Relational topic models: Derived from the traditional topic models [12, 29], RTMs [14, 15] are introduced to jointly consider the generations of document contents and their relationships.

To analyze a collection of interconnected documents, relational topic models (RTMs) have been developed to describe both the link structure and document content, exploring their underlying relationships via a single-layer latent representation with limited expressive capability. To better utilize the document network, we first propose graph Poisson factor analysis (GPFA) that constructs a probabilistic model for interconnected documents and also provides closed-form Gibbs sampling update equations, moving beyond sophisticated approximate assumptions of existing RTMs. Extending GPFA, we develop a novel hierarchical RTM named graph Poisson gamma belief network (GPGBN), and further introduce two different Weibull distribution based variational graph auto-encoders for efficient model inference and effective network information aggregation. Experimental results demonstrate that our models extract high-quality hierarchical latent document representations, leading to improved performance over baselines on various graph analytic tasks.

Estimating counterfactual outcomes from time-series observations is crucial for effective decision-making, e.g. when to administer a life-saving treatment, yet remains significantly challenging because (i) the counterfactual trajectory is never observed and (ii) confounders evolve with time and distort estimation at every step. To address these challenges, we propose a novel framework that synergistically integrates two complementary approaches: Sub-treatment Group Alignment (SGA) and Random Temporal Masking (RTM). Instead of the coarse practice of aligning marginal distributions of the treatments in latent space, SGA uses iterative treatment-agnostic clustering to identify fine-grained sub-treatment groups. Aligning these fine-grained groups achieves improved distributional matching, thus leading to more effective deconfounding. We theoretically demonstrate that SGA optimizes a tighter upper bound on counterfactual risk and empirically verify its deconfounding efficacy. RTM promotes temporal generalization by randomly replacing input covariates with Gaussian noises during training. This encourages the model to rely less on potentially noisy or spuriously correlated covariates at the current step and more on stable historical patterns, thereby improving its ability to generalize across time and better preserve underlying causal relationships. Our experiments demonstrate that while applying SGA and RTM individually improves counterfactual outcome estimation, their synergistic combination consistently achieves state-of-the-art performance. This success comes from their distinct yet complementary roles: RTM enhances temporal generalization and robustness across time steps, while SGA improves deconfounding at each specific time point.

MI can lead to the disclosure of highly sensitive information about the individual, e.g. that

MI can lead to the disclosure of highly sensitive information about the individual, e.g. that

This innovative practice WIP paper describes a research study that explores the integration of ChatGPT into the software testing curriculum and evaluates its effectiveness compared to human-generated testing artifacts. In a Capstone Project course, students were tasked with generating preparatory testing artifacts using ChatGPT prompts, which they had previously created manually. Their understanding and the effectiveness of the Artificial Intelligence generated artifacts were assessed through targeted questions. The results, drawn from this in-class assignment at a North American community college indicate that while ChatGPT can automate many testing preparation tasks, it cannot fully replace human expertise. However, students, already familiar with Information Technology at the postgraduate level, found the integration of ChatGPT into their workflow to be straightforward. The study suggests that AI can be gradually introduced into software testing education to keep pace with technological advancements.

To analyze a collection of interconnected documents, relational topic models (RTMs) have been developed to describe both the link structure and document content, exploring their underlying relationships via a single-layer latent representation with limited expressive capability. To better utilize the document network, we first propose graph Poisson factor analysis (GPFA) that constructs a probabilistic model for interconnected documents and also provides closed-form Gibbs sampling update equations, moving beyond sophisticated approximate assumptions of existing RTMs. Extending GPFA, we develop a novel hierarchical RTM named graph Poisson gamma belief network (GPGBN), and further introduce two different Weibull distribution based variational graph auto-encoders for efficient model inference and effective network information aggregation. Experimental results demonstrate that our models extract high-quality hierarchical latent document representations, leading to improved performance over baselines on various graph analytic tasks.

We use referential translation machines (RTMs) to identify the similarity between an attribute and two words in English by casting the task as machine translation performance prediction (MTPP) between the words and the attribute word and the distance between their similarities for Task 10 with stacked RTM models. RTMs are also used to predict the Figure 1: RTM depiction: parfda selects interpretants intensity of the structure and content in tweets close to the data using corpora; two MTPPS use in English, Arabic, and Spanish in Task 1 interpretants, training data, and test data to generate where MTPP is between the tweets and the features in the same space; learning and prediction use set of words for the emotion selected from these features as input. Spheres are for feature spaces.

Railway Transportation is extremely popular all around the globe and urges the requirement of digitized databases that includes railway track information with all railway track components such as signals, switches and mileposts (Figure 1). A Railway Technical Map (RTM) is a complex diagram (Figure 1) which includes all the information associated with a railway track. At present, most railway companies maintain RTMs designed with computer aided software, yet they are only available in PDF format. These contain partially distorted map components where identifying those components using basic digital image processing techniques is hard due to its complexity. This work focuses on implementing an automated system to generate CSV formatted files for given RTM input images containing all the digitized data that can be used with further decision support tools. The final formatted text will include the component associativity with mileposts, component names and descriptions.

This paper considers automatic classification of unstructured social group activity videos. To bridge the semantic gap between low-level features and the class-labels, the authors adopt a latent topic model based on replicated softmax to extract topics as mid-level representations for video classification. The main idea of this paper is the integration of sparse Bayesian learning and replicated softmax, which leads to the proposed model referred to "relevance topic model (RTM)". In RTM, the discriminative topics and sparse classifier weights are learned jointly, and the authors proposes variational EM algorithm for model parameter estimation and inference. The authors test their algorithm on a benchmark dataset and demonstrate better performance compared to other supervised topic models and some baseline algorithms.