Searcharxiv⌕ Search

arXiv subjects

Astrit Tola

Publications and source records attributed to Astrit Tola.

8 recordsLinked to original sources

A Topological Encoder Decoder Framework for Temporal Graph Learning

Most temporal graph learning methods reduce future prediction to discriminative inference over past interactions, focusing on edges or node labels for a largely persistent set of nodes. This view breaks down when new nodes and edges appear, since the future graph becomes a new object with changing size, composition, and structure. We address this gap by framing temporal graph prediction as an inverse topology problem. Instead of predicting edges directly, we first predict a multiscale topological descriptor of the future graph and then reconstruct a plausible future snapshot that realizes this descriptor under inductive constraints. This approach makes global structure and node churn explicit prediction targets and produces forecasted graphs that downstream tasks can evaluate without retraining. Across 14 temporal graph datasets, we evaluate our method, TOPOGED, on node, link, and graph property prediction and compare it against state-of-the-art temporal graph models. TOPOGED significantly improves node-level forecasting accuracy over the strongest baseline, with a macro average of 0.49 versus 0.05. It also outperforms baselines in 60% of graph-structure metric evaluations and substantially increases macro-average edge prediction metrics, from near-zero to 0.12. Our results show that topology-guided graph forecasting can predict inductive future snapshots whose structure supports multiple downstream evaluations.

cs.AI↗

TopoFormer: Topology Meets Attention for Graph Learning

We introduce Topoformer, a lightweight and scalable framework for graph representation learning that encodes topological structure into attention-friendly sequences. At the core of our method is Topo-Scan, a novel module that decomposes a graph into a short, ordered sequence of topological tokens by slicing over node or edge filtrations. These sequences capture multi-scale structural patterns, from local motifs to global organization, and are processed by a Transformer to produce expressive graph-level embeddings. Unlike traditional persistent homology pipelines, Topo-Scan is parallelizable, avoids costly diagram computations, and integrates seamlessly with standard deep learning architectures. We provide theoretical guarantees on the stability of our topological encodings and demonstrate state-of-the-art performance across graph classification and molecular property prediction benchmarks. Our results show that Topoformer matches or exceeds strong GNN and topology-based baselines while offering predictable and efficient compute. This work opens a new path for parallelizable and unifying approaches to graph representation learning that integrate topological inductive biases into attention frameworks.

cs.LG↗

TopER: Topological Embeddings in Graph Representation Learning

Graph embeddings play a critical role in graph representation learning, allowing machine learning models to explore and interpret graph-structured data. However, existing methods often rely on opaque, high-dimensional embeddings, limiting interpretability and practical visualization. In this work, we introduce Topological Evolution Rate (TopER), a novel, low-dimensional embedding approach grounded in topological data analysis. TopER simplifies a key topological approach, Persistent Homology, by calculating the evolution rate of graph substructures, resulting in intuitive and interpretable visualizations of graph data. This approach not only enhances the exploration of graph datasets but also delivers competitive performance in graph clustering and classification tasks. Our TopER-based models achieve or surpass state-of-the-art results across molecular, biological, and social network datasets in tasks such as classification, clustering, and visualization.

cs.LG↗

SCNode: Spatial and Contextual Coordinates for Graph Representation Learning

Effective node representation lies at the heart of Graph Neural Networks (GNNs), as it directly impacts their ability to perform downstream tasks such as node classification and link prediction. Most existing GNNs, particularly message passing graph neural networks, rely on neighborhood aggregation to iteratively compute node embeddings. While powerful, this paradigm suffers from well-known limitations of oversquashing, oversmoothing, and underreaching that degrade representation quality. More critically, MPGNNs often assume homophily, where connected nodes share similar features or labels, leading to poor generalization in heterophilic graphs where this assumption breaks down. To address these challenges, we propose \textit{SCNode}, a \textit{Spatial-Contextual Node Embedding} framework designed to perform consistently well in both homophilic and heterophilic settings. SCNode integrates spatial and contextual information, yielding node embeddings that are not only more discriminative but also structurally aware. Our approach introduces new homophily matrices for understanding class interactions and tendencies. Extensive experiments on benchmark datasets show that SCNode achieves superior performance over conventional GNN models, demonstrating its robustness and adaptability in diverse graph structures.

cs.LG↗

PROXI: Challenging the GNNs for Link Prediction

Over the past decade, Graph Neural Networks (GNNs) have transformed graph representation learning. In the widely adopted message-passing GNN framework, nodes refine their representations by aggregating information from neighboring nodes iteratively. While GNNs excel in various domains, recent theoretical studies have raised concerns about their capabilities. GNNs aim to address various graph-related tasks by utilizing such node representations, however, this one-size-fits-all approach proves suboptimal for diverse tasks. Motivated by these observations, we conduct empirical tests to compare the performance of current GNN models with more conventional and direct methods in link prediction tasks. Introducing our model, PROXI, which leverages proximity information of node pairs in both graph and attribute spaces, we find that standard machine learning (ML) models perform competitively, even outperforming cutting-edge GNN models when applied to these proximity metrics derived from node neighborhoods and attributes. This holds true across both homophilic and heterophilic networks, as well as small and large benchmark datasets, including those from the Open Graph Benchmark (OGB). Moreover, we show that augmenting traditional GNNs with PROXI significantly boosts their link prediction performance. Our empirical findings corroborate the previously mentioned theoretical observations and imply that there exists ample room for enhancement in current GNN models to reach their potential.

cs.LG↗

Strange Non-Chaotic Attractors with Unpredictable Trajectories

Continuous and discrete time systems possessing strange non-chaotic attractors are under investigation. It is demonstrated that unpredictable trajectories exist in the dynamics. A recent numerical technique, the sequential test, is utilized to show the presence of unpredictability.

nlin.CD↗

Unpredictable Strings

A novel notion of unpredictable strings is revealed and utilized to define deterministic unpredictable sequences on a finite number of symbols. We prove the first law of large strings for random processes in discrete time, which confirms that there exists the uncountable set of unpredictable realizations. The hypothesis on the second law of large strings is formulated, which is relative to the Bernoulli theorem. Theoretical and numerical backgrounds for the laws are provided.

math.DS↗

The Sequential Test for Chaos

This paper reveals a novel numerical method, the sequential test, which approves chaos through sequences of numbers observations. The method alights alongside the Lyapunov exponent and bifurcation diagram test. Explicitly elucidation of the method application for both continuous and discrete systemswas given affiliated with the corresponding algorithms. The theoretical results are exemplified on systems satisfying different types of definitions of chaos or numerical methods. The results are supplemented with illustrative graphics.

math.GM↗