Šarūnas Girdzijauskas

Yifei Jin, Marios Daoutis, Sarunas Girdzijauskas et al.

Cellular coverage quality estimation has been a critical task for self-organized networks. In real-world scenarios, deep-learning-powered coverage quality estimation methods cannot scale up to large areas due to little ground truth can be provided during network design & optimization. In addition they fall short in produce expressive embeddings to adequately capture the variations of the cells' configurations. To deal with this challenge, we formulate the task in a graph representation and so that we can apply state-of-the-art graph neural networks, that show exemplary performance. We propose a novel training framework that can both produce quality cell configuration embeddings for estimating multiple KPIs, while we show it is capable of generalising to large (area-wide) scenarios given very few labeled cells. We show that our framework yields comparable accuracy with models that have been trained using massively labeled samples.

Yifei Jin, Marios Daoutis, Sarunas Girdzijauskas et al.

Accurate routing network status estimation is a key component in Software Defined Networking. However, existing deep-learning-based methods for modeling network routing are not able to extrapolate towards unseen feature distributions. Nor are they able to handle scaled and drifted network attributes in test sets that include open-world inputs. To deal with these challenges, we propose a novel approach for modeling network routing, using Graph Neural Networks. Our method can also be used for network-latency estimation. Supported by a domain-knowledge-assisted graph formulation, our model shares a stable performance across different network sizes and configurations of routing networks, while at the same time being able to extrapolate towards unseen sizes, configurations, and user behavior. We show that our model outperforms most conventional deep-learning-based models, in terms of prediction accuracy, computational resources, inference speed, as well as ability to generalize towards open-world input.

Edvin Listo Zec, Ebba Ekblom, Martin Willbo et al.

We study the problem of training personalized deep learning models in a decentralized peer-to-peer setting, focusing on the setting where data distributions differ between the clients and where different clients have different local learning tasks. We study both covariate and label shift, and our contribution is an algorithm which for each client finds beneficial collaborations based on a similarity estimate for the local task. Our method does not rely on hyperparameters which are hard to estimate, such as the number of client clusters, but rather continuously adapts to the network topology using soft cluster assignment based on a novel adaptive gossip algorithm. We test the proposed method in various settings where data is not independent and identically distributed among the clients. The experimental evaluation shows that the proposed method performs better than previous state-of-the-art algorithms for this problem setting, and handles situations well where previous methods fail.

Martin Isaksson, Edvin Listo Zec, Rickard Cöster et al.

Federated Learning (FL) is a promising framework for distributed learning when data is private and sensitive. However, the state-of-the-art solutions in this framework are not optimal when data is heterogeneous and non-Independent and Identically Distributed (non-IID). We propose a practical and robust approach to personalization in FL that adjusts to heterogeneous and non-IID data by balancing exploration and exploitation of several global models. To achieve our aim of personalization, we use a Mixture of Experts (MoE) that learns to group clients that are similar to each other, while using the global models more efficiently. We show that our approach achieves an accuracy up to 29.78 % and up to 4.38 % better compared to a local model in a pathological non-IID setting, even though we tune our approach in the IID setting.

Remi Bourgerie, Sarunas Girdzijauskas, Viktoria Fodor

Deep Graph Neural Networks (GNNs) are essential for capturing complex dependencies in graph-structured data. However, scaling GNNs to depth remains challenging, as stacking layers leads to representation collapse and diminishing sensitivity due to repeated aggregation. While Neural Sheaf Diffusion (NSD) provides strong theoretical guarantees against such collapse, these guarantees do not translate to practice: as depth increases, the disagreement signal of the sheaf Laplacian vanishes, limiting the contribution of deeper layers. We identify mechanisms that hinder NSD effectiveness at depth and propose \emph{Deep Neural Sheaf Diffusion} (DNSD), which replaces the sheaf Laplacian with a sheaf adjacency operator to maintain informative signals across layers. This is complemented by normalization, odd nonlinearities, and gating. To provide a principled explanation of the expected performance improvement, we contrast sheaf diffusion to graph attention mechanisms, highlighting that DNSD replaces scalar attention scores with matrix-valued edge functions and normalizes node representations rather than attention scores. We demonstrate empirically that DNSD effectively utilizes deep aggregation in graph tasks, outperforming GNN and NSD baselines with up to 30pp accuracy on synthetic long-range datasets, and consistently outperforming them on real-world benchmarks. These results position sheaf-based architectures as a promising building block for graph foundation models by supporting effective deep architectures.

Ivan Kralj, Lodovico Giaretta, Gordan Ježić et al.

Spatio-Temporal Graph Neural Networks (ST-GNNs) are well-suited for processing high-frequency data streams from geographically distributed sensors in smart mobility systems. However, their deployment at the edge across distributed compute nodes (cloudlets) createssubstantial communication overhead due to repeated transmission of overlapping node features between neighbouring cloudlets. To address this, we propose an adaptive pruning algorithm that dynamically filters redundant neighbour features while preserving the most informative spatial context for prediction. The algorithm adjusts pruning rates based on recent model performance, allowing each cloudlet to focus on regions experiencing traffic changes without compromising accuracy. Additionally, we introduce the Sudden Event Prediction Accuracy (SEPA), a novel event-focused metric designed to measure responsiveness to traffic slowdowns and recoveries, which are often missed by standard error metrics. We evaluate our approach in an online semi-decentralized setting with traditional FL, server-free FL, and Gossip Learning on two large-scale traffic datasets, PeMS-BAY and PeMSD7-M, across short-, mid-, and long-term prediction horizons. Experiments show that, in contrast to standard metrics, SEPA exposes the true value of spatial connectivity in predicting dynamic and irregular traffic. Our adaptive pruning algorithm maintains prediction accuracy while significantly lowering communication cost in all online semi-decentralized settings, demonstrating that communication can be reduced without compromising responsiveness to critical traffic events.

Ayush K. Varshney, Konstantinos Vandikas, Šarūnas Girdzijauskas et al.

Deploying deep neural networks on resource-constrained 6G edge devices demands aggressive compression with minimal accuracy loss. Quantization-Aware Training (QAT) has emerged as a leading compression approach; however, existing mixed-precision methods typically operate at coarse layer- or channel-level granularity. These methods often rely on heuristic or search-based bit-allocation strategies, which may overlook fine-grained variability at the neuron level. We propose Neuron-Level Mixed-Precision QAT (NMP-QAT), where each neuron independently learns its own discrete precision during training. Starting from low-bit precision, NMP-QAT expands bit-width only when training signals demand it, via differentiable surrogates and straight-through estimators, while preserving a fully discrete inference graph. This adaptability extends to both weights and activations, reducing memory movement. Evaluated on telecom and non-telecom datasets across MLP and tabular foundation model architectures, NMP-QAT achieves superior compression-accuracy trade-offs over mixed-precision QAT baselines, making it well-suited for Green AI deployments at the network edge.

Ankit Grover, Lodovico Giaretta, Rémi Bourgerie et al.

The integration of Graph Neural Networks (GNNs) with Large Language Models (LLMs) has emerged as a promising paradigm for Graph Question Answering (GraphQA). However, effective methods for encoding complex structural information into the LLM's latent space remain an open challenge. Current state-of-the-art architectures, such as G-Retriever, typically rely on standard GNNs and aggressive mean pooling to compress entire graph substructures into a single token, creating a severe information bottleneck. This work mitigates this bottleneck by investigating two orthogonal strategies: (1) increasing the bandwidth of the graph-to-LLM interface via multi-token pooling, and (2) enhancing the semantic quality of the graph encoder via global attention mechanisms. We evaluate a suite of hierarchical pruning and clustering-based pooling operators including Top-k, SAGPool, DiffPool, MinCutPool, and Virtual Node Pooling (VNPool) to project graph data into multiple learnable tokens. Empirically, we demonstrate that while pooling introduces significant instability during soft prompt tuning, the application of Low-Rank Adaptation (LoRA) effectively stabilizes specific hierarchical projections (notably VNPool and pruning methods), though dense clustering operators remain challenging. This stabilization allows compressed representations to rival full-graph baselines (achieving ~73% Hit@1 on WebQSP). Conceptually, we demonstrate that a Graph Transformer with VNPool implementation functions structurally as a single-layer Perceiver IO encoder. Finally, we adapt the FandE (Features and Edges) Score to the generative GraphQA domain. Our analysis reveals that the GraphQA benchmark suffers from representational saturation, where target answers are often highly correlated with isolated node features. The implementation is available at https://github.com/Agrover112/G-Retriever/tree/all_good/

Adam Orucu, Marcus Medhage, Farnaz Moradi et al.

The telecommunications industry is experiencing rapid growth in adopting deep learning for critical tasks such as traffic prediction, signal strength prediction, and quality of service optimisation. However, designing neural network architectures for these applications remains challenging and time-consuming, particularly when targeting compact models suitable for resource-constrained network environments. Therefore, there is a need for automating the model design process to create high-performing models efficiently. This paper introduces TabGNS (Tabular Gated Neuron Selection), a novel gradient-based Neural Architecture Search (NAS) method specifically tailored for tabular data in telecommunications networks. We evaluate TabGNS across multiple telecommunications and generic tabular datasets, demonstrating improvements in prediction performance while reducing the architecture size by 51-82% and reducing the search time by up to 36x compared to state-of-the-art tabular NAS methods. Integrating TabGNS into the model lifecycle management enables automated design of neural networks throughout the lifecycle, accelerating deployment of ML solutions in telecommunications networks.

Edvin Listo Zec, Tom Hagander, Eric Ihre-Thomason et al.

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.

Ahmed E. Samy, Zekarias T. Kefatoa, Sarunas Girdzijauskasa

Self-supervised graph representation learning (SSGRL) is a representation learning paradigm used to reduce or avoid manual labeling. An essential part of SSGRL is graph data augmentation. Existing methods usually rely on heuristics commonly identified through trial and error and are effective only within some application domains. Also, it is not clear why one heuristic is better than another. Moreover, recent studies have argued against some techniques (e.g., dropout: that can change the properties of molecular graphs or destroy relevant signals for graph-based document classification tasks). In this study, we propose a novel data-driven SSGRL approach that automatically learns a suitable graph augmentation from the signal encoded in the graph (i.e., the nodes' predictive feature and topological information). We propose two complementary approaches that produce learnable feature and topological augmentations. The former learns multi-view augmentation of node features, and the latter learns a high-order view of the topology. Moreover, the augmentations are jointly learned with the representation. Our approach is general that it can be applied to homogeneous and heterogeneous graphs. We perform extensive experiments on node classification (using nine homogeneous and heterogeneous datasets) and graph property prediction (using another eight datasets). The results show that the proposed method matches or outperforms the SOTA SSGRL baselines and performs similarly to semi-supervised methods. The anonymised source code is available at https://github.com/AhmedESamy/dsgrl/

Ayush K. Varshney, Šarūnas Girdzijauskas, Konstantinos Vandikas et al.

Learning rate scheduling plays a critical role in the optimization of deep neural networks, directly influencing convergence speed, stability, and generalization. While existing schedulers such as cosine annealing, cyclical learning rates, and warm restarts have shown promise, they often rely on fixed or periodic triggers that are agnostic to the training dynamics, such as stagnation or convergence behavior. In this work, we propose a simple yet effective strategy, which we call Stochastic Gradient Descent with Escalating Restarts (SGD-ER). It adaptively increases the learning rate upon convergence. Our method monitors training progress and triggers restarts when stagnation is detected, linearly escalating the learning rate to escape sharp local minima and explore flatter regions of the loss landscape. We evaluate SGD-ER across CIFAR-10, CIFAR-100, and TinyImageNet on a range of architectures including ResNet-18/34/50, VGG-16, and DenseNet-101. Compared to standard schedulers, SGD-ER improves test accuracy by 0.5-4.5%, demonstrating the benefit of convergence-aware escalating restarts for better local optima.

Ahmed E. Samy, Zekarias T. Kefato, Sarunas Girdzijauskas

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 (https://github.com/AhmedESamy/LEAP/)

Stefanos Antaris, Dimitrios Rafailidis, Sarunas Girdzijauskas

In this study, we present a meta-learning model to adapt the predictions of the network's capacity between viewers who participate in a live video streaming event. We propose the MELANIE model, where an event is formulated as a Markov Decision Process, performing meta-learning on reinforcement learning tasks. By considering a new event as a task, we design an actor-critic learning scheme to compute the optimal policy on estimating the viewers' high-bandwidth connections. To ensure fast adaptation to new connections or changes among viewers during an event, we implement a prioritized replay memory buffer based on the Kullback-Leibler divergence of the reward/throughput of the viewers' connections. Moreover, we adopt a model-agnostic meta-learning framework to generate a global model from past events. As viewers scarcely participate in several events, the challenge resides on how to account for the low structural similarity of different events. To combat this issue, we design a graph signature buffer to calculate the structural similarities of several streaming events and adjust the training of the global model accordingly. We evaluate the proposed model on the link weight prediction task on three real-world datasets of live video streaming events. Our experiments demonstrate the effectiveness of our proposed model, with an average relative gain of 25% against state-of-the-art strategies. For reproduction purposes, our evaluation datasets and implementation are publicly available at https://github.com/stefanosantaris/melanie

Zekarias T. Kefato, Sarunas Girdzijauskas, Hannes Stärk

Self-supervised Learning (SSL) aims at learning representations of objects without relying on manual labeling. Recently, a number of SSL methods for graph representation learning have achieved performance comparable to SOTA semi-supervised GNNs. A Siamese network, which relies on data augmentation, is the popular architecture used in these methods. However, these methods rely on heuristically crafted data augmentation techniques. Furthermore, they use either contrastive terms or other tricks (e.g., asymmetry) to avoid trivial solutions that can occur in Siamese networks. In this study, we propose, GraphSurgeon, a novel SSL method for GNNs with the following features. First, instead of heuristics we propose a learnable data augmentation method that is jointly learned with the embeddings by leveraging the inherent signal encoded in the graph. In addition, we take advantage of the flexibility of the learnable data augmentation and introduce a new strategy that augments in the embedding space, called post augmentation. This strategy has a significantly lower memory overhead and run-time cost. Second, as it is difficult to sample truly contrastive terms, we avoid explicit negative sampling. Third, instead of relying on engineering tricks, we use a scalable constrained optimization objective motivated by Laplacian Eigenmaps to avoid trivial solutions. To validate the practical use of GraphSurgeon, we perform empirical evaluation using 14 public datasets across a number of domains and ranging from small to large scale graphs with hundreds of millions of edges. Our finding shows that GraphSurgeon is comparable to six SOTA semi-supervised and on par with five SOTA self-supervised baselines in node classification tasks. The source code is available at https://github.com/zekarias-tilahun/graph-surgeon.

Zekarias T. Kefato, Sarunas Girdzijauskas

Real world data is mostly unlabeled or only few instances are labeled. Manually labeling data is a very expensive and daunting task. This calls for unsupervised learning techniques that are powerful enough to achieve comparable results as semi-supervised/supervised techniques. Contrastive self-supervised learning has emerged as a powerful direction, in some cases outperforming supervised techniques. In this study, we propose, SelfGNN, a novel contrastive self-supervised graph neural network (GNN) without relying on explicit contrastive terms. We leverage Batch Normalization, which introduces implicit contrastive terms, without sacrificing performance. Furthermore, as data augmentation is key in contrastive learning, we introduce four feature augmentation (FA) techniques for graphs. Though graph topological augmentation (TA) is commonly used, our empirical findings show that FA perform as good as TA. Moreover, FA incurs no computational overhead, unlike TA, which often has O(N^3) time complexity, N-number of nodes. Our empirical evaluation on seven publicly available real-world data shows that, SelfGNN is powerful and leads to a performance comparable with SOTA supervised GNNs and always better than SOTA semi-supervised and unsupervised GNNs. The source code is available at https://github.com/zekarias-tilahun/SelfGNN.

Ivan Kralj, Lodovico Giaretta, Gordan Ježić et al.

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 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 that arise from the large receptive field of GNNs, leading to substantial data transfers and increased computation of partial embeddings.

Filip Cornell, Yifei Jin, Jussi Karlgren et al.

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 negative candidates. 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 can work extremely well, and that they match advanced neural approaches. Even when a large portion of true candidates for a property are missed, the estimation 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, filtered 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.

Stefanos Antaris, Dimitrios Rafailidis, Sarunas Girdzijauskas

In this paper we present a deep graph reinforcement learning model to predict and improve the user experience during a live video streaming event, orchestrated by an agent/tracker. We first formulate the user experience prediction problem as a classification task, accounting for the fact that most of the viewers at the beginning of an event have poor quality of experience due to low-bandwidth connections and limited interactions with the tracker. In our model we consider different factors that influence the quality of user experience and train the proposed model on diverse state-action transitions when viewers interact with the tracker. In addition, provided that past events have various user experience characteristics we follow a gradient boosting strategy to compute a global model that learns from different events. Our experiments with three real-world datasets of live video streaming events demonstrate the superiority of the proposed model against several baseline strategies. Moreover, as the majority of the viewers at the beginning of an event has poor experience, we show that our model can significantly increase the number of viewers with high quality experience by at least 75% over the first streaming minutes. Our evaluation datasets and implementation are publicly available at https://publicresearch.z13.web.core.windows.net

Daniel Garcia Bernal, Lodovico Giaretta, Sarunas Girdzijauskas et al.

Large scale contextual representation models have significantly advanced NLP in recent years, understanding the semantics of text to a degree never seen before. However, they need to process large amounts of data to achieve high-quality results. Joining and accessing all these data from multiple sources can be extremely challenging due to privacy and regulatory reasons. Federated Learning can solve these limitations by training models in a distributed fashion, taking advantage of the hardware of the devices that generate the data. We show the viability of training NLP models, specifically Word2Vec, with the Federated Learning protocol. In particular, we focus on a scenario in which a small number of organizations each hold a relatively large corpus. The results show that neither the quality of the results nor the convergence time in Federated Word2Vec deteriorates as compared to centralised Word2Vec.

Stefanos Antaris, Dimitrios Rafailidis, Sarunas Girdzijauskas

In this study, we present a dynamic graph representation learning model on weighted graphs to accurately predict the network capacity of connections between viewers in a live video streaming event. We propose EGAD, a neural network architecture to capture the graph evolution by introducing a self-attention mechanism on the weights between consecutive graph convolutional networks. In addition, we account for the fact that neural architectures require a huge amount of parameters to train, thus increasing the online inference latency and negatively influencing the user experience in a live video streaming event. To address the problem of the high online inference of a vast number of parameters, we propose a knowledge distillation strategy. In particular, we design a distillation loss function, aiming to first pretrain a teacher model on offline data, and then transfer the knowledge from the teacher to a smaller student model with less parameters. We evaluate our proposed model on the link prediction task on three real-world datasets, generated by live video streaming events. The events lasted 80 minutes and each viewer exploited the distribution solution provided by the company Hive Streaming AB. The experiments demonstrate the effectiveness of the proposed model in terms of link prediction accuracy and number of required parameters, when evaluated against state-of-the-art approaches. In addition, we study the distillation performance of the proposed model in terms of compression ratio for different distillation strategies, where we show that the proposed model can achieve a compression ratio up to 15:100, preserving high link prediction accuracy. For reproduction purposes, our evaluation datasets and implementation are publicly available at https://stefanosantaris.github.io/EGAD.

Zekarias T. Kefato, Sarunas Girdzijauskas, Nasrullah Sheikh et al.

In recommender systems (RSs), predicting the next item that a user interacts with is critical for user retention. While the last decade has seen an explosion of RSs aimed at identifying relevant items that match user preferences, there is still a range of aspects that could be considered to further improve their performance. For example, often RSs are centered around the user, who is modeled using her recent sequence of activities. Recent studies, however, have shown the effectiveness of modeling the mutual interactions between users and items using separate user and item embeddings. Building on the success of these studies, we propose a novel method called DeePRed that addresses some of their limitations. In particular, we avoid recursive and costly interactions between consecutive short-term embeddings by using long-term (stationary) embeddings as a proxy. This enable us to train DeePRed using simple mini-batches without the overhead of specialized mini-batches proposed in previous studies. Moreover, DeePRed's effectiveness comes from the aforementioned design and a multi-way attention mechanism that inspects user-item compatibility. Experiments show that DeePRed outperforms the best state-of-the-art approach by at least 14% on next item prediction task, while gaining more than an order of magnitude speedup over the best performing baselines. Although this study is mainly concerned with temporal interaction networks, we also show the power and flexibility of DeePRed by adapting it to the case of static interaction networks, substituting the short- and long-term aspects with local and global ones.

Simone Zamboni, Zekarias Tilahun Kefato, Sarunas Girdzijauskas et al.

Predicting the future trajectories of pedestrians is a challenging problem that has a range of application, from crowd surveillance to autonomous driving. In literature, methods to approach pedestrian trajectory prediction have evolved, transitioning from physics-based models to data-driven models based on recurrent neural networks. In this work, we propose a new approach to pedestrian trajectory prediction, with the introduction of a novel 2D convolutional model. This new model outperforms recurrent models, and it achieves state-of-the-art results on the ETH and TrajNet datasets. We also present an effective system to represent pedestrian positions and powerful data augmentation techniques, such as the addition of Gaussian noise and the use of random rotations, which can be applied to any model. As an additional exploratory analysis, we present experimental results on the inclusion of occupancy methods to model social information, which empirically show that these methods are ineffective in capturing social interaction.

Zekarias T. Kefato, Sarunas Girdzijauskas

Graph representation learning (GRL) is a powerful technique for learning low-dimensional vector representation of high-dimensional and often sparse graphs. Most studies explore the structure and metadata associated with the graph using random walks and employ an unsupervised or semi-supervised learning schemes. Learning in these methods is context-free, resulting in only a single representation per node. Recently studies have argued on the adequacy of a single representation and proposed context-sensitive approaches, which are capable of extracting multiple node representations for different contexts. This proved to be highly effective in applications such as link prediction and ranking. However, most of these methods rely on additional textual features that require complex and expensive RNNs or CNNs to capture high-level features or rely on a community detection algorithm to identify multiple contexts of a node. In this study we show that in-order to extract high-quality context-sensitive node representations it is not needed to rely on supplementary node features, nor to employ computationally heavy and complex models. We propose GOAT, a context-sensitive algorithm inspired by gossip communication and a mutual attention mechanism simply over the structure of the graph. We show the efficacy of GOAT using 6 real-world datasets on link prediction and node clustering tasks and compare it against 12 popular and state-of-the-art (SOTA) baselines. GOAT consistently outperforms them and achieves up to 12% and 19% gain over the best performing methods on link prediction and clustering tasks, respectively.

Zekarias T. Kefato, Sarunas Girdzijauskas

Network representation learning (NRL) is a powerful technique for learning low-dimensional vector representation of high-dimensional and sparse graphs. Most studies explore the structure and metadata associated with the graph using random walks and employ an unsupervised or semi-supervised learning schemes. Learning in these methods is context-free, because only a single representation per node is learned. Recently studies have argued on the sufficiency of a single representation and proposed a context-sensitive approach that proved to be highly effective in applications such as link prediction and ranking. However, most of these methods rely on additional textual features that require RNNs or CNNs to capture high-level features or rely on a community detection algorithm to identify multiple contexts of a node. In this study, without requiring additional features nor a community detection algorithm, we propose a novel context-sensitive algorithm called GAP that learns to attend on different parts of a node's neighborhood using attentive pooling networks. We show the efficacy of GAP using three real-world datasets on link prediction and node clustering tasks and compare it against 10 popular and state-of-the-art (SOTA) baselines. GAP consistently outperforms them and achieves up to ~9% and ~20% gain over the best performing methods on link prediction and clustering tasks, respectively.