Publication Library
On the Utilization of Unique Node Identifiers in Graph Neural Networks
Description: Graph neural networks have inherent representational limitations due to their messagepassing structure. Recent work has suggested that these limitations can be overcome by using unique node identifiers (UIDs). Here we argue that despite the advantages of UIDs, one of their disadvantages is that they lose the desirable property of permutationequivariance. We thus propose to focus on UID models that are permutation-equivariant, and present theoretical arguments for their advantages. Motivated by this, we propose a method to regularize UID models towards permutation equivariance, via a contrastive loss. We empirically demonstrate that our approach improves generalization and extrapolation abilities while providing faster training convergence. On the recent BREC expressiveness benchmark, our proposed method achieves state-of-the-art performance compared to other random-based approaches.
Created At: 15 December 2024
Updated At: 15 December 2024
Artificial Intelligence in E-commerce Applications, Implications and Challenges
Description: Artificial intelligence (AI) is a large subject of computer science devoted to the development of intelligent computers capable of doing tasks that would typically need human intelligence. AI programming focuses on three cognitive processes: learning, reasoning, and self-correction. Many E-Commerce firms today employ artificial intelligence to better understand their customers and meet their expectations. Machine learning, the most popular subset of AI technology, can make sense of all the data that online stores collect and use it to provide insights that improve customer experience, streamline internal business operations, and combat fraud. This paper basically aims to identify some key applications of AI in E-commerce by reviewing research articles from various sources. The study concluded that AI has great impact on improving the efficiency of E-commerce companies and these companies are investng more and more with coming time to help their business to grow and boom in the recent years.
Created At: 15 December 2024
Updated At: 15 December 2024
Reallocation of Temporary Identities Applying 5G Cybersecurity and Privacy Capabilities
Description: This white paper is part of a series called Applying 5G Cybersecurity and Privacy Capabilities, which covers 5G cybersecurity- and privacy-supporting capabilities that were implemented as part of the 5G Cybersecurity project at the National Cybersecurity Center of Excellence (NCCoE). This white paper provides additional details regarding how 5G protects subscriber identities (IDs). It focuses on how the network reallocates temporary IDs to protect users from being identified and located by an attacker. Unlike previous generations of cellular systems, new requirements in 5G explicitly define when the temporary ID must be reallocated (refreshed). 5G network operators should be aware of how this standards-defined security capability protects their users and subscribers. Operators should ensure that their 5G technologies are refreshing temporary identities as described in the 5G standards.
Created At: 15 December 2024
Updated At: 15 December 2024
Applying 5G Cybersecurity and Privacy Capabilities
Description: This document introduces the white paper series titled Applying 5G Cybersecurity and Privacy Capabilities. This series is being published by the National Cybersecurity Center of Excellence (NCCoE) 5G Cybersecurity project. Each paper in the series will include information, guidance, and research findings for an individual technical cybersecurity- or privacy-supporting capability available in 5G systems or their supporting infrastructures. Each of the capabilities has been implemented in a testbed as part of the NCCoE project, and each white paper reflects the results of that implementation and its testing.
Created At: 15 December 2024
Updated At: 15 December 2024
Model Swarms Collaborative Search to Adapt LLM Experts via Swarm Intelligence
Description: We propose MODEL SWARMS, a collaborative search algorithm to adapt LLMs via swarmintelligence, the collective behavior guiding individual systems. Specifically, MODEL SWARMS starts with a pool of LLM experts and a utility function. Guided by the best-found checkpoints across models, diverse LLM experts collaboratively move in the weight space and optimize a utility function representing model adaptation objectives. Compared to existing model composition approaches, MODEL SWARMS offers tuning-free model adaptation, works in lowdata regimes with as few as 200 examples, and does not require assumptions about specific experts in the swarm or how they should be composed. Extensive experiments demonstrate that MODEL SWARMS could flexibly adapt LLM experts to a single task, multi-task domains, reward models, as well as diverse human interests, improving over 12 model composition baselines by up to 21.0% across tasks and contexts. Further analysis reveals that LLM experts discover previously unseen capabilities in initial checkpoints and that MODEL SWARMS enable the weak-to-strong transition of experts through the collaborative search process.
Created At: 14 December 2024
Updated At: 14 December 2024