Spatio-Temporal Graph Neural Networks (STGNNs) have emerged as a powerful tool for modeling dynamic graph-structured data across diverse domains. However, they often fail to generalize in Spatio-Temporal Out-of-Distribution (STOOD) scenarios, where both temporal dynamics and spatial structures evolve beyond the training distribution. To address this problem, we propose an innovative Spatio-Temporal Retrieval-Augmented Pattern Learning framework,STRAP, which enhances model generalization by integrating retrieval-augmented learning into the STGNN continue learning pipeline. The core of STRAP is a compact and expressive pattern library that stores representative spatio-temporal patterns enriched with historical, structural, and semantic information, which is obtained and optimized during the training phase. During inference, STRAP retrieves relevant patterns from this library based on similarity to the current input and injects them into the model via a plug-and-play prompting mechanism. This not only strengthens spatio-temporal representations but also mitigates catastrophic forgetting. Moreover, STRAP introduces a knowledge-balancing objective to harmonize new information with retrieved knowledge. Extensive experiments across multiple real-world streaming graph datasets show that STRAP consistently outperforms state-of-the-art STGNN baselines on STOOD tasks, demonstrating its robustness, adaptability, and strong generalization capability without task-specific fine-tuning.

Emergency department's (ED) boarding (defined as ED waiting time greater than four hours) has been linked to poor patient outcomes and health system performance. Yet, effective forecasting models is rare before COVID-19, lacking during the peri-COVID era. Here, a hybrid convolutional neural network (CNN)-Long short-term memory (LSTM) model was applied to public-domain data sourced from Hong Kong's Hospital Authority, Department of Health, and Housing Authority. In addition, we sought to identify the phase of the COVID-19 pandemic that most significantly perturbed our complex adaptive healthcare system, thereby revealing a stable pattern of interconnectedness among its components, using deep transfer learning methodology. Our result shows that 1) the greatest proportion of days with ED boarding was found between waves four and five; 2) the best-performing model for forecasting ED boarding was observed between waves four and five, which was based on features representing time-invariant residential buildings' built environment and sociodemographic profiles and the historical time series of ED boarding and case counts, compared to during the waves when best-performing forecasting is based on time-series features alone; and 3) when the model built from the period between waves four and five was applied to data from other waves via deep transfer learning, the transferred model enhanced the performance of indigenous models.

Assigning appropriate industry tag(s) to a company is a critical task in a financial institution as it impacts various financial machineries. Yet, it remains a complex task. Typically, such industry tags are to be assigned by Subject Matter Experts (SME) after evaluating company business lines against the industry definitions. It becomes even more challenging as companies continue to add new businesses and newer industry definitions are formed. Given the periodicity of the task it is reasonable to assume that an Artificial Intelligent (AI) agent could be developed to carry it out in an efficient manner. While this is an exciting prospect, the challenges appear from the need of historical patterns of such tag assignments (or Labeling). Labeling is often considered the most expensive task in Machine Learning (ML) due its dependency on SMEs and manual efforts. Therefore, often, in enterprise set up, an ML project encounters noisy and dependent labels. Such labels create technical hindrances for ML Models to produce robust tag assignments. We propose an ML pipeline which uses semantic similarity matching as an alternative to multi label text classification, while making use of a Label Similarity Matrix and a minimum labeling strategy. We demonstrate this pipeline achieves significant improvements over the noise and exhibit robust predictive capabilities.

The Transform Technology Summits start October 13th with Low-Code/No Code: Enabling Enterprise Agility. After a 2019 research paper demonstrated that commercially available facial analysis tools fail to work for women with dark skin, AWS executives went on the attack. Instead of offering up more equitable performance results or allowing the federal government to assess their algorithm like other companies with facial recognition tech have done, AWS executives attempted to discredit study coauthors Joy Buolamwini and Deb Raji in multiple blog posts. More than 70 respected AI researchers rebuked this attack, defended the study, and called on Amazon to stop selling the technology to police, a position the company temporarily adopted last year after the death of George Floyd. But according to the Abuse and Misogynoir Playbook, published earlier this year by a trio of MIT researchers, Amazon's attempt to smear two Black women AI researchers and discredit their work follows a set of tactics that have been used against Black women for centuries.

In spite of incidents of inaccuracy and bias, agencies like Artificial Intelligence (AI) court judges are starting to get accepted. However, AI has a lot to learn before we allow it to judge our moral behavior. Ganes Kesari, Co-Founder and Head of Analytics at Gramener, tells The Sociable that right now AI is not ready to take decisions on cases, and even in the future, it would be better off in the court in an assistant's role. AI needs to acquire skills in'understanding' context and interpreting scenarios "Today, AI is more suited to play the role of a judicial assistant than that of a criminal judge. It is smart at processing details, summarizing cases and looking up references. It is not ready to take decisions on cases just as yet," he says.

SwiftKey has launched a new experimental app that uses language pattern recognition from no other than William Shakespeare. ShakeSpeak might help you compare your spouse to a summer's day, but its predictive typing technology goes well beyond that. SwiftKey recently rolled out a new app that the Microsoft-owned company says will enable you to write just like William Shakespeare. ShakeSpeak is one Android app that is part of a suite of experimental apps that mix technology show-off with clean, linguistic fun. The release of the software was scheduled to coincide with 400 years since the Bard's death and one way in which the coders commemorate the great writer is by having his iconic face as the app's background image.