Search

Fully inductive knowledge graph models can be trained on multiple domains and subsequently perform zero-shot knowledge graph completion (KGC) in new unseen domains. This is an important capability towards the goal of having foundation models for knowledge graphs. In this work, we introduce a more expressive and capable fully inductive model, dubbed TRIX, which not only yields strictly more expressive triplet embeddings (head entity, relation, tail entity) compared to state-of-the-art methods, but also introduces a new capability: directly handling both entity and relation prediction tasks in inductive settings. Empirically, we show that TRIX outperforms the state-of-the-art fully inductive models in zero-shot entity and relation predictions in new domains, and outperforms large-context LLMs in out-of-domain predictions. The source code is available at https://github.com/yuchengz99/TRIX.

While machine learning on graphs has demonstrated promise in drug design and molecular property prediction, significant benchmarking challenges hinder its further progress and relevance. Current benchmarking practices often lack focus on transformative, real-world applications, favoring narrow domains like two-dimensional molecular graphs over broader, impactful areas such as combinatorial optimization, relational databases, or chip design. Additionally, many benchmark datasets poorly represent the underlying data, leading to inadequate abstractions and misaligned use cases. Fragmented evaluations and an excessive focus on accuracy further exacerbate these issues, incentivizing overfitting rather than fostering generalizable insights. These limitations have prevented the development of truly useful graph foundation models. This position paper calls for a paradigm shift toward more meaningful benchmarks, rigorous evaluation protocols, and stronger collaboration with domain experts to drive impactful and reliable advances in graph learning research, unlocking the potential of graph learning.

Knowledge Graph Foundation Models (KGFMs) are at the frontier for deep learning on knowledge graphs (KGs), as they can generalize to completely novel knowledge graphs with different relational vocabularies. Despite their empirical success, our theoretical understanding of KGFMs remains very limited. In this paper, we conduct a rigorous study of the expressive power of KGFMs. Specifically, we show that the expressive power of KGFMs directly depends on the motifs that are used to learn the relation representations. We then observe that the most typical motifs used in the existing literature are binary, as the representations are learned based on how pairs of relations interact, which limits the model's expressiveness. As part of our study, we design more expressive KGFMs using richer motifs, which necessitate learning relation representations based on, e.g., how triples of relations interact with each other. Finally, we empirically validate our theoretical findings, showing that the use of richer motifs results in better performance on a wide range of datasets drawn from different domains.

Generating novel crystalline materials has potential to lead to advancements in fields such as electronics, energy storage, and catalysis. The defining characteristic of crystals is their symmetry, which plays a central role in determining their physical properties. However, existing crystal generation methods either fail to generate materials that display the symmetries of real-world crystals, or simply replicate the symmetry information from examples in a database. To address this limitation, we propose SymmCD, a novel diffusion-based generative model that explicitly incorporates crystallographic symmetry into the generative process. We decompose crystals into two components and learn their joint distribution through diffusion: 1) the asymmetric unit, the smallest subset of the crystal which can generate the whole crystal through symmetry transformations, and; 2) the symmetry transformations needed to be applied to each atom in the asymmetric unit. We also use a novel and interpretable representation for these transformations, enabling generalization across different crystallographic symmetry groups. We showcase the competitive performance of SymmCD on a subset of the Materials Project, obtaining diverse and valid crystals with realistic symmetries and predicted properties.

Semileptonic decays of $D$ and $D_s$ mesons into orbitally and radially excited strange and light mesons are studied in detail within the framework of the relativistic quark model based on the quasipotential approach and quantum chromodynamics. The hadronic matrix elements of the weak current between meson states are calculated with the consistent account of relativistic effects including contributions of the intermediate negative energy states and boosts of the meson wave functions from the rest to moving reference frame. The invariant form factors that parameterize these matrix elements are obtained as the overlap integrals of the initial and final meson wave functions. Their dependence on the square of the transferred momentum $q^2$ is explicitly determined within the whole accessible kinematic range. A convenient analytical approximation for numerical values of form factors is given. These form factors and helicity formalism are employed for the calculation of the differential and total semileptonic decay rates of charm mesons into excited strange and light mesons. Different asymmetry and polarization parameters are also evaluated. The obtained results are compared with other theoretical calculations and available experimental data. Reasonable agreement with experimentally measured semileptonic decay branching fractions and upper bounds is obtained., Comment: 30 pages, 4 figures. arXiv admin note: substantial text overlap with arXiv:1911.08209

Unmanned Aerial Vehicles (UAVs) are increasingly essential in various fields such as surveillance, reconnaissance, and telecommunications. This study aims to develop a learning algorithm for the path planning of UAV wireless communication relays, which can reduce storage requirements and accelerate Deep Reinforcement Learning (DRL) convergence. Assuming the system possesses terrain maps of the area and can estimate user locations using localization algorithms or direct GPS reporting, it can input these parameters into the learning algorithms to achieve optimized path planning performance. However, higher resolution terrain maps are necessary to extract topological information such as terrain height, object distances, and signal blockages. This requirement increases memory and storage demands on UAVs while also lengthening convergence times in DRL algorithms. Similarly, defining the telecommunication coverage map in UAV wireless communication relays using these terrain maps and user position estimations demands higher memory and storage utilization for the learning path planning algorithms. Our approach reduces path planning training time by applying a dimensionality reduction technique based on Principal Component Analysis (PCA), sample combination, Prioritized Experience Replay (PER), and the combination of Mean Squared Error (MSE) and Mean Absolute Error (MAE) loss calculations in the coverage map estimates, thereby enhancing a Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm. The proposed solution reduces the convergence episodes needed for basic training by approximately four times compared to the traditional TD3., Comment: This paper was accepted in https://camad2024.ieee-camad.org/ conference but it is not available from the conference yet

The study of cosmic rays in the energy range from 1 to 1000 PeV is crucial for understanding their origins and propagation paths. As part of this research, a new SPHERE-3 installation is being developed, featuring enhanced light sensitivity and optical resolution, based on the experience gained with the balloon-borne SPHERE-2 installation. This report describes a computational complex designed for simulating the formation of Cherenkov light on the detector grid of the SPHERE-3 telescope., Comment: Published as a conference paper at X International Conference on Mathematial Modeling. 4 pages, 1 figure

A new Cherenkov telescope of the SPHERE type is under development. Its main goal is to promote the solution of the problem of the primary cosmic ray mass composition at ultra high energies (1--100 PeV) using a newly developed technique of the primary mass assignment to EAS event on event-by-event basis. The telescope will carry out measurements of both the Cherenkov light reflected from the snow surface as well as the direct one. Sensitivity of the direct Cherenkov images' shapes to the primary mass is demonstrated., Comment: Published as a conference paper at 21st Lomonosov Conference on Elementary Particle Physics. 7 pages, 5 figures

Recent equivariant models have shown significant progress in not just chemical property prediction, but as surrogates for dynamical simulations of molecules and materials. Many of the top performing models in this category are built within the framework of tensor products, which preserves equivariance by restricting interactions and transformations to those that are allowed by symmetry selection rules. Despite being a core part of the modeling process, there has not yet been much attention into understanding what information persists in these equivariant representations, and their general behavior outside of benchmark metrics. In this work, we report on a set of experiments using a simple equivariant graph convolution model on the QM9 dataset, focusing on correlating quantitative performance with the resulting molecular graph embeddings. Our key finding is that, for a scalar prediction task, many of the irreducible representations are simply ignored during training -- specifically those pertaining to vector ($l=1$) and tensor quantities ($l=2$) -- an issue that does not necessarily make itself evident in the test metric. We empirically show that removing some unused orders of spherical harmonics improves model performance, correlating with improved latent space structure. We provide a number of recommendations for future experiments to try and improve efficiency and utilization of equivariant features based on these observations., Comment: Accepted in the Findings track at the AI4Mat workshop, NeurIPS 2024 Vancouver, BC

A new SPHERE-3 telescope is being developed for cosmic rays spectrum and mass composition studies in the 5--1000 PeV energy range. Registration of extensive air showers using reflected Cherenkov light method applied in the SPHERE detector series requires a good trigger system for accurate separation of events from the background produced by starlight and airglow photons reflected from the snow. Here we present the results of convolutional networks application for the classification of images obtained from Monte Carlo simulation of the detector. Detector response simulations include photons tracing through the optical system, silicon photomultiplier operation and electronics response and digitization process. The results are compared to the SPHERE-2 trigger system performance., Comment: 7 pages, 5 figures Published as a conference paper at DLCP2024, June 19-21, 2024, Moscow, Russia. https://dlcp2024.sinp.msu.ru Submitted to Moscow University Physics Bulletin

Postsecondary education and middle-skills occupational training are viewed as important paths to higher-paying jobs and careers. Lifelong learning pathways geared toward working learners aged 25 and older also seem essential for career advancement and professional growth in the current job market. However, many learners face financial and other barriers to accessing and completing occupational training. Social Finance, Inc., a national nonprofit that creates impact-first investments, launched the UP Fund, a $50 million fund that aims to improve economic mobility by expanding access to job training programs to underserved learners and learners from low-income backgrounds. The UP Fund enables learners to enroll in short-term, sector-based occupational training programs with access to career and supportive services without paying up-front tuition costs. Learners enter into "income share agreements" (ISAs) that are intended to repay tuition costs. This is achieved by learners committing to repay a fixed percentage or amount of their income over a set term and up to a capped amount. However, this repayment obligation is contingent upon the learner's earnings meeting a minimum income threshold. The UP Fund's Career Impact Bond (CIB) model focuses on providing ISAs to learners from low-income backgrounds who might not otherwise have access to the training programs. The CIB model also emphasizes the importance of comprehensive support services to help learners achieve career success. MDRC launched a multisite, multiyear study of the UP Fund's CIB model in 2022. The study includes four training providers that enroll learners financed by the UP Fund across multiple industries. This brief provides an overview of the study, details of the UP Fund's CIB model, and early implementation findings. Initial results suggest that individuals who enrolled in a training program supported by the UP Fund learned helpful skills to find jobs in their chosen careers.

Traditional query answering over knowledge graphs -- or broadly over relational data -- is one of the most fundamental problems in data management. Motivated by the incompleteness of modern knowledge graphs, a new setup for query answering has emerged, where the goal is to predict answers that do not necessarily appear in the knowledge graph, but are present in its completion. In this work, we propose AnyCQ, a graph neural network model that can classify answers to any conjunctive query on any knowledge graph, following training. At the core of our framework lies a graph neural network model trained using a reinforcement learning objective to answer Boolean queries. Our approach and problem setup differ from existing query answering studies in multiple dimensions. First, we focus on the problem of query answer classification: given a query and a set of possible answers, classify these proposals as true or false relative to the complete knowledge graph. Second, we study the problem of query answer retrieval: given a query, retrieve an answer to the query relative to the complete knowledge graph or decide that no correct solutions exist. Trained on simple, small instances, AnyCQ can generalize to large queries of arbitrary structure, reliably classifying and retrieving answers to samples where existing approaches fail, which is empirically validated on new and challenging benchmarks. Furthermore, we demonstrate that our AnyCQ models effectively transfer to out-of-distribution knowledge graphs, when equipped with a relevant link predictor, highlighting their potential to serve as a general engine for query answering.

We investigate the asymptotic behavior, in the long time limit, of the random homology associated to realizations of stochastic diffusion processes on a compact Riemannian manifold. In particular a rigidity result is established: if the rate is quadratic, then the manifold is a locally trivial fiber bundle over a flat torus, with fibers being minimal in a weighted sense (that is, regarding the manifold as a metric measured space, with the invariant probability being the weight measure). Surprisingly, this entails that at least for some classes of manifolds, the homology of non-reversible processes relaxes to equilibrium slower than its reversible counterpart (as opposed to the respective empirical measure, which relaxes faster)., Comment: 20 pages

Multi-relational temporal graphs are powerful tools for modeling real-world data, capturing the evolving and interconnected nature of entities over time. Recently, many novel models are proposed for ML on such graphs intensifying the need for robust evaluation and standardized benchmark datasets. However, the availability of such resources remains scarce and evaluation faces added complexity due to reproducibility issues in experimental protocols. To address these challenges, we introduce Temporal Graph Benchmark 2.0 (TGB 2.0), a novel benchmarking framework tailored for evaluating methods for predicting future links on Temporal Knowledge Graphs and Temporal Heterogeneous Graphs with a focus on large-scale datasets, extending the Temporal Graph Benchmark. TGB 2.0 facilitates comprehensive evaluations by presenting eight novel datasets spanning five domains with up to 53 million edges. TGB 2.0 datasets are significantly larger than existing datasets in terms of number of nodes, edges, or timestamps. In addition, TGB 2.0 provides a reproducible and realistic evaluation pipeline for multi-relational temporal graphs. Through extensive experimentation, we observe that 1) leveraging edge-type information is crucial to obtain high performance, 2) simple heuristic baselines are often competitive with more complex methods, 3) most methods fail to run on our largest datasets, highlighting the need for research on more scalable methods., Comment: 29 pages, 8 figures, 11 tables, accepted at NeurIPS 2024 Track on Datasets and Benchmarks

One fundamental challenge in graph machine learning is generalizing to new graphs. Many existing methods following the inductive setup can generalize to test graphs with new structures, but assuming the feature and label spaces remain the same as the training ones. This paper introduces a fully-inductive setup, where models should perform inference on arbitrary test graphs with new structures, feature and label spaces. We propose GraphAny as the first attempt at this challenging setup. GraphAny models inference on a new graph as an analytical solution to a LinearGNN, which can be naturally applied to graphs with any feature and label spaces. To further build a stronger model with learning capacity, we fuse multiple LinearGNN predictions with learned inductive attention scores. Specifically, the attention module is carefully parameterized as a function of the entropy-normalized distance features between pairs of LinearGNN predictions to ensure generalization to new graphs. Empirically, GraphAny trained on a single Wisconsin dataset with only 120 labeled nodes can generalize to 30 new graphs with an average accuracy of 67.26\%, surpassing not only all inductive baselines, but also strong transductive methods trained separately on each of the 30 test graphs., Comment: ICLR2025

We continue investigation of asymptotics of quantum differential equation for Fano manifolds, with a special regard to Gamma conjecture I and its underlying Conjecture $\mathcal{O}$. We introduce the A-model conifold value, a symplectic invariant of a Fano manifold, and propose modifications for Gamma conjecture I based on this new definition. We discuss an interplay of birational transformations with an extension of Gamma conjecture I over the K\"ahler moduli space. These heuristics are applied to rigorously identify the principal asymptotic class in the case of $\mathbb{P}^1$-bundles $X_n=\mathbb{P}_{\mathbb{P}^{n}}(\mathcal{O}\oplus\mathcal{O}(n))$. We observe, in particular, that for $X_n$ of dimension at least four, the Conjecture $\mathcal{O}$ holds just for even values of $n$, and in these cases we falsify the original non-modified Gamma conjecture I., Comment: 49 pages. The title is changed and the abstract is rewritten. Substantial revision on Section 5 is made, where the notion of A-model conifold value is introduced for any Fano manifolds and Gamma conjecture I is well modified now. Comments are welcome

The floorplanning of Systems-on-a-Chip (SoCs) and of chip sub-systems is a crucial step in the physical design flow as it determines the optimal shapes and locations of the blocks that make up the system. Simulated Annealing (SA) has been the method of choice for tackling classical floorplanning problems where the objective is to minimize wire-length and the total placement area. The goal in industry-relevant floorplanning problems, however, is not only to minimize area and wire-length, but to do that while respecting hard placement constraints that specify the general area and/or the specific locations for the placement of some blocks. We show that simply incorporating these constraints into the SA objective function leads to sub-optimal, and often illegal, solutions. We propose the Constraints-Aware Simulated Annealing (CA-SA) method and show that it strongly outperforms vanilla SA in floorplanning problems with hard placement constraints. We developed a new floorplanning tool on top of CA-SA: PARSAC (Parallel Simulated Annealing with Constraints). PARSAC is an efficient, easy-to-use, and massively parallel floorplanner. Unlike current SA-based or learning-based floorplanning tools that cannot effectively incorporate hard placement-constraints, PARSAC can quickly construct the Pareto-optimal legal solutions front for constrained floorplanning problems. PARSAC also outperforms traditional SA on legacy floorplanning benchmarks. PARSAC is available as an open-source repository for researchers to replicate and build on our result., Comment: 9 pages, 7 figures

Floorplanning for systems-on-a-chip (SoCs) and its sub-systems is a crucial and non-trivial step of the physical design flow. It represents a difficult combinatorial optimization problem. A typical large scale SoC with 120 partitions generates a search-space of nearly 10E250. As novel machine learning (ML) approaches emerge to tackle such problems, there is a growing need for a modern benchmark that comprises a large training dataset and performance metrics that better reflect real-world constraints and objectives compared to existing benchmarks. To address this need, we present FloorSet -- two comprehensive datasets of synthetic fixed-outline floorplan layouts that reflect the distribution of real SoCs. Each dataset has 1M training samples and 100 test samples where each sample is a synthetic floor-plan. FloorSet-Prime comprises fully-abutted rectilinear partitions and near-optimal wire-length. A simplified dataset that reflects early design phases, FloorSet-Lite comprises rectangular partitions, with under 5 percent white-space and near-optimal wire-length. Both datasets define hard constraints seen in modern design flows such as shape constraints, edge-affinity, grouping constraints, and pre-placement constraints. FloorSet is intended to spur fundamental research on large-scale constrained optimization problems. Crucially, FloorSet alleviates the core issue of reproducibility in modern ML driven solutions to such problems. FloorSet is available as an open-source repository for the research community., Comment: 10 pages, 11 figures

Complex logical query answering (CLQA) in knowledge graphs (KGs) goes beyond simple KG completion and aims at answering compositional queries comprised of multiple projections and logical operations. Existing CLQA methods that learn parameters bound to certain entity or relation vocabularies can only be applied to the graph they are trained on which requires substantial training time before being deployed on a new graph. Here we present UltraQuery, the first foundation model for inductive reasoning that can zero-shot answer logical queries on any KG. The core idea of UltraQuery is to derive both projections and logical operations as vocabulary-independent functions which generalize to new entities and relations in any KG. With the projection operation initialized from a pre-trained inductive KG reasoning model, UltraQuery can solve CLQA on any KG after finetuning on a single dataset. Experimenting on 23 datasets, UltraQuery in the zero-shot inference mode shows competitive or better query answering performance than best available baselines and sets a new state of the art on 15 of them., Comment: NeurIPS 2024

Graph Foundation Models (GFMs) are emerging as a significant research topic in the graph domain, aiming to develop graph models trained on extensive and diverse data to enhance their applicability across various tasks and domains. Developing GFMs presents unique challenges over traditional Graph Neural Networks (GNNs), which are typically trained from scratch for specific tasks on particular datasets. The primary challenge in constructing GFMs lies in effectively leveraging vast and diverse graph data to achieve positive transfer. Drawing inspiration from existing foundation models in the CV and NLP domains, we propose a novel perspective for the GFM development by advocating for a ``graph vocabulary'', in which the basic transferable units underlying graphs encode the invariance on graphs. We ground the graph vocabulary construction from essential aspects including network analysis, expressiveness, and stability. Such a vocabulary perspective can potentially advance the future GFM design in line with the neural scaling laws. All relevant resources with GFM design can be found here., Comment: 23 pages, 2 figures

Masses of the ground, orbitally and radially excited states of the asymmetric fully heavy tetraquarks, composed of charm (c) and bottom (b) quarks and antiquarks are calculated in the relativistic diquark-antidiquark picture. The relativistic quark model based on the quasipotential approach and quantum chromodynamics is used to construct the quasipotentials of the quark-quark and diquark-antidiquark interactions. These quasipotentials consist of the short-range one-gluon exchange and long-distance linear confinement interactions. Relativistic effects are consistently taken into account. A tetraquark is considered as a bound state of a diquark and an antidiquark which are treated as a spatially extended colored objects and interact as a whole. It is shown that most of the investigated tetraquarks states (including all ground states) lie above the fall-apart strong decay thresholds into a meson pair. As a result they can be observed as wide resonances. Nevertheless, several orbitally excited states lie slightly above or even below these fall-apart thresholds, thus they could be narrow states., Comment: 25 pages, 1 figure; version to be published in Eur. Phys. J. A

Compositional generalization, the ability of an agent to generalize to unseen combinations of latent factors, is easy for humans but hard for deep neural networks. A line of research in cognitive science has hypothesized a process, ``iterated learning,'' to help explain how human language developed this ability; the theory rests on simultaneous pressures towards compressibility (when an ignorant agent learns from an informed one) and expressivity (when it uses the representation for downstream tasks). Inspired by this process, we propose to improve the compositional generalization of deep networks by using iterated learning on models with simplicial embeddings, which can approximately discretize representations. This approach is further motivated by an analysis of compositionality based on Kolmogorov complexity. We show that this combination of changes improves compositional generalization over other approaches, demonstrating these improvements both on vision tasks with well-understood latent factors and on real molecular graph prediction tasks where the latent structure is unknown.

Artificial intelligence and machine learning have shown great promise in their ability to accelerate novel materials discovery. As researchers and domain scientists seek to unify and consolidate chemical knowledge, the case for models with potential to generalize across different tasks within materials science - so-called "foundation models" - grows with ambitions. This manuscript reviews our recent progress with development of Open MatSci ML Toolkit, and details experiments that lay the groundwork for foundation model research and development with our framework. First, we describe and characterize a new pretraining task that uses synthetic data generated from symmetry operations, and reveal complex training dynamics at large scales. Using the pretrained model, we discuss a number of use cases relevant to foundation model development: semantic architecture of datasets, and fine-tuning for property prediction and classification. Our key results show that for simple applications, pretraining appears to provide worse modeling performance than training models from random initialization. However, for more complex instances, such as when a model is required to learn across multiple datasets and types of targets simultaneously, the inductive bias from pretraining provides significantly better performance. This insight will hopefully inform subsequent efforts into creating foundation models for materials science applications., Comment: 17 pages, 7 figures, 1 table. Accepted paper/presentation at the AI4Science workshop at Super Computing '23

Foundation models in language and vision have the ability to run inference on any textual and visual inputs thanks to the transferable representations such as a vocabulary of tokens in language. Knowledge graphs (KGs) have different entity and relation vocabularies that generally do not overlap. The key challenge of designing foundation models on KGs is to learn such transferable representations that enable inference on any graph with arbitrary entity and relation vocabularies. In this work, we make a step towards such foundation models and present ULTRA, an approach for learning universal and transferable graph representations. ULTRA builds relational representations as a function conditioned on their interactions. Such a conditioning strategy allows a pre-trained ULTRA model to inductively generalize to any unseen KG with any relation vocabulary and to be fine-tuned on any graph. Conducting link prediction experiments on 57 different KGs, we find that the zero-shot inductive inference performance of a single pre-trained ULTRA model on unseen graphs of various sizes is often on par or better than strong baselines trained on specific graphs. Fine-tuning further boosts the performance., Comment: ICLR 2024

We propose MatSci ML, a novel benchmark for modeling MATerials SCIence using Machine Learning (MatSci ML) methods focused on solid-state materials with periodic crystal structures. Applying machine learning methods to solid-state materials is a nascent field with substantial fragmentation largely driven by the great variety of datasets used to develop machine learning models. This fragmentation makes comparing the performance and generalizability of different methods difficult, thereby hindering overall research progress in the field. Building on top of open-source datasets, including large-scale datasets like the OpenCatalyst, OQMD, NOMAD, the Carolina Materials Database, and Materials Project, the MatSci ML benchmark provides a diverse set of materials systems and properties data for model training and evaluation, including simulated energies, atomic forces, material bandgaps, as well as classification data for crystal symmetries via space groups. The diversity of properties in MatSci ML makes the implementation and evaluation of multi-task learning algorithms for solid-state materials possible, while the diversity of datasets facilitates the development of new, more generalized algorithms and methods across multiple datasets. In the multi-dataset learning setting, MatSci ML enables researchers to combine observations from multiple datasets to perform joint prediction of common properties, such as energy and forces. Using MatSci ML, we evaluate the performance of different graph neural networks and equivariant point cloud networks on several benchmark tasks spanning single task, multitask, and multi-data learning scenarios. Our open-source code is available at https://github.com/IntelLabs/matsciml.

Unmanned Aerial Vehicles (UAVs) are a disruptive technology that is transforming a range of industries. Because they operate in the sky, UAVs are able to take advantage of strong Line-of-Sight (LoS) channels for radio propagation, allowing them to communicate over much larger distances than equivalent hardware located at ground level. This has attracted the attention of organisations such as the Irish Defence Forces (DF), with whom we are developing a UAV-based radio relay system as part of the MISTRAL project. This relay system will support digital Very High Frequency (VHF) band communication between ground personnel, while they are deployed on missions. In this paper we report on the initial set of experimental measurements which were carried out to verify the feasibility of VHF signal relaying via UAV. In our experiments, a UAV carrying a lightweight Software-Defined Radio (SDR) receiver is positioned at a height of 500 meters above ground, while two 5W transmitters travel in vehicles on the ground. The SDR receiver measures the received signal power, while the Global Positioning System (GPS) coordinates of the vehicles are logged. This is combined to measure the signal pathloss over distance. Our results show that the signal is received successfully at distances of over 50 kilometers away. While the signals still appear to suffer from a degree of obstacle blockage and multipath effects, these communication ranges are a substantial improvement over the ground communication baseline, and validate the use of UAVs to support wide area emergency communication., Comment: Pre-print of paper presented at the Workshop on Integrating UAVs into 5G and Beyond at IEEE International Conference on Communications 2023