Relation Extraction (RE) is a pivotal task in automatically extracting structured information from unstructured text. In this paper, we present a multi-faceted approach that integrates representative examples and through co-set expansion. The primary goal of our method is to enhance relation classification accuracy and mitigating confusion between contrastive classes. Our approach begins by seeding each relationship class with representative examples. Subsequently, our co-set expansion algorithm enriches training objectives by incorporating similarity measures between target pairs and representative pairs from the target class. Moreover, the co-set expansion process involves a class ranking procedure that takes into account exemplars from contrastive classes. Contextual details encompassing relation mentions are harnessed via context-free Hearst patterns to ascertain contextual similarity. Empirical evaluation demonstrates the efficacy of our co-set expansion approach, resulting in a significant enhancement of relation classification performance. Our method achieves an observed margin of at least 1 percent improvement in accuracy in most settings, on top of existing fine-tuning approaches. To further refine our approach, we conduct an in-depth analysis that focuses on tuning contrastive examples. This strategic selection and tuning effectively reduce confusion between classes sharing similarities, leading to a more precise classification process. Experimental results underscore the effectiveness of our proposed framework for relation extraction. The synergy between co-set expansion and context-aware prompt tuning substantially contributes to improved classification accuracy. Furthermore, the reduction in confusion between contrastive classes through contrastive examples tuning validates the robustness and reliability of our method.

The integration of emotional support into various conversational scenarios presents profound societal benefits, such as social interactions, mental health counseling, and customer service. However, there are unsolved challenges that hinder real-world applications in this field, including limited data availability and the absence of well-accepted model training paradigms. This work endeavors to navigate these challenges by harnessing the capabilities of Large Language Models (LLMs). We introduce an innovative methodology that synthesizes human insights with the computational prowess of LLMs to curate an extensive emotional support dialogue dataset. Our approach is initiated with a meticulously designed set of dialogues spanning diverse scenarios as generative seeds. By utilizing the in-context learning potential of ChatGPT, we recursively generate an ExTensible Emotional Support dialogue dataset, named ExTES. Following this, we deploy advanced tuning techniques on the LLaMA model, examining the impact of diverse training strategies, ultimately yielding an LLM meticulously optimized for emotional support interactions. An exhaustive assessment of the resultant model showcases its proficiency in offering emotional support, marking a pivotal step in the realm of emotional support bots and paving the way for subsequent research and implementations.

Multi-objective Markov decision processes are a special kind of multi-objective optimization problem that involves sequential decision making while satisfying the Markov property of stochastic processes. Multi-objective reinforcement learning methods address this problem by fusing the reinforcement learning paradigm with multi-objective optimization techniques. One major drawback of these methods is the lack of adaptability to non-stationary dynamics in the environment. This is because they adopt optimization procedures that assume stationarity to evolve a coverage set of policies that can solve the problem. This paper introduces a developmental optimization approach that can evolve the policy coverage set while exploring the preference space over the defined objectives in an online manner. We propose a novel multi-objective reinforcement learning algorithm that can robustly evolve a convex coverage set of policies in an online manner in non-stationary environments. We compare the proposed algorithm with two state-of-the-art multi-objective reinforcement learning algorithms in stationary and non-stationary environments. Results showed that the proposed algorithm significantly outperforms the existing algorithms in non-stationary environments while achieving comparable results in stationary environments.

The aquaculture sector in New Zealand is experiencing rapid expansion, with a particular emphasis on mussel exports. As the demands of mussel farming operations continue to evolve, the integration of artificial intelligence and computer vision techniques, such as intelligent object detection, is emerging as an effective approach to enhance operational efficiency. This study delves into advancing buoy detection by leveraging deep learning methodologies for intelligent mussel farm monitoring and management. The primary objective centers on improving accuracy and robustness in detecting buoys across a spectrum of real-world scenarios. A diverse dataset sourced from mussel farms is captured and labeled for training, encompassing imagery taken from cameras mounted on both floating platforms and traversing vessels, capturing various lighting and weather conditions. To establish an effective deep learning model for buoy detection with a limited number of labeled data, we employ transfer learning techniques. This involves adapting a pre-trained object detection model to create a specialized deep learning buoy detection model. We explore different pre-trained models, including YOLO and its variants, alongside data diversity to investigate their effects on model performance. Our investigation demonstrates a significant enhancement in buoy detection performance through deep learning, accompanied by improved generalization across diverse weather conditions, highlighting the practical effectiveness of our approach.

Developing effective Multi-Agent Systems (MAS) is critical for many applications requiring collaboration and coordination with humans. Despite the rapid advance of Multi-Agent Deep Reinforcement Learning (MADRL) in cooperative MAS, one major challenge is the simultaneous learning and interaction of independent agents in dynamic environments in the presence of stochastic rewards. State-of-the-art MADRL models struggle to perform well in Coordinated Multi-agent Object Transportation Problems (CMOTPs), wherein agents must coordinate with each other and learn from stochastic rewards. In contrast, humans often learn rapidly to adapt to nonstationary environments that require coordination among people. In this paper, motivated by the demonstrated ability of cognitive models based on Instance-Based Learning Theory (IBLT) to capture human decisions in many dynamic decision making tasks, we propose three variants of Multi-Agent IBL models (MAIBL). The idea of these MAIBL algorithms is to combine the cognitive mechanisms of IBLT and the techniques of MADRL models to deal with coordination MAS in stochastic environments from the perspective of independent learners. We demonstrate that the MAIBL models exhibit faster learning and achieve better coordination in a dynamic CMOTP task with various settings of stochastic rewards compared to current MADRL models. We discuss the benefits of integrating cognitive insights into MADRL models.

Training deep neural networks using backpropagation is very memory and computationally intensive. This makes it difficult to run on-device learning or fine-tune neural networks on tiny, embedded devices such as low-power micro-controller units (MCUs). Sparse backpropagation algorithms try to reduce the computational load of on-device learning by training only a subset of the weights and biases. Existing approaches use a static number of weights to train. A poor choice of this so-called backpropagation ratio limits either the computational gain or can lead to severe accuracy losses. In this paper we present TinyProp, the first sparse backpropagation method that dynamically adapts the back-propagation ratio during on-device training for each training step. TinyProp induces a small calculation overhead to sort the elements of the gradient, which does not significantly impact the computational gains. TinyProp works particularly well on fine-tuning trained networks on MCUs, which is a typical use case for embedded applications. For typical datasets from three datasets MNIST, DCASE2020 and CIFAR10, we are 5 times faster compared to non-sparse training with an accuracy loss of on average 1%. On average, TinyProp is 2.9 times faster than existing, static sparse backpropagation algorithms and the accuracy loss is reduced on average by 6 % compared to a typical static setting of the back-propagation ratio.

Network complexity and computational efficiency have become increasingly significant aspects of deep learning. Sparse deep learning addresses these challenges by recovering a sparse representation of the underlying target function by reducing heavily over-parameterized deep neural networks. Specifically, deep neural architectures compressed via structured sparsity (e.g. node sparsity) provide low latency inference, higher data throughput, and reduced energy consumption. In this paper, we explore two well-established shrinkage techniques, Lasso and Horseshoe, for model compression in Bayesian neural networks. To this end, we propose structurally sparse Bayesian neural networks which systematically prune excessive nodes with (i) Spike-and-Slab Group Lasso (SS-GL), and (ii) Spike-and-Slab Group Horseshoe (SS-GHS) priors, and develop computationally tractable variational inference including continuous relaxation of Bernoulli variables. We establish the contraction rates of the variational posterior of our proposed models as a function of the network topology, layer-wise node cardinalities, and bounds on the network weights. We empirically demonstrate the competitive performance of our models compared to the baseline models in prediction accuracy, model compression, and inference latency.

Multi-hop QA involves finding multiple relevant passages and step-by-step reasoning to answer complex questions. While previous approaches have developed retrieval modules for selecting relevant passages, they face challenges in scenarios beyond two hops, owing to the limited performance of one-step methods and the failure of two-step methods when selecting irrelevant passages in earlier stages. In this work, we introduce Beam Retrieval, a general end-to-end retrieval framework for multi-hop QA. This approach maintains multiple partial hypotheses of relevant passages at each step, expanding the search space and reducing the risk of missing relevant passages. Moreover, Beam Retrieval jointly optimizes an encoder and two classification heads by minimizing the combined loss across all hops. To establish a complete QA system, we incorporate a supervised reader or a zero-shot GPT-3.5. Experimental results demonstrate that Beam Retrieval achieves a nearly 50% improvement compared with baselines on challenging MuSiQue-Ans, and it also surpasses all previous retrievers on HotpotQA and 2WikiMultiHopQA. Providing high-quality context, Beam Retrieval helps our supervised reader achieve new state-of-the-art performance and substantially improves (up to 28.8 points) the QA performance of zero-shot GPT-3.5.

Factuality can play an important role when automatically processing clinical text, as it makes a difference if particular symptoms are explicitly not present, possibly present, not mentioned, or affirmed. In most cases, a sufficient number of examples is necessary to handle such phenomena in a supervised machine learning setting. However, as clinical text might contain sensitive information, data cannot be easily shared. In the context of factuality detection, this work presents a simple solution using machine translation to translate English data to German to train a transformer-based factuality detection model.

A learner aims to minimize a function $f$ by repeatedly querying a distributed oracle that provides noisy gradient evaluations. At the same time, the learner seeks to hide $\arg\min f$ from a malicious eavesdropper that observes the learner's queries. This paper considers the problem of \textit{covert} or \textit{learner-private} optimization, where the learner has to dynamically choose between learning and obfuscation by exploiting the stochasticity. The problem of controlling the stochastic gradient algorithm for covert optimization is modeled as a Markov decision process, and we show that the dynamic programming operator has a supermodular structure implying that the optimal policy has a monotone threshold structure. A computationally efficient policy gradient algorithm is proposed to search for the optimal querying policy without knowledge of the transition probabilities. As a practical application, our methods are demonstrated on a hate speech classification task in a federated setting where an eavesdropper can use the optimal weights to generate toxic content, which is more easily misclassified. Numerical results show that when the learner uses the optimal policy, an eavesdropper can only achieve a validation accuracy of $52\%$ with no information and $69\%$ when it has a public dataset with 10\% positive samples compared to $83\%$ when the learner employs a greedy policy.