Oleg Platonov

Oleg Platonov, Denis Kuznedelev, Michael Diskin, Artem Babenko, Liudmila Prokhorenkova

Node classification is a classical graph machine learning task on which Graph Neural Networks (GNNs) have recently achieved strong results. However, it is often believed that standard GNNs only work well for homophilous graphs, i.e., graphs where edges tend to connect nodes of the same class. Graphs without this property are called heterophilous, and it is typically assumed that specialized methods are required to achieve strong performance on such graphs. In this work, we challenge this assumption. First, we show that the standard datasets used for evaluating heterophily-specific models have serious drawbacks, making results obtained by using them unreliable. The most significant of these drawbacks is the presence of a large number of duplicate nodes in the datasets Squirrel and Chameleon, which leads to train-test data leakage. We show that removing duplicate nodes strongly affects GNN performance on these datasets. Then, we propose a set of heterophilous graphs of varying properties that we believe can serve as a better benchmark for evaluating the performance of GNNs under heterophily. We show that standard GNNs achieve strong results on these heterophilous graphs, almost always outperforming specialized models. Our datasets and the code for reproducing our experiments are available at https://github.com/yandex-research/heterophilous-graphs

Oleg Platonov, Denis Kuznedelev, Artem Babenko, Liudmila Prokhorenkova

Homophily is a graph property describing the tendency of edges to connect similar nodes; the opposite is called heterophily. It is often believed that heterophilous graphs are challenging for standard message-passing graph neural networks (GNNs), and much effort has been put into developing efficient methods for this setting. However, there is no universally agreed-upon measure of homophily in the literature. In this work, we show that commonly used homophily measures have critical drawbacks preventing the comparison of homophily levels across different datasets. For this, we formalize desirable properties for a proper homophily measure and verify which measures satisfy which properties. In particular, we show that a measure that we call adjusted homophily satisfies more desirable properties than other popular homophily measures while being rarely used in graph learning literature. Then, we go beyond the homophily-heterophily dichotomy and propose a new characteristic allowing one to further distinguish different sorts of heterophily. The proposed label informativeness (LI) characterizes how much information a neighbor's label provides about a node's label. We analyze LI via the same theoretical framework and show that it is comparable across different datasets. We also observe empirically that LI better agrees with GNN performance compared to homophily measures, which confirms that it is a useful characteristic of the graph structure.

Dmitry Eremeev, Gleb Bazhenov, Oleg Platonov, Artem Babenko, Liudmila Prokhorenkova

While foundation models have revolutionized fields such as natural language processing and computer vision, their potential in graph machine learning remains largely unexplored. One of the key challenges in designing graph foundation models (GFMs) is handling diverse node features that can vary across different graph datasets. While many works on GFMs have focused exclusively on text-attributed graphs, the problem of handling arbitrary features of other types in GFMs has not been fully addressed. However, this problem is not unique to the graph domain, as it also arises in the field of machine learning for tabular data. In this work, motivated by the recent success of tabular foundation models (TFMs) like TabPFNv2 and LimiX, we propose G2T-FM, a simple framework that allows tabular foundation models to be applied to graph node-level tasks. Specifically, G2T-FM augments the original node features with neighborhood feature aggregation, adds structural embeddings, and then applies a TFM to the constructed node representations. Even in the in-context learning setting, our model achieves strong results when combined with a strong TFM, outperforming both prior GFMs and well-tuned GNNs trained from scratch. Moreover, after finetuning, G2T-FM consistently surpasses well-tuned GNN baselines, often by a significant margin. In summary, our paper reveals the potential of a previously overlooked direction: utilizing tabular foundation models for graph machine learning tasks.

Oleg Platonov, Denis Kuznedelev, Artem Babenko, Liudmila Prokhorenkova

A. Dvigun, O. Datsii, N. Levchenko, G. Shyshkanova, O. Platonov, V. Zalizniuk

Introduction. It has been stated that the strategic guideline for the transformation of Ukraine's economy towards climate neutrality is to increase the ambition to reduce the carbon trace of multimodal transportation through the use of an arsenal of effective regulatory and fiscal measures.Problem Statement. The challenge is to find ways to increase the ambition to reduce the carbon footprint of multimodal transportation in the context of transforming Ukraine's economy to climate neutrality.Purpose. The purpose of this research is to developscenarios for reducing the carbon footprint of multimodal transportation to ensure the environment preservation and well-being of the future generations.Materials and Methods. The following methods have been used: economic and mathematical modelling on the basis of correlation-regressive analysis, for determining the dependence of greenhouse gas emissions on fuel consumption in the transport sector, cargo and passenger turnover, GDP, the number of permanent population; decoupling analysis, for estimating the impact of transport on the environment; comparative analysis, for studying the elasticity of greenhouse gas emissions with GDP changes in countries with the length of transport routes close to Ukraine; strategic analysis, for assessing the realism of NDCs2; scenario forecasting, for identifying alternative scenarios of changes in greenhouse gas emissions, provided that the traffic flows increase.Results. For the first time, a mechanism for paying a carbon tax on fuel, which ensures a fair attitude towards environmental pollutants and a reasonable formation of the investment potential of the Decarbonisation Fund. has been proposed.Conclusions. Having chosen the transformation of Ukraine's economy towards climate neutrality as a strategic guideline, the government shall decide to increase the ambition to reduce the carbon footprint of multimodal transportation through the use of an arsenal of effective fiscal measures.