Abstract--The future 6G network is envisioned to be AI-native, and as such, ML models will be pervasive in support of optimizing performance, reducing energy consumption, and in coping with increasing complexity and heterogeneity. A key challenge is automating the process of finding optimal model architectures satisfying stringent requirements stemming from varying tasks, dynamicity and available resources in the infrastructure and deployment positions. In this paper, we describe and review the state-of-the-art in Neural Architecture Search and Transfer Learning and their applicability in networking. Further, we identify open research challenges and set directions with a specific focus on three main requirements with elements unique to the future network, namely combining NAS and TL, multi-objective search, and tabular data. Artificial Intelligence (AI) and Machine Learning (ML) are technologies which are envisioned to have a prominent Transfer Learning (TL) is a key technology that can play a role in the future AI-native 6G network.

This paper presents an initial exploration on the use of 2D cellular automata (CA) for generating 3D terrains through a simple yet effective additive approach. By experimenting with multiple CA transition rules, this preliminary investigation yielded aesthetically interesting landscapes, hinting at the technique's potential applicability for real-time terrain generation in games.

Graph neural architecture search (Graph NAS) has emerged as a promising approach for autonomously designing graph neural network architectures by leveraging the correlations between graphs and architectures. However, the existing methods fail to generalize under distribution shifts that are ubiquitous in real-world graph scenarios, mainly because the graph-architecture correlations they exploit might be spurious and varying across distributions. In this paper, we propose to handle the distribution shifts in the graph architecture search process by discovering and exploiting the causal relationship between graphs and architectures to search for the optimal architectures that can generalize under distribution shifts. The problem remains unexplored with the following critical challenges: 1) how to discover the causal graph-architecture relationship that has stable predictive abilities across distributions, 2) how to handle distribution shifts with the discovered causal graph-architecture relationship to search the generalized graph architectures. To address these challenges, we propose a novel approach, Causal-aware Graph Neural Architecture Search (CARNAS), which is able to capture the causal graph-architecture relationship during the architecture search process and discover the generalized graph architecture under distribution shifts. Specifically, we propose Disentangled Causal Subgraph Identification to capture the causal subgraphs that have stable prediction abilities across distributions. Then, we propose Graph Embedding Intervention to intervene on causal subgraphs within the latent space, ensuring that these subgraphs encapsulate essential features for prediction while excluding non-causal elements. Additionally, we propose Invariant Architecture Customization to reinforce the causal invariant nature of the causal subgraphs, which are utilized to tailor generalized graph architectures. Extensive experiments on synthetic and real-world datasets demonstrate that our proposed CARNAS achieves advanced out-of-distribution generalization ability by discovering the causal relationship between graphs and architectures during the search process.

In this paper, we present Misaka, a visualized swarm testbed for smart grid algorithm evaluation, also an extendable open-source open-hardware platform for developing tabletop tangible swarm interfaces. The platform consists of a collection of custom-designed 3 omni-directional wheels robots each 10 cm in diameter, high accuracy localization through a microdot pattern overlaid on top of the activity sheets, and a software framework for application development and control, while remaining affordable (per unit cost about 30 USD at the prototype stage). We illustrate the potential of tabletop swarm user interfaces through a set of smart grid algorithm application scenarios developed with Misaka.

A variety of forms of artificial intelligence systems have been developed. Two well-known techniques are neural networks and rule-fact expert systems. The former can be trained from presented data while the latter is typically developed by human domain experts. A combined implementation that uses gradient descent to train a rule-fact expert system has been previously proposed. A related system type, the Blackboard Architecture, adds an actualization capability to expert systems. This paper proposes and evaluates the incorporation of a defensible-style gradient descent training capability into the Blackboard Architecture. It also introduces the use of activation functions for defensible artificial intelligence systems and implements and evaluates a new best path-based training algorithm.

Algorithms developed to solve many-body quantum problems, like tensor networks, can turn into powerful quantum-inspired tools to tackle problems in the classical domain. In this work, we focus on matrix product operators, a prominent numerical technique to study many-body quantum systems, especially in one dimension. It has been previously shown that such a tool can be used for classification, learning of deterministic sequence-to-sequence processes and of generic quantum processes. We further develop a matrix product operator algorithm to learn probabilistic sequence-to-sequence processes and apply this algorithm to probabilistic cellular automata. This new approach can accurately learn probabilistic cellular automata processes in different conditions, even when the process is a probabilistic mixture of different chaotic rules. In addition, we find that the ability to learn these dynamics is a function of the bit-wise difference between the rules and whether one is much more likely than the other.

Enhancing robot navigation efficiency is a crucial objective in modern robotics. Robots relying on external navigation systems are often susceptible to electromagnetic interference (EMI) and encounter environmental disturbances, resulting in orientation errors within their surroundings. Therefore, the study employed an internal navigation system to enhance robot navigation efficacy under interference conditions, based on the analysis of the internal parameters and the external signals. This article presents details of the robot's autonomous operation, which allows for setting the robot's trajectory using an embedded map. The robot's navigation process involves counting the number of wheel revolutions as well as adjusting wheel orientation after each straight path section. In this article, an autonomous robot navigation system has been presented that leverages an embedded control navigation map utilising cellular automata with active cells which can effectively navigate in an environment containing various types of obstacles. By analysing the neighbouring cells of the active cell, the cellular environment determines which cell should become active during the robot's next movement step. This approach ensures the robot's independence from external control inputs. Furthermore, the accuracy and speed of the robot's movement have been further enhanced using a hexagonal mosaic for navigation surface mapping. This concept of utilising on cellular automata with active cells has been extended to the navigation of a group of robots on a shared navigation surface, taking into account the intersections of the robots' trajectories over time. To achieve this, a distance control module has been used that records the travelled trajectories in terms of wheel turns and revolutions.

Neural cellular automata represent an evolution of the traditional cellular automata model, enhanced by the integration of a deep learning-based transition function. This shift from a manual to a data-driven approach significantly increases the adaptability of these models, enabling their application in diverse domains, including content generation and artificial life. However, their widespread application has been hampered by significant computational requirements. In this work, we introduce the Latent Neural Cellular Automata (LNCA) model, a novel architecture designed to address the resource limitations of neural cellular automata. Our approach shifts the computation from the conventional input space to a specially designed latent space, relying on a pre-trained autoencoder. We apply our model in the context of image restoration, which aims to reconstruct high-quality images from their degraded versions. This modification not only reduces the model's resource consumption but also maintains a flexible framework suitable for various applications. Our model achieves a significant reduction in computational requirements while maintaining high reconstruction fidelity. This increase in efficiency allows for inputs up to 16 times larger than current state-of-the-art neural cellular automata models, using the same resources.

The existing graph neural architecture search (GNAS) methods heavily rely on supervised labels during the search process, failing to handle ubiquitous scenarios where supervisions are not available. In this paper, we study the problem of unsupervised graph neural architecture search, which remains unexplored in the literature. The key problem is to discover the latent graph factors that drive the formation of graph data as well as the underlying relations between the factors and the optimal neural architectures. Handling this problem is challenging given that the latent graph factors together with architectures are highly entangled due to the nature of the graph and the complexity of the neural architecture search process. To address the challenge, we propose a novel Disentangled Self-supervised Graph Neural Architecture Search (DSGAS) model, which is able to discover the optimal architectures capturing various latent graph factors in a self-supervised fashion based on unlabeled graph data. Specifically, we first design a disentangled graph super-network capable of incorporating multiple architectures with factor-wise disentanglement, which are optimized simultaneously. Then, we estimate the performance of architectures under different factors by our proposed self-supervised training with joint architecture-graph disentanglement. Finally, we propose a contrastive search with architecture augmentations to discover architectures with factor-specific expertise. Extensive experiments on 11 real-world datasets demonstrate that the proposed model is able to achieve state-of-the-art performance against several baseline methods in an unsupervised manner.

For robots to perform assistive tasks in unstructured home environments, they must learn and reason on the semantic knowledge of the environments. Despite a resurgence in the development of semantic reasoning architectures, these methods assume that all the training data is available a priori. However, each user's environment is unique and can continue to change over time, which makes these methods unsuitable for personalized home service robots. Although research in continual learning develops methods that can learn and adapt over time, most of these methods are tested in the narrow context of object classification on static image datasets. In this paper, we combine ideas from continual learning, semantic reasoning, and interactive machine learning literature and develop a novel interactive continual learning architecture for continual learning of semantic knowledge in a home environment through human-robot interaction. The architecture builds on core cognitive principles of learning and memory for efficient and real-time learning of new knowledge from humans. We integrate our architecture with a physical mobile manipulator robot and perform extensive system evaluations in a laboratory environment over two months. Our results demonstrate the effectiveness of our architecture to allow a physical robot to continually adapt to the changes in the environment from limited data provided by the users (experimenters), and use the learned knowledge to perform object fetching tasks.