Graph Neural Network (GNN) architectures are defined by their implementations of update and aggregation modules. While many works focus on new ways to parametrise the update modules, the aggregation modules receive comparatively little attention. Because it is difficult to parametrise aggregation functions, currently most methods select a "standard aggregator" such as mean, sum, or max . While this selection is often made without any reasoning, it has been shown that the choice in aggregator has a significant impact on performance, and the best choice in aggregator is problem-dependent. Since aggregation is a lossy operation, it is crucial to select the most appropriate aggregator in order to minimise information loss. In this paper, we present GenAgg, a generalised aggregation operator, which parametrises a function space that includes all standard aggregators. In our experiments, we show that GenAgg is able to represent the standard aggregators with much higher accuracy than baseline methods. We also show that using GenAgg as a drop-in replacement for an existing aggregator in a GNN often leads to a significant boost in performance across various tasks.

AIDE: Fastand Communication Efficient Distributed Optimization.arXive-prints,

PCWorld reports that Google's Threat Intelligence Group documented state-sponsored hackers from Russia, China, North Korea, and Iran exploiting Gemini AI for cyberattacks. These malicious actors leverage Gemini's capabilities for surveillance, target identification, vulnerability discovery, and debugging exploit code, including developing WinRAR exploits. Google restricts access for identified bad actors, but the report highlights AI's dual-use nature and emerging cybersecurity challenges. "AI" systems aren't just great for raising the price of your electronics, giving you wrong search results, and filling up your social media feed with slop.

Bayesian optimisation (BO) is a powerful framework for global optimisation of costly functions, using predictions from Gaussian process models (GPs).

However, it is important to consider users' privacy in the dataset, since results from data

Some leveloflanguage structure (e.g., compositionality) has been found in the learned communication protocols.

Video understanding relies on accurate action detection for temporal analysis.