the-art results in many relevant tasks where decisions might disproportionately impact specific communities. However, existing work on fair GNNs often assumes that either sensitive attributes are fully observed or they are missing completely at random. We show that an adversarial missingness process can inadvertently disguise a fair model through the imputation, leading the model to overestimate the fairness of its predictions. We address this challenge by proposing Better Fair than Sorry (BFtS), a fair missing data imputation model for sensitive attributes. The key principle behind BFtS is that imputations should approximate the worst-case scenario for fairness---i.e. when optimizing fairness is the hardest. We implement this idea using a 3-player adversarial scheme where two adversaries collaborate against a GNN classifier, and the classifier minimizes the maximum bias. Experiments using synthetic and real datasets show that BFtS often achieves a better fairness x accuracy trade-off than existing alternatives under an adversarial missingness process.

Graph Neural Networks (GNNs) achieve high performance but can be opaque to humans, making it difficult to understand and compare the many proposed architectures. While existing explainability methods attribute individual predictions to nodes, edges, or features, they do not provide architectural transparency or explain the fundamental performance gap between simple and more complex models. To address this limitation, we introduce Model-to-Data (M2D) distillation, a new framework that increases transparency by transferring model complexity into the data space. M2D distills the teacher model into an augmented graph with enriched features and structure, enabling a simple student to match the teacher's performance. By materializing model behavior in the data, our approach allows humans to inspect architectural advantages directly. We show that M2D reveals underlying mechanisms such as fairness objectives and attention-based aggregation in an interpretable way, enhancing GNN transparency while preserving performance.

Graph Anomaly Detection (GAD) has demonstrated great effectiveness in identifying unusual patterns within graph-structured data. However, while labeled anomalies are often scarce in emerging applications, existing supervised GAD approaches are either ineffective or not applicable when moved across graph domains due to distribution shifts and heterogeneous feature spaces. To address these challenges, we present GADT3, a novel test-time training framework for cross-domain GAD. GADT3 combines supervised and self-supervised learning during training while adapting to a new domain during test time using only self-supervised learning by leveraging a homophily-based affinity score that captures domain-invariant properties of anomalies. Our framework introduces four key innovations to cross-domain GAD: an effective self-supervision scheme, an attention-based mechanism that dynamically learns edge importance weights during message passing, domain-specific encoders for handling heterogeneous features, and class-aware regularization to address imbalance. Experiments across multiple cross-domain settings demonstrate that GADT3 significantly outperforms existing approaches, achieving average improvements of over 8.2% in AUROC and AUPRC compared to the best competing model.

Traffic incident detection is a well-established task in transportation, traditionally addressed using a combination of traffic sensors and driver reports. More recently, social media has become a rich data source for timely incident detection. However, the highly dynamic nature of social media, the challenges in mapping textual content to precise real-world locations, and potentially misleading posts complicate the extraction of reliable traffic information. Motivated by these challenges and leveraging recent advances in large language models (LLMs), we propose a real-time tweet validation pipeline that extracts and verifies traffic incidents reported on X (former Twitter). Our approach employs advanced parsing techniques for localization extraction. It integrates publicly available data to confirm the existence of an incident, thereby enhancing the robustness of downstream traffic analysis methods that combine sensor data with verified textual features. To support further research in this domain, we also introduce two new datasets: the Twitter Traffic Incidents dataset, which comprises manually curated and human-verified incident reports, and the PeMS Sensor + Incidents Reports dataset, featuring snapshots from California's PeMS traffic sensor system. Experimental results demonstrate that our pipeline significantly improves the reliability of traffic incident validation in tweets, serving as a basis for future traffic anomaly detection research.

Link prediction is a fundamental problem in graph data. In its most realistic setting, the problem consists of predicting missing or future links between random pairs of nodes from the set of disconnected pairs. Graph Neural Networks (GNNs) have become the predominant framework for link prediction. GNN-based methods treat link prediction as a binary classification problem and handle the extreme class imbalance -- real graphs are very sparse -- by sampling (uniformly at random) a balanced number of disconnected pairs not only for training but also for evaluation. However, we show that the reported performance of GNNs for link prediction in the balanced setting does not translate to the more realistic imbalanced setting and that simpler topology-based approaches are often better at handling sparsity. These findings motivate Gelato, a similarity-based link-prediction method that applies (1) graph learning based on node attributes to enhance a topological heuristic, (2) a ranking loss for addressing class imbalance, and (3) a negative sampling scheme that efficiently selects hard training pairs via graph partitioning. Experiments show that Gelato outperforms existing GNN-based alternatives.

Flood modeling is an important tool for supporting preventive and emergency measures to mitigate flood risks. Recently, there has been an increasing interest in exploring machine learning-based models as an alternative to traditional hydrodynamic models for flood simulation to address challenges such as scalability and accuracy. However, current ML approaches are ineffective at modeling early stages of flooding events, limiting their ability to simulate the entire evolution of the flood. Another key challenge is how to incorporate physics domain-knowledge into these data-driven models. In this paper, we address these challenges by introducing a physics-inspired graph neural network for flood simulation. Given a (geographical) region and precipitation data, our model predicts water depths in an autoregressive fashion. We propose a message-passing framework inspired by the conservation of momentum and mass expressed in the shallow-water equations, which describe the physical process of a flooding event. Empirical results on a dataset covering 9 regions and 7 historical precipitation events demonstrate that our model outperforms the best baseline, and is able to capture the propagation of water flow better, especially at the very early stage of the flooding event.

Classical approaches for flood prediction apply numerical methods for the solution of partial differential equations that capture the physics of inundation processes (e.g., the 2D Shallow Water equations). However, traditional inundation models are still unable to satisfy the requirements of many relevant applications, including early-warning systems, high-resolution (or large spatial domain) simulations, and robust inference over distributions of inputs (e.g., rainfall events). Machine learning (ML) approaches are a promising alternative to physics-based models due to their ability to efficiently capture correlations between relevant inputs and outputs in a data-driven fashion. In particular, once trained, ML models can be tested/deployed much more efficiently than classical approaches. Yet, few ML-based solutions for spatio-temporal flood prediction have been developed, and their reliability/accuracy is poorly understood. In this paper, we propose FloodGNN-GRU, a spatio-temporal flood prediction model that combines a graph neural network (GNN) and a gated recurrent unit (GRU) architecture. Compared to existing approaches, FloodGNN-GRU (i) employs a graph-based model (GNN); (ii) operates on both spatial and temporal dimensions; and (iii) processes the water flow velocities as vector features, instead of scalar features. We evaluate FloodGNN-GRU using a LISFLOOD-FP simulation of Hurricane Harvey (2017) in Houston, Texas. Our results, based on several metrics, show that FloodGNN-GRU outperforms several data-driven alternatives in terms of accuracy. Moreover, our approach can be trained 100x faster and tested 1000x faster than the time required to run a comparable simulation. These findings illustrate the potential of ML-based methods to efficiently emulate physics-based inundation models, especially for short-term predictions.

Large infrastructure networks (e.g. for transportation and power distribution) require constant monitoring for failures, congestion, and other adversarial events. However, assigning a sensor to every link in the network is often infeasible due to placement and maintenance costs. Instead, sensors can be placed only on a few key links, and machine learning algorithms can be leveraged for the inference of missing measurements (e.g. traffic counts, power flows) across the network. This paper investigates the sensor placement problem for networks. We first formalize the problem under a flow conservation assumption and show that it is NP-hard to place a fixed set of sensors optimally. Next, we propose an efficient and adaptive greedy heuristic for sensor placement that scales to large networks. Our experiments, using datasets from real-world application domains, show that the proposed approach enables more accurate inference than existing alternatives from the literature. We demonstrate that considering even imperfect or incomplete ground-truth estimates can vastly improve the prediction error, especially when a small number of sensors is available.

Machine Learning (ML) has emerged as a promising alternative to numerical methods for physics-based simulation due to its flexibility and efficiency. Flood modeling is a key case study for ML-based simulation due to its relevance as a tool for supporting preventive and emergency measures to mitigate flood risks. However, the complexity of the topography or domain (ground elevation) and the sparsity of the time-evolving precipitations (external forcing) can be challenging for most existing ML approaches for simulating flooding processes in space and time. Another critical challenge is incorporating physics domain knowledge (hydraulics) into these data-driven models. This paper addresses these challenges by introducing a hydraulics-informed graph neural network for flood simulation. Given a (geographical) region and precipitation data, our model predicts water depths in an auto-regressive fashion. We propose a message-passing framework inspired by the conservation of momentum and mass expressed in the shallow-water equations, which describe the physical process of a flooding event. Empirical results on a dataset covering 9 regions and 7 historical precipitation events demonstrate that our model outperforms the best baseline, and can capture the propagation of water flow more effectively, especially at the very early stage of the flooding event when the amount of water in the domain is scarce. Differently from some of the most recent methods for ML-based simulation, which tend to work well only when the domain is a smooth surface (e.g., flat terrain), we show that our solution achieves accurate results for real ground elevation data.

All-optical circuit-switching (OCS) technology is the key to design energy-efficient and high-performance datacenter network (DCN) architectures for the future. However, existing round-robin based OCS cores perform poorly under realistic workloads having high traffic skewness and high volume of inter-rack traffic. To address this issue, we propose a novel DCN architecture OSSV: a combination of OCS-based core (between ToR switches) and OCS-based reconfigurable edge (between servers and ToR switches). On one hand, the OCS core is traffic agnostic and realizes reconfigurably non-blocking ToR-level connectivity. On the other hand, OCS-based edge reconfigures itself to reshape the incoming traffic in order to jointly minimize traffic skewness and inter-rack traffic volume. Our novel optimization framework can obtain the right balance between these intertwined objectives. Our extensive simulations and testbed evaluation show that OSSV can achieve high performance under diverse DCN traffic while consuming low power and incurring low cost.

All-optical circuit-switched (OCS) core is the holy grail for the future generation datacenter architectures. However, such proposals consist of a common operational abstraction termed as round-robin circuit scheduling, which heavily suffers from a) high traffic skewness, and b) high volume of inter-rack traffic. To address this issue, we propose a novel architecture: round-robin OCS-core equipped with OCS-based reconfigurable edge for joint Skewness and Inter-rack traffic Volume (SV) minimization. Our architecture significantly improves the performance of all-optical cores, making it very close to a non-blocking network.

The Transportation Cybersecurity Center for Advanced Research and Education (CYBER-CARE) is a US Department of Transportation (USDOT) Tier-1 University Transportation Center (UTC) funded in 2023. CYBER-CARE primarily focuses on the USDOT statutory research priority area of “Reducing Transportation Cybersecurity Risks.” CYBER-CARE aims to establish a fundamental knowledge basis and explore advanced theory to mitigate the impacts of large-scale cyberattacks on transportation infrastructure and connected and automated vehicle (CAV) systems. The research projects at CYBER-CARE will develop conceptual frameworks, construct comprehensive datasets, explore novel analytical approaches, support the implementation of public policies and infrastructure investments, and build a high-quality industry workforce through education. All CYBER-CARE research projects can be organized into four thrusts: CAV cybersecurity, transportation data security, advanced traffic management system (ATMS) cybersecurity, and next-generation transportation cybersecurity systems. In addition, CYBER-CARE will accelerate industry collaborations, foster new technologies, and provide professionals with the skills and opportunities needed to become successful leaders in their fields. Notably, as CYBER-CARE will prioritize engagement with underrepresented minorities, these communities stand to benefit from professional development training in transportation cybersecurity.

Explaining the decisions made by machine learning models for high-stakes applications is critical for increasing transparency and guiding improvements to these decisions. This is particularly true in the case of models for graphs, where decisions often depend on complex patterns combining rich structural and attribute data. While recent work has focused on designing so-called post-hoc explainers, the broader question of what constitutes a good explanation remains open. One intuitive property is that explanations should be sufficiently informative to reproduce the predictions given the data. In other words, a good explainer can be repurposed as a predictor. Post-hoc explainers do not achieve this goal as their explanations are highly dependent on fixed model parameters (e.g., learned GNN weights). To address this challenge, we propose RAGE (Robust Ante-hoc Graph Explainer), a novel and flexible ante-hoc explainer designed to discover explanations for graph neural networks using bilevel optimization, with a focus on the chemical domain. RAGE can effectively identify molecular substructures that contain the full information needed for prediction while enabling users to rank these explanations in terms of relevance. Our experiments on various molecular classification tasks show that RAGE explanations are better than existing post-hoc and ante-hoc approaches.

Ensuring fairness in machine learning algorithms is a challenging and essential task. We consider the problem of clustering a set of points while satisfying fairness constraints. While there have been several attempts to capture group fairness in the $k$-clustering problem, fairness at an individual level is relatively less explored. We introduce a new notion of individual fairness in $k$-clustering based on features not necessarily used for clustering. We show that this problem is NP-hard and does not admit a constant factor approximation. Therefore, we design a randomized algorithm that guarantees approximation both in terms of minimizing the clustering distance objective and individual fairness under natural restrictions on the distance metric and fairness constraints. Finally, our experimental results against six competing baselines validate that our algorithm produces individually fairer clusters than the fairest baseline by 12.5% on average while also being less costly in terms of the clustering objective than the best baseline by 34.5% on average.

Link prediction, which consists of predicting edges based on graph features, is a fundamental task in many graph applications. As for several related problems, Graph Neural Networks (GNNs), which are based on an attribute-centric message-passing paradigm, have become the predominant framework for link prediction. GNNs have consistently outperformed traditional topology-based heuristics, but what contributes to their performance? Are there simpler approaches that achieve comparable or better results? To answer these questions, we first identify important limitations in how GNN-based link prediction methods handle the intrinsic class imbalance of the problem -- due to the graph sparsity -- in their training and evaluation. Moreover, we propose Gelato, a novel topology-centric framework that applies a topological heuristic to a graph enhanced by attribute information via graph learning. Our model is trained end-to-end with an N-pair loss on an unbiased training set to address class imbalance. Experiments show that Gelato is 145% more accurate, trains 11 times faster, infers 6,000 times faster, and has less than half of the trainable parameters compared to state-of-the-art GNNs for link prediction.

This paper addresses the problem of learning fair Graph Neural Networks (GNNs) under missing protected attributes. GNNs have achieved state-of-the-art results in many relevant tasks where decisions might disproportionately impact specific communities. However, existing work on fair GNNs assumes that either protected attributes are fully-observed or that the missing data imputation is fair. In practice, biases in the imputation will be propagated to the model outcomes, leading them to overestimate the fairness of their predictions. We address this challenge by proposing Better Fair than Sorry (BFtS), a fair missing data imputation model for protected attributes used by fair GNNs. The key design principle behind BFtS is that imputations should approximate the worst-case scenario for the fair GNN -- i.e. when optimizing fairness is the hardest. We implement this idea using a 3-player adversarial scheme where two adversaries collaborate against the fair GNN. Experiments using synthetic and real datasets show that BFtS often achieves a better fairness $\times$ accuracy trade-off than existing alternatives.

Flow graphs capture the directed flow of a quantity of interest (e.g., water, power, vehicles) being transported through an underlying network. Modeling and generating realistic flow graphs is key in many applications in infrastructure design, transportation, and biomedical and social sciences. However, they pose a great challenge to existing generative models due to a complex dynamics that is often governed by domain-specific physical laws or patterns. We introduce FlowGEN, an implicit generative model for flow graphs, that learns how to jointly generate graph topologies and flows with diverse dynamics directly from data using a novel (flow) graph neural network. Experiments show that our approach is able to effectively reproduce relevant local and global properties of flow graphs, including flow conservation, cyclic trends, and congestion around hotspots.

Online social networks have become major battlegrounds for political campaigns, viral marketing, and the dissemination of news. As a consequence, “bad actors” are increasingly exploiting these platforms, which is a key challenge for their administrators, businesses and society in general. The spread of fake news is a classical example of the abuse of social networks by these bad actors. While some have advocated for stricter policies to control the spread of misinformation in social networks, this often happens in detriment of their democratic and organic structure. In this paper, we aim to limit the influence of a target group in a social network via the removal of a few users/links. We formulate the influence limitation problem in a data-driven fashion, by taking into account past propagation traces. More specifically, our algorithms find critical edges to be removed in order to decrease the influence of a target group based on past data. The idea is to control the diffusion processes while minimizing the amount of disturbance in the network structure. Moreover, we consider two types of constraints over edge removals, a budget constraint and also a, more general, set of matroid constraints. These problems lead to interesting challenges in terms of algorithm design. For instance, we are able to show that influence limitation is APX-hard and propose deterministic and probabilistic approximation algorithms for the budgeted and the matroid version of the problem, respectively. Experiments show that the proposed approaches outperform several baselines.

Flow graphs capture the directed flow of a quantity of interest (e.g., water, power, vehicles) being transported through an underlying network. Modeling and generating realistic flow graphs is key in many applications in infrastructure design, transportation, and biomedical and social sciences. However, they pose a great challenge to existing generative models due to a complex dynamics that is often governed by domain-specific physical laws or patterns. We introduce FlowGEN, an implicit generative model for flow graphs, that learns how to jointly generate graph topologies and flows with diverse dynamics directly from data using a novel (flow) graph neural network. Experiments show that our approach is able to effectively reproduce relevant local and global properties of flow graphs, including flow conservation, cyclic trends, and congestion around hotspots.