Graphs are widely used as a popular representation of the network structure of connected data. Graph data can be found in a broad spectrum of application domains such as social systems, ecosystems, biological networks, knowledge graphs, and information systems. With the continuous penetration of artificial intelligence technologies, graph learning (i.e., machine learning on graphs) is gaining attention from both researchers and practitioners. Graph learning proves effective for many tasks, such as classification, link prediction, and matching. Generally, graph learning methods extract relevant features of graphs by taking advantage of machine learning algorithms. In this survey, we present a comprehensive overview on the state-of-the-art of graph learning. Special attention is paid to four categories of existing graph learning methods, including graph signal processing, matrix factorization, random walk, and deep learning. Major models and algorithms under these categories are reviewed respectively. We examine graph learning applications in areas such as text, images, science, knowledge graphs, and combinatorial optimization. In addition, we discuss several promising research directions in this field.

Public knowledge graphs such as DBpedia and Wikidata have been recognized as interesting sources of background knowledge to build content-based recommender systems. They can be used to add information about the items to be recommended and links between those. While quite a few approaches for exploiting knowledge graphs have been proposed, most of them aim at optimizing the recommendation strategy while using a fixed knowledge graph. In this paper, we take a different approach, i.e., we fix the recommendation strategy and observe changes when using different underlying knowledge graphs. Particularly, we use different language editions of DBpedia. We show that the usage of different knowledge graphs does not only lead to differently biased recommender systems, but also to recommender systems that differ in performance for particular fields of recommendations.

Graph domain variables and constraints are an extension of constraint programming introduced by Dooms et al. This approach had been further investigated by Fages in its PhD thesis. On the other hand, Beldiceanu et al. presented a generic filtering scheme for global constraints based on graph properties. This scheme strongly relies on the computation of graph properties' bounds and can be used in the context of graph domain variables and constraints with a few adjustments. Bounds of MIN_NCC and MAX_NCC had been defined for the graph-based representation of global constraint for the path_with_loops graph class. In this note, we generalize those bounds for graph domain variables and for any graph class. We also provide a filtering scheme for any graph class and arbitrary bounds.

The diversity and quantity of the data warehousing, gathering data from distributed devices such as mobile phones, can enhance machine learning algorithms' success and robustness. Federated learning enables distributed participants to collaboratively learn a commonly-shared model while holding data locally. However, it is also faced with expensive communication and limitations due to the heterogeneity of distributed data sources and lack of access to global data. In this paper, we investigate a practical distributed learning scenario where multiple downstream tasks (e.g., classifiers) could be learned from dynamically-updated and non-iid distributed data sources, efficiently and providing local privatization. We introduce a new distributed learning scheme to address communication overhead via latent compression, leveraging global data while providing local privatization of local data without additional cost due to encryption or perturbation. This scheme divides the learning into (1) informative feature encoding, extracting and transmitting the latent space compressed representation features of local data at each node to address communication overhead; (2) downstream tasks centralized at the server using the encoded codes gathered from each node to address computing and storage overhead. Besides, a disentanglement strategy is applied to address the privatization of sensitive components of local data. Extensive experiments are conducted on image and speech datasets. The results demonstrate that downstream tasks on the compact latent representations can achieve comparable accuracy to centralized learning with the privatization of local data.

AI agent and the human coexist, and have partial observability of each other's activities. There are several real-world This paper addresses the problem of synthesizing workspaces like factory floors, warehouses, restaurants, nursing the behavior of an AI agent that provides proactive homes for elderly, disaster response areas, etc., where this task assistance to a human in settings like factory problem of providing proactive task assistance to the involved floors where they may coexist in a common humans is important. Our formulation considers a scenario environment. Unlike in the case of requested assistance, where the AI agent is aware of the tasks being allocated to the human may not be expecting proactive the human by the ecosystem and may also know the rules and assistance and hence it is crucial for the agent to protocols of the ecosystem. We assume that the agent has ensure that the human is aware of how the assistance access to an input that captures the human's planning process affects her task. This becomes harder when for her goals. For instance, prior works that study the there is a possibility that the human may neither problem of action model acquisition [Zhuo and Yang, 2014; have full knowledge of the AI agent's capabilities Zhuo and Kambhampati, 2013] can be used to derive the human's nor have full observability of its activities.

Wireless channels can be inherently privacy-preserving by distorting the received signals due to channel noise, and superpositioning multiple signals over-the-air. By harnessing these natural distortions and superpositions by wireless channels, we propose a novel privacy-preserving machine learning (ML) framework at the network edge, coined over-the-air mixup ML (AirMixML). In AirMixML, multiple workers transmit analog-modulated signals of their private data samples to an edge server who trains an ML model using the received noisy-and superpositioned samples. AirMixML coincides with model training using mixup data augmentation achieving comparable accuracy to that with raw data samples. From a privacy perspective, AirMixML is a differentially private (DP) mechanism limiting the disclosure of each worker's private sample information at the server, while the worker's transmit power determines the privacy disclosure level. To this end, we develop a fractional channel-inversion power control (PC) method, {\alpha}-Dirichlet mixup PC (DirMix({\alpha})-PC), wherein for a given global power scaling factor after channel inversion, each worker's local power contribution to the superpositioned signal is controlled by the Dirichlet dispersion ratio {\alpha}. Mathematically, we derive a closed-form expression clarifying the relationship between the local and global PC factors to guarantee a target DP level. By simulations, we provide DirMix({\alpha})-PC design guidelines to improve accuracy, privacy, and energy-efficiency. Finally, AirMixML with DirMix({\alpha})-PC is shown to achieve reasonable accuracy compared to a privacy-violating baseline with neither superposition nor PC.

There has been recently a growing interest in studying adversarial examples on natural language models in the black-box setting. These methods attack natural language classifiers by perturbing certain important words until the classifier label is changed. In order to find these important words, these methods rank all words by importance by querying the target model word by word for each input sentence, resulting in high query inefficiency. A new interesting approach was introduced that addresses this problem through interpretable learning to learn the word ranking instead of previous expensive search. The main advantage of using this approach is that it achieves comparable attack rates to the state-of-the-art methods, yet faster and with fewer queries, where fewer queries are desirable to avoid suspicion towards the attacking agent. Nonetheless, this approach sacrificed the useful information that could be leveraged from the target classifier for that sake of query efficiency. In this paper we study the effect of leveraging the target model outputs and data on both attack rates and average number of queries, and we show that both can be improved, with a limited overhead of additional queries.

New Zealand's most powerful supercomputer for artificial intelligence applications has been installed at the University of Waikato as part of its commitment positioning New Zealand as a world leader in AI research and development. The NVIDIA DGX A100 is the first computer of its kind in New Zealand and is the world's most advanced system for powering universal AI workloads. The machine has been referred to as the Ferrari of computing because of how fast it can rapidly and efficiently process massive amounts of data, allowing students and researchers at the University to process at lightning-fast speeds, enabling machine learning and artificial intelligence that can solve problems from addressing climate change to managing our biodiversity. Machine learning uses algorithms to explore huge data sets and create models that provide answers or outcomes mirroring human decision making. Models can be trained to recognise things like patterns, facial expressions, and spoken words - or they can find anomalies like credit card fraud.

Time series forecasting based on deep architectures has been gaining popularity in recent years due to their ability to model complex non-linear temporal dynamics. The recurrent neural network is one such model capable of handling variable-length input and output. In this paper, we leverage recent advances in deep generative models and the concept of state space models to propose a stochastic adaptation of the recurrent neural network for multistep-ahead time series forecasting, which is trained with stochastic gradient variational Bayes. In our model design, the transition function of the recurrent neural network, which determines the evolution of the hidden states, is stochastic rather than deterministic as in a regular recurrent neural network; this is achieved by incorporating a latent random variable into the transition process which captures the stochasticity of the temporal dynamics. Our model preserves the architectural workings of a recurrent neural network for which all relevant information is encapsulated in its hidden states, and this flexibility allows our model to be easily integrated into any deep architecture for sequential modelling. We test our model on a wide range of datasets from finance to healthcare; results show that the stochastic recurrent neural network consistently outperforms its deterministic counterpart.

A written proposal to ban several uses of artificial intelligence (AI) and to place new oversight on other "high-risk" AI applications--published by the European Commission this week--met fierce opposition from several digital rights advocates in Europe. Portrayed as a missed opportunity by privacy experts, the EU Commission's proposal bans four broad applications of AI, but it includes several loopholes that could lead to abuse, and it fails to include a mechanism to add other AI applications to the ban list. It deems certain types of AI applications as "high-risk"--meaning their developers will need to abide by certain restrictions--but some of those same applications were specifically called out by many digital rights groups earlier this year as "incompatible with a democratic society." It creates new government authorities, but the responsibilities of those authorities may overlap with separate authorities devoted to overall data protection. Most upsetting to digital rights experts, it appears, is that the 107-page document (not including the necessary annexes) offers only glancing restrictions on biometric surveillance, like facial recognition software.