Policy gradient algorithms are an important family of deep reinforcement learning techniques. Many past research endeavors focused on using the first-order policy gradient information to train policy networks. Different from these works, we conduct research in this paper driven by the believe that properly utilizing and controlling Hessian information associated with the policy gradient can noticeably improve the performance of policy gradient algorithms. One key Hessian information that attracted our attention is the Hessian trace, which gives the divergence of the policy gradient vector field in the Euclidean policy parametric space. We set the goal to generalize this Euclidean policy parametric space into a general Riemmanian manifold by introducing a metric tensor field $g_ab$ in the parametric space. This is achieved through newly developed mathematical tools, deep learning algorithms, and metric tensor deep neural networks (DNNs). Armed with these technical developments, we propose a new policy gradient algorithm that learns to minimize the absolute divergence in the Riemannian manifold as an important regularization mechanism, allowing the Riemannian manifold to smoothen its policy gradient vector field. The newly developed algorithm is experimentally studied on several benchmark reinforcement learning problems. Our experiments clearly show that the new metric tensor regularized algorithm can significantly outperform its counterpart that does not use our regularization technique. Additional experimental analysis further suggests that the trained metric tensor DNN and the corresponding metric tensor $g_{ab}$ can effectively reduce the absolute divergence towards zero in the Riemannian manifold.

Modern online service providers such as online shopping platforms often provide both search and recommendation (S&R) services to meet different user needs. Rarely has there been any effective means of incorporating user behavior data from both S&R services. Most existing approaches either simply treat S&R behaviors separately, or jointly optimize them by aggregating data from both services, ignoring the fact that user intents in S&R can be distinctively different. In our paper, we propose a Search-Enhanced framework for the Sequential Recommendation (SESRec) that leverages users' search interests for recommendation, by disentangling similar and dissimilar representations within S&R behaviors. Specifically, SESRec first aligns query and item embeddings based on users' query-item interactions for the computations of their similarities. Two transformer encoders are used to learn the contextual representations of S&R behaviors independently. Then a contrastive learning task is designed to supervise the disentanglement of similar and dissimilar representations from behavior sequences of S&R. Finally, we extract user interests by the attention mechanism from three perspectives, i.e., the contextual representations, the two separated behaviors containing similar and dissimilar interests. Extensive experiments on both industrial and public datasets demonstrate that SESRec consistently outperforms state-of-the-art models. Empirical studies further validate that SESRec successfully disentangle similar and dissimilar user interests from their S&R behaviors.

Deep reinforcement learning has considerable potential to improve irrigation scheduling in many cropping systems by applying adaptive amounts of water based on various measurements over time. The goal is to discover an intelligent decision rule that processes information available to growers and prescribes sensible irrigation amounts for the time steps considered. Due to the technical novelty, however, the research on the technique remains sparse and impractical. To accelerate the progress, the paper proposes a principled framework and actionable procedure that allow researchers to formulate their own optimisation problems and implement solution algorithms based on deep reinforcement learning. The effectiveness of the framework was demonstrated using a case study of irrigated wheat grown in a productive region of Australia where profits were maximised. Specifically, the decision rule takes nine state variable inputs: crop phenological stage, leaf area index, extractable soil water for each of the five top layers, cumulative rainfall and cumulative irrigation. It returns a probabilistic prescription over five candidate irrigation amounts (0, 10, 20, 30 and 40 mm) every day. The production system was simulated at Goondiwindi using the APSIM-Wheat crop model. After training in the learning environment using 1981-2010 weather data, the learned decision rule was tested individually for each year of 2011-2020. The results were compared against the benchmark profits obtained by a conventional rule common in the region. The discovered decision rule prescribed daily irrigation amounts that uniformly improved on the conventional rule for all the testing years, and the largest improvement reached 17% in 2018. The framework is general and applicable to a wide range of cropping systems with realistic optimisation problems.

This paper presents a parameter-efficient learning (PEL) to develop a low-resource accent adaptation for text-to-speech (TTS). A resource-efficient adaptation from a frozen pre-trained TTS model is developed by using only 1.2\% to 0.8\% of original trainable parameters to achieve competitive performance in voice synthesis. Motivated by a theoretical foundation of optimal transport (OT), this study carries out PEL for TTS where an auxiliary unsupervised loss based on OT is introduced to maximize a difference between the pre-trained source domain and the (unseen) target domain, in addition to its supervised training loss. Further, we leverage upon this unsupervised loss refinement to boost system performance via either sliced Wasserstein distance or maximum mean discrepancy. The merit of this work is demonstrated by fulfilling PEL solutions based on residual adapter learning, and model reprogramming when evaluating the Mandarin accent adaptation. Experiment results show that the proposed methods can achieve competitive naturalness with parameter-efficient decoder fine-tuning, and the auxiliary unsupervised loss improves model performance empirically.

The rise of cryptocurrencies like Bitcoin, which enable transactions with a degree of pseudonymity, has led to a surge in various illicit activities, including ransomware payments and transactions on darknet markets. These illegal activities often utilize Bitcoin as the preferred payment method. However, current tools for detecting illicit behavior either rely on a few heuristics and laborious data collection processes or employ computationally inefficient graph neural network (GNN) models that are challenging to interpret. To overcome the computational and interpretability limitations of existing techniques, we introduce an effective solution called Chainlet Orbits. This approach embeds Bitcoin addresses by leveraging their topological characteristics in transactions. By employing our innovative address embedding, we investigate e-crime in Bitcoin networks by focusing on distinctive substructures that arise from illicit behavior. The results of our node classification experiments demonstrate superior performance compared to state-of-the-art methods, including both topological and GNN-based approaches. Moreover, our approach enables the use of interpretable and explainable machine learning models in as little as 15 minutes for most days on the Bitcoin transaction network.

\textit{\textbf{\textcolor{red}{Warning}:} This paper contains content that may be offensive or upsetting.} Pretrained conversational agents have been exposed to safety issues, exhibiting a range of stereotypical human biases such as gender bias. However, there are still limited bias categories in current research, and most of them only focus on English. In this paper, we introduce a new Chinese dataset, CHBias, for bias evaluation and mitigation of Chinese conversational language models. Apart from those previous well-explored bias categories, CHBias includes under-explored bias categories, such as ageism and appearance biases, which received less attention. We evaluate two popular pretrained Chinese conversational models, CDial-GPT and EVA2.0, using CHBias. Furthermore, to mitigate different biases, we apply several debiasing methods to the Chinese pretrained models. Experimental results show that these Chinese pretrained models are potentially risky for generating texts that contain social biases, and debiasing methods using the proposed dataset can make response generation less biased while preserving the models' conversational capabilities.

Amazon updated its Echo speaker lineup today, including a new $40 model with a semi-spherical design, the Echo Pop. Additionally, Echo Auto is coming to more countries. The Echo Pop is Amazon's newest entry-level Alexa-powered device. Its half-globe design uses a front-facing speaker with "full sound," although it sounds like it will be a better fit for small spaces like dorm rooms where you only need to hear it from one direction. It also carries over two features from the latest Echo Dot. First, it has Amazon's AZ2 Neural Edge processor for on-device machine learning tasks.

Sam Altman, the CEO of artificial intelligence lab OpenAI, told a Senate panel he welcomes federal regulation on the technology "to mitigate" its risks. A software company is looking to use artificial intelligence (AI) to help companies mitigate and avoid human rights risks in their supply chain. "When it comes to transparency in supply chains, there is such an enormous amount of data that is being spread not just in spreadsheets but also through social that we can start to use to identify and zero in," Justin Dillon, CEO and Founder of FRDM, told Fox News Digital, adding that it's "early, early days" for the technology and methods his company uses. Any AI technology requires significant amounts of data to analyze and process, and Dillon pointed to a treasure trove of data available on social media that his company can use to help map out problematic hotspots in supply chains -- areas that companies can then work to avoid and help create more ethical routes. Dillon related a story from a father in Australia who was talking about using "social listening," which is the analysis of conversations and trends related to different brands.

ML models are increasingly being pushed to mobile devices, for low-latency inference and offline operation. However, once the models are deployed, it is hard for ML operators to track their accuracy, which can degrade unpredictably (e.g., due to data drift). We design the first end-to-end system for continuously monitoring and adapting models on mobile devices without requiring feedback from users. Our key observation is that often model degradation is due to a specific root cause, which may affect a large group of devices. Therefore, once the system detects a consistent degradation across a large number of devices, it employs a root cause analysis to determine the origin of the problem and applies a cause-specific adaptation. We evaluate the system on two computer vision datasets, and show it consistently boosts accuracy compared to existing approaches. On a dataset containing photos collected from driving cars, our system improves the accuracy on average by 15%.

Virtual Reality (VR), Augmented Reality (AR), Mixed Reality (MR), digital twin, Metaverse and other related digital technologies have attracted much attention in recent years. These new emerging technologies are changing the world significantly. This research introduces a fusion model, i.e. Fusion Universe (FU), where the virtual, physical, and cognitive worlds are merged together. Therefore, it is crucial to establish a set of principles for the fusion model that is compatible with our physical universe laws and principles. This paper investigates several aspects that could affect immersive and interactive experience; and proposes the fundamental principles for Fusion Universe that can integrate physical and virtual world seamlessly.