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.

As the housing market stalls, Zillow's CEO sees AI as "an ingredient rather than a threat" that can both help the company protect its turf and reinvent how people search for homes. This will not be a banner year for the real estate app Zillow. "We describe the home market as bouncing along the bottom," CEO Jeremy Wacksman said in our conversation this week. Last year was dismal for the real estate market, and he expects things to improve only marginally in 2026. "The way to think about it is that there were 4.1 million existing homes sold last year--a normal market is 5.5 to 6 million," Wacksman says.

To mitigate the threat of adversarial examples, a large number of methods have been developed.

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

Neural Information Processing Systems http://nips.cc/

Video understanding relies on accurate action detection for temporal analysis.

Cross-object occlusions remain an important source of failures for current state-of-the-art object detectors [29],which, despite their formidable performance increase inrecent years, still carrythe biases and idiosyncrasies of the data they were trained on [16]: static images from Imagenet and COCOdatasets.

Neural Information Processing Systems http://nips.cc/

Neural Information Processing Systems http://nips.cc/

Neural Information Processing Systems http://nips.cc/