Key elements of human events are extracted as quadruples that consist of subject, relation, object, and timestamp. This representation can be extended to a quintuple by adding a fifth element: a textual summary that briefly describes the event. These quadruples or quintuples, when organized within a specific domain, form a temporal knowledge graph (TKG). Current learning frameworks focus on a few TKG-related tasks, such as predicting an object given a subject and a relation or forecasting the occurrences of multiple types of events (i.e., relation) in the next time window. They typically rely on complex structural and sequential models like graph neural networks (GNNs) and recurrent neural networks (RNNs) to update intermediate embeddings. However, these methods often neglect the contextual information inherent in each quintuple, which can be effectively captured through concise textual descriptions. In this paper, we investigate how large language models (LLMs) can streamline the design of TKG learning frameworks while maintaining competitive accuracy in prediction and forecasting tasks. We develop multiple prompt templates to frame the object prediction (OP) task as a standard question-answering (QA) task, suitable for instruction fine-tuning with an encoder-decoder generative LLM. For multi-event forecasting (MEF), we design simple yet effective prompt templates for each TKG quintuple. This novel approach removes the need for GNNs and RNNs, instead utilizing an encoder-only LLM to generate fixed intermediate embeddings, which are subsequently processed by a prediction head with a self-attention mechanism to forecast potential future relations. Extensive experiments on multiple real-world datasets using various evaluation metrics validate the effectiveness and robustness of our approach.

Machine Learning algorithms (ML) impact virtually every aspect of human lives and have found use across diverse sectors, including healthcare, finance, and education. Often, ML algorithms have been found to exacerbate societal biases presented in datasets, leading to adversarial impacts on subsets/groups of individuals, in many cases minority groups. To effectively mitigate these untoward effects, it is crucial that disparities/biases are identified and assessed early in a ML pipeline. This proactive approach facilitates timely interventions to prevent bias amplification and reduce complexity at later stages of model development. In this paper, we introduce DispaRisk, a novel framework designed to proactively assess the potential risks of disparities in datasets during the initial stages of the ML pipeline. We evaluate DispaRisk's effectiveness by benchmarking it with commonly used datasets in fairness research. Our findings demonstrate the capabilities of DispaRisk to identify datasets with a high-risk of discrimination, model families prone to biases, and characteristics that heighten discrimination susceptibility in a ML pipeline. The code for our experiments is available in the following repository: https://github.com/jovasque156/disparisk

As general chair of this year's ACM Conference on Knowledge Discovery and Data Mining (KDD), Huzefa Rangwala, a senior manager at the Amazon Machine Learning Solutions Lab, has a broad view of the topics under discussion there. Two of the most prominent, he says, are graph neural networks and fairness in AI. Graphs are data representations that can encode relationships between different data items, and graph neural networks are machine learning models that are useful for knowledge discovery because they can be used to infer graph structures. "Our world is connected in lots of ways, so you'll see graph neural networks find applications in lots of different domains, all the way from social networks and transportation networks to knowledge graphs and drug discovery," Rangwala says. The Amazon Machine Learning Solutions Lab brings the expertise of Amazon scientists and the resources of Amazon Web Services to bear on customers' machine learning problems.

Tesla has reportedly acquired the four-year-old startup DeepScale, which provides interesting insight into the state of Artificial Intelligence in assisted and automated driving. Operating on $18M in venture funding, DeepScale described themselves as developers of perceptual systems for semi-autonomous and autonomous vehicles, focusing on low-wattage processors used in mass-market automotive crash avoidance systems to power more accurate perception. This is an important niche in the intelligent vehicle eco-system; the volumes of systems like automatic emergency braking (AEB) are increasing rapidly due to OEMs making them a standard feature. JATO reports that AEB sales as standard equipment have increased from 6% in Model Year 2016 to 39% in Model Year 2018, with the fitment rate rising to 49% of vehicles sold for Model Year 2019. As one who well remembers the refrain "safety doesn't sell" in automotive circles during the 1990's, this is remarkable and gladdening.