Search

Unsupervised representation learning techniques are commonly employed to analyze high-dimensional or unstructured data. In some cases, users may have prior knowledge of the topology of the data, such as a known cluster structure or the fact that it follows a tree- or graph-based structure. However, generic methods for ensuring this inherent structure is evident in low-dimensional representations are lacking and it is unknown how imposing topological constraints affects downstream learning tasks. To fill this gap, we propose topological regularization - a generic approach based on algebraic topology to incorporate topological prior knowledge into low-dimensional representations. We introduce a class of topological loss functions and demonstrate that optimizing an embedding loss together with one of these loss functions as a regularizer results in embeddings that consider not only local proximities but also the desired topological structure. We provide a self-contained introduction to essential concepts in algebraic topology and offer intuitive guidance for designing topological loss functions suitable for a variety of data shapes, such as clusters, cycles, or bifurcations. We empirically assess the efficiency, robustness, and versatility of the proposed method when combined with linear and non-linear dimensionality reduction techniques, as well as graph embedding methods.

Recommender systems often face congestion, characterized by an uneven distribution in the frequency of item recommendations. The presence of congestion in recommendations is especially problematic in domains where users or items have limited availability. For example, recommending one vacancy to many job seekers results in frustration of job seekers and job market inefficiency. We propose a novel in-processing approach to job recommendation called ReCon, accounting for the congestion problem. Our approach is to use an optimal transport component to ensure a more equal spread of vacancies over job seekers, combined with a job recommendation model in a multi-objective optimization problem. Moreover, we propose a scalable solution so that ReCon is applicable to large-scale datasets. We evaluated our approach on several real-world job market datasets. The evaluation results show that ReCon has good performance on both congestion-related (e.g., Congestion, Coverage, and Gini Index) and desirability (e.g., NDCG, Recall, and Hit Rate) measures. In most cases, ReCon is Pareto optimal for some selections of hyper-parameters in comparison to the baselines.

Dynamic Link Prediction (DLP) addresses the prediction of future links in evolving networks. However, accurately portraying the performance of DLP algorithms poses challenges that might impede progress in the field. Importantly, common evaluation pipelines usually calculate ranking or binary classification metrics, where the scores of observed interactions (positives) are compared with those of randomly generated ones (negatives). However, a single metric is not sufficient to fully capture the differences between DLP algorithms, and is prone to overly optimistic performance evaluation. Instead, an in-depth evaluation should reflect performance variations across different nodes, edges, and time segments. In this work, we contribute tools to perform such a comprehensive evaluation. (1) We propose Birth–Death diagrams, a simple but powerful visualization technique that illustrates the effect of time-based train–test splitting on the difficulty of DLP on a given dataset. (2) We describe an exhaustive taxonomy of negative sampling methods that can be used at evaluation time. (3) We carry out an empirical study of the effect of the different negative sampling strategies. Our comparison between heuristics and state-of-the-art memory-based methods on various real-world datasets confirms a strong effect of using different negative sampling strategies on the test area under the curve (AUC). Moreover, we conduct a visual exploration of the prediction, with additional insights on which different types of errors are prominent over time.

Representing the nodes of continuous-time temporal graphs in a low-dimensional latent space has wide-ranging applications, from prediction to visualization. Yet, analyzing continuous-time relational data with timestamped interactions introduces unique challenges due to its sparsity. Merely embedding nodes as trajectories in the latent space overlooks this sparsity. However, a natural way to account for this sparsity is to model the uncertainty around the latent positions. In this paper, we propose TGNE (Temporal Gaussian Network Embedding), an innovative method that bridges two distinct strands of literature: the statistical analysis of networks via Latent Space Models (LSM) and temporal graph machine learning. TGNE embeds nodes as piece-wise linear trajectories of Gaussian distributions in the latent space, capturing both structural information and uncertainty around the trajectories. We evaluate TGNE’s effectiveness in reconstructing the original graph and modelling uncertainty. The results demonstrate that TGNE generates time-varying embedding locations that can accurately reconstruct missing parts of the network based on observed ones. Furthermore, the uncertainty estimates align experimentally with the time-varying degree distribution in the network, providing valuable insights into the temporal dynamics of the graph. To facilitate reproducibility, we provide an open-source implementation of TGNE at https://github.com/aida-ugent/tgne/.

In this paper we introduce EvalNE, a Python toolbox for network embedding evaluation. The main goal of EvalNE is to aid researchers and practitioners in performing consistent and reproducible evaluations of new embedding methods, replicating existing evaluations, and conducting benchmark studies. The toolbox can evaluate models independently of their programming language and assess the quality of learned representations through data visualization and downstream tasks such as sign and link prediction, network reconstruction, and node multi-label classification. EvalNE streamlines evaluation by providing automation and abstraction for tasks such as hyperparameter tuning and model validation, node and edge sampling, node-pair embedding computation, and performance reporting. As a command line tool, configuration files describe the evaluation setup and guarantee consistency and reproducibility. As an API, EvalNE provides the building blocks to design any evaluation setup while minimizing the risk of evaluation errors.

The democratization of AI tools for content generation, combined with unrestricted access to mass media for all (e.g. through microblogging and social media), makes it increasingly hard for people to distinguish fact from fiction. This raises the question of how individual opinions evolve in such a networked environment without grounding in a known reality. The dominant approach to studying this problem uses simple models from the social sciences on how individuals change their opinions when exposed to their social neighborhood, and applies them on large social networks. We propose a novel model that incorporates two known social phenomena: (i) Biased Assimilation: the tendency of individuals to adopt other opinions if they are similar to their own; (ii) Backfire Effect: the fact that an opposite opinion may further entrench people in their stances, making their opinions more extreme instead of moderating them. To the best of our knowledge, this is the first DeGroot-type opinion formation model that captures the Backfire Effect. A thorough theoretical and empirical analysis of the proposed model reveals intuitive conditions for polarization and consensus to exist, as well as the properties of the resulting opinions.

Abstract We present the open-source implementation of the first fully automatic and comprehensive DJ system, able to generate seamless music mixes using songs from a given library much like a human DJ does. The proposed system is built on top of several enhanced music information retrieval (MIR) techniques, such as for beat tracking, downbeat tracking, and structural segmentation, to obtain an understanding of the musical structure. Leveraging the understanding of the music tracks offered by these state-of-the-art MIR techniques, the proposed system surpasses existing automatic DJ systems both in accuracy and completeness. To the best of our knowledge, it is the first fully integrated solution that takes all basic DJing best practices into account, from beat and downbeat matching to identification of suitable cue points, determining a suitable cross-fade profile and compiling an interesting playlist that trades off innovation with continuity. To make this possible, we focused on one specific sub-genre of electronic dance music, namely Drum and Bass. This allowed us to exploit genre-specific properties, resulting in a more robust performance and tailored mixing behavior. Evaluation on a corpus of 160 Drum and Bass songs and an additional hold-out set of 220 songs shows that the used MIR algorithms can annotate 91% of the songs with fully correct annotations (tempo, beats, downbeats, and structure for cue points). On these songs, the proposed song selection process and the implemented DJing techniques enable the system to generate mixes of high quality, as confirmed by a subjective user test in which 18 Drum and Bass fans participated.