Xiao‐Jun Zeng

Viktor Schlegel, Hao Li, Yuping Wu et al. · tencent-ai

This paper describes PULSAR, our system submission at the ImageClef 2023 MediQA-Sum task on summarising patient-doctor dialogues into clinical records. The proposed framework relies on domain-specific pre-training, to produce a specialised language model which is trained on task-specific natural data augmented by synthetic data generated by a black-box LLM. We find limited evidence towards the efficacy of domain-specific pre-training and data augmentation, while scaling up the language model yields the best performance gains. Our approach was ranked second and third among 13 submissions on task B of the challenge. Our code is available at https://github.com/yuping-wu/PULSAR.

Hao Li, Yuping Wu, Viktor Schlegel et al. · tencent-ai

Medical progress notes play a crucial role in documenting a patient's hospital journey, including his or her condition, treatment plan, and any updates for healthcare providers. Automatic summarisation of a patient's problems in the form of a problem list can aid stakeholders in understanding a patient's condition, reducing workload and cognitive bias. BioNLP 2023 Shared Task 1A focuses on generating a list of diagnoses and problems from the provider's progress notes during hospitalisation. In this paper, we introduce our proposed approach to this task, which integrates two complementary components. One component employs large language models (LLMs) for data augmentation; the other is an abstractive summarisation LLM with a novel pre-training objective for generating the patients' problems summarised as a list. Our approach was ranked second among all submissions to the shared task. The performance of our model on the development and test datasets shows that our approach is more robust on unknown data, with an improvement of up to 3.1 points over the same size of the larger model.

Ching-Hsun Tseng, Shao-Ju Chien, Po-Shen Wang et al.

Motion mode (M-mode) recording is an essential part of echocardiography to measure cardiac dimension and function. However, the current diagnosis cannot build an automatic scheme, as there are three fundamental obstructs: Firstly, there is no open dataset available to build the automation for ensuring constant results and bridging M-mode echocardiography with real-time instance segmentation (RIS); Secondly, the examination is involving the time-consuming manual labelling upon M-mode echocardiograms; Thirdly, as objects in echocardiograms occupy a significant portion of pixels, the limited receptive field in existing backbones (e.g., ResNet) composed from multiple convolution layers are inefficient to cover the period of a valve movement. Existing non-local attentions (NL) compromise being unable real-time with a high computation overhead or losing information from a simplified version of the non-local block. Therefore, we proposed RAMEM, a real-time automatic M-mode echocardiography measurement scheme, contributes three aspects to answer the problems: 1) provide MEIS, a dataset of M-mode echocardiograms for instance segmentation, to enable consistent results and support the development of an automatic scheme; 2) propose panel attention, local-to-global efficient attention by pixel-unshuffling, embedding with updated UPANets V2 in a RIS scheme toward big object detection with global receptive field; 3) develop and implement AMEM, an efficient algorithm of automatic M-mode echocardiography measurement enabling fast and accurate automatic labelling among diagnosis. The experimental results show that RAMEM surpasses existing RIS backbones (with non-local attention) in PASCAL 2012 SBD and human performances in real-time MEIS tested. The code of MEIS and dataset are available at https://github.com/hanktseng131415go/RAME.

ChengHui Yu, MingKang Tang, ShengGe Yang et al.

Deep learning-based melanoma classification with dermoscopic images has recently shown great potential in automatic early-stage melanoma diagnosis. However, limited by the significant data imbalance and obvious extraneous artifacts, i.e., the hair and ruler markings, discriminative feature extraction from dermoscopic images is very challenging. In this study, we seek to resolve these problems respectively towards better representation learning for lesion features. Specifically, a GAN-based data augmentation (GDA) strategy is adapted to generate synthetic melanoma-positive images, in conjunction with the proposed implicit hair denoising (IHD) strategy. Wherein the hair-related representations are implicitly disentangled via an auxiliary classifier network and reversely sent to the melanoma-feature extraction backbone for better melanoma-specific representation learning. Furthermore, to train the IHD module, the hair noises are additionally labeled on the ISIC2020 dataset, making it the first large-scale dermoscopic dataset with annotation of hair-like artifacts. Extensive experiments demonstrate the superiority of the proposed framework as well as the effectiveness of each component. The improved dataset publicly avaliable at https://github.com/kirtsy/DermoscopicDataset.

Yuping Wu, Ching-Hsun Tseng, Jiayu Shang et al.

Extractive models usually formulate text summarization as extracting fixed top-$k$ salient sentences from the document as a summary. Few works exploited extracting finer-grained Elementary Discourse Unit (EDU) with little analysis and justification for the extractive unit selection. Further, the selection strategy of the fixed top-$k$ salient sentences fits the summarization need poorly, as the number of salient sentences in different documents varies and therefore a common or best $k$ does not exist in reality. To fill these gaps, this paper first conducts the comparison analysis of oracle summaries based on EDUs and sentences, which provides evidence from both theoretical and experimental perspectives to justify and quantify that EDUs make summaries with higher automatic evaluation scores than sentences. Then, considering this merit of EDUs, this paper further proposes an EDU-level extractive model with Varying summary Lengths and develops the corresponding learning algorithm. EDU-VL learns to encode and predict probabilities of EDUs in the document, generate multiple candidate summaries with varying lengths based on various $k$ values, and encode and score candidate summaries, in an end-to-end training manner. Finally, EDU-VL is experimented on single and multi-document benchmark datasets and shows improved performances on ROUGE scores in comparison with state-of-the-art extractive models, and further human evaluation suggests that EDU-constituent summaries maintain good grammaticality and readability.

Shengzhong Mao, Chaoli Zhang, Yichi Song et al.

Recent advancements in the collection and analysis of sequential educational data have brought time series analysis to a pivotal position in educational research, highlighting its essential role in facilitating data-driven decision-making. However, there is a lack of comprehensive summaries that consolidate these advancements. To the best of our knowledge, this paper is the first to provide a comprehensive review of time series analysis techniques specifically within the educational context. We begin by exploring the landscape of educational data analytics, categorizing various data sources and types relevant to education. We then review four prominent time series methods-forecasting, classification, clustering, and anomaly detection-illustrating their specific application points in educational settings. Subsequently, we present a range of educational scenarios and applications, focusing on how these methods are employed to address diverse educational tasks, which highlights the practical integration of multiple time series methods to solve complex educational problems. Finally, we conclude with a discussion on future directions, including personalized learning analytics, multimodal data fusion, and the role of large language models (LLMs) in educational time series. The contributions of this paper include a detailed taxonomy of educational data, a synthesis of time series techniques with specific educational applications, and a forward-looking perspective on emerging trends and future research opportunities in educational analysis. The related papers and resources are available and regularly updated at the project page.

Yuping Wu, Hao Li, Goran Nenadic et al.

Extract-then-Abstract is a naturally coherent paradigm to conduct abstractive summarization with the help of salient information identified by the extractive model. Previous works that adopt this paradigm train the extractor and abstractor separately and introduce extra parameters to highlight the extracted salients to the abstractor, which results in error accumulation and additional training costs. In this paper, we first introduce a parameter-free highlight method into the encoder-decoder framework: replacing the encoder attention mask with a saliency mask in the cross-attention module to force the decoder to focus only on salient parts of the input. A preliminary analysis compares different highlight methods, demonstrating the effectiveness of our saliency mask. We further propose the novel extract-and-abstract paradigm, ExtAbs., which jointly and seamlessly performs Extractive and Abstractive summarization tasks within single encoder-decoder model to reduce error accumulation. In ExtAbs, the vanilla encoder is augmented to extract salients, and the vanilla decoder is modified with the proposed saliency mask to generate summaries. Built upon BART and PEGASUS, experiments on three datasets show that ExtAbs can achieve superior performance than baselines on the extractive task and performs comparable, or even better than the vanilla models on the abstractive task.

Ching-Hsun. Tseng, Liu-Hsueh. Cheng, Shin-Jye. Lee et al.

In deep learning, optimization plays a vital role. By focusing on image classification, this work investigates the pros and cons of the widely used optimizers, and proposes a new optimizer: Perturbated Unit Gradient Descent (PUGD) algorithm with extending normalized gradient operation in tensor within perturbation to update in unit space. Via a set of experiments and analyses, we show that PUGD is locally bounded updating, which means the updating from time to time is controlled. On the other hand, PUGD can push models to a flat minimum, where the error remains approximately constant, not only because of the nature of avoiding stationary points in gradient normalization but also by scanning sharpness in the unit ball. From a series of rigorous experiments, PUGD helps models to gain a state-of-the-art Top-1 accuracy in Tiny ImageNet and competitive performances in CIFAR- {10, 100}. We open-source our code at link: https://github.com/hanktseng131415go/PUGD.

Ching-Hsun Tseng, Shin-Jye Lee, Jia-Nan Feng et al.

Among image classification, skip and densely-connection-based networks have dominated most leaderboards. Recently, from the successful development of multi-head attention in natural language processing, it is sure that now is a time of either using a Transformer-like model or hybrid CNNs with attention. However, the former need a tremendous resource to train, and the latter is in the perfect balance in this direction. In this work, to make CNNs handle global and local information, we proposed UPANets, which equips channel-wise attention with a hybrid skip-densely-connection structure. Also, the extreme-connection structure makes UPANets robust with a smoother loss landscape. In experiments, UPANets surpassed most well-known and widely-used SOTAs with an accuracy of 96.47% in Cifar-10, 80.29% in Cifar-100, and 67.67% in Tiny Imagenet. Most importantly, these performances have high parameters efficiency and only trained in one customer-based GPU. We share implementing code of UPANets in https://github.com/hanktseng131415go/UPANets.

Tianyu Ren, Xiao-Jun Zeng

The significance of network structures in promoting group cooperation within social dilemmas has been widely recognized. Prior studies attribute this facilitation to the assortment of strategies driven by spatial interactions. Although reinforcement learning has been employed to investigate the impact of dynamic interaction on the evolution of cooperation, there remains a lack of understanding about how agents develop neighbour selection behaviours and the formation of strategic assortment within an explicit interaction structure. To address this, our study introduces a computational framework based on multi-agent reinforcement learning in the spatial Prisoner's Dilemma game. This framework allows agents to select dilemma strategies and interacting neighbours based on their long-term experiences, differing from existing research that relies on preset social norms or external incentives. By modelling each agent using two distinct Q-networks, we disentangle the coevolutionary dynamics between cooperation and interaction. The results indicate that long-term experience enables agents to develop the ability to identify non-cooperative neighbours and exhibit a preference for interaction with cooperative ones. This emergent self-organizing behaviour leads to the clustering of agents with similar strategies, thereby increasing network reciprocity and enhancing group cooperation.

Kaiyue Wu, Xiao-Jun Zeng, Tingting Mu

Group-agent reinforcement learning (GARL) is a newly arising learning scenario, where multiple reinforcement learning agents study together in a group, sharing knowledge in an asynchronous fashion. The goal is to improve the learning performance of each individual agent. Under a more general heterogeneous setting where different agents learn using different algorithms, we advance GARL by designing novel and effective group-learning mechanisms. They guide the agents on whether and how to learn from action choices from the others, and allow the agents to adopt available policy and value function models sent by another agent if they perform better. We have conducted extensive experiments on a total of 43 different Atari 2600 games to demonstrate the superior performance of the proposed method. After the group learning, among the 129 agents examined, 96% are able to achieve a learning speed-up, and 72% are able to learn over 100 times faster. Also, around 41% of those agents have achieved a higher accumulated reward score by learning in less than 5% of the time steps required by a single agent when learning on its own.

Chengdong Shi, Ching-Hsun Tseng, Wei Zhao et al.

We propose a novel approach to nonlinear functional regression, called the Mapping-to-Parameter function model, which addresses complex and nonlinear functional regression problems in parameter space by employing any supervised learning technique. Central to this model is the mapping of function data from an infinite-dimensional function space to a finite-dimensional parameter space. This is accomplished by concurrently approximating multiple functions with a common set of B-spline basis functions by any chosen order, with their knot distribution determined by the Iterative Local Placement Algorithm, a newly proposed free knot placement algorithm. In contrast to the conventional equidistant knot placement strategy that uniformly distributes knot locations based on a predefined number of knots, our proposed algorithms determine knot location according to the local complexity of the input or output functions. The performance of our knot placement algorithms is shown to be robust in both single-function approximation and multiple-function approximation contexts. Furthermore, the effectiveness and advantage of the proposed prediction model in handling both function-on-scalar regression and function-on-function regression problems are demonstrated through several real data applications, in comparison with four groups of state-of-the-art methods.

Qianshan Zhan, Xiao-Jun Zeng

In transfer learning, transferability is one of the most fundamental problems, which aims to evaluate the effectiveness of arbitrary transfer tasks. Existing research focuses on classification tasks and neglects domain or task differences. More importantly, there is a lack of research to determine whether to transfer or not. To address these, we propose a new analytical approach and metric, Wasserstein Distance based Joint Estimation (WDJE), for transferability estimation and determination in a unified setting: classification and regression problems with domain and task differences. The WDJE facilitates decision-making on whether to transfer or not by comparing the target risk with and without transfer. To enable the comparison, we approximate the target transfer risk by proposing a non-symmetric, easy-to-understand and easy-to-calculate target risk bound that is workable even with limited target labels. The proposed bound relates the target risk to source model performance, domain and task differences based on Wasserstein distance. We also extend our bound into unsupervised settings and establish the generalization bound from finite empirical samples. Our experiments in image classification and remaining useful life regression prediction illustrate the effectiveness of the WDJE in determining whether to transfer or not, and the proposed bound in approximating the target transfer risk.

Kaiyue Wu, Xiao-Jun Zeng

It can largely benefit the reinforcement learning (RL) process of each agent if multiple geographically distributed agents perform their separate RL tasks cooperatively. Different from multi-agent reinforcement learning (MARL) where multiple agents are in a common environment and should learn to cooperate or compete with each other, in this case each agent has its separate environment and only communicates with others to share knowledge without any cooperative or competitive behaviour as a learning outcome. In fact, this scenario exists widely in real life whose concept can be utilised in many applications, but is not well understood yet and not well formulated. As the first effort, we propose group-agent system for RL as a formulation of this scenario and the third type of RL system with respect to single-agent and multi-agent systems. We then propose a distributed RL framework called DDAL (Decentralised Distributed Asynchronous Learning) designed for group-agent reinforcement learning (GARL). We show through experiments that DDAL achieved desirable performance with very stable training and has good scalability.

Fanlin Meng, Qian Ma, Zixu Liu et al.

In this paper, we propose a realistic multiple dynamic pricing approach to demand response in the retail market. First, an adaptive clustering-based customer segmentation framework is proposed to categorize customers into different groups to enable the effective identification of usage patterns. Second, customized demand models with important market constraints which capture the price-demand relationship explicitly, are developed for each group of customers to improve the model accuracy and enable meaningful pricing. Third, the multiple pricing based demand response is formulated as a profit maximization problem subject to realistic market constraints. The overall aim of the proposed scalable and practical method aims to achieve 'right' prices for 'right' customers so as to benefit various stakeholders in the system such as grid operators, customers and retailers. The proposed multiple pricing framework is evaluated via simulations based on real-world datasets.

Elizabeth Fons, Paula Dawson, Xiao-jun Zeng et al.

Data augmentation methods have been shown to be a fundamental technique to improve generalization in tasks such as image, text and audio classification. Recently, automated augmentation methods have led to further improvements on image classification and object detection leading to state-of-the-art performances. Nevertheless, little work has been done on time-series data, an area that could greatly benefit from automated data augmentation given the usually limited size of the datasets. We present two sample-adaptive automatic weighting schemes for data augmentation: the first learns to weight the contribution of the augmented samples to the loss, and the second method selects a subset of transformations based on the ranking of the predicted training loss. We validate our proposed methods on a large, noisy financial dataset and on time-series datasets from the UCR archive. On the financial dataset, we show that the methods in combination with a trading strategy lead to improvements in annualized returns of over 50$\%$, and on the time-series data we outperform state-of-the-art models on over half of the datasets, and achieve similar performance in accuracy on the others.

Elizabeth Fons, Paula Dawson, Xiao-jun Zeng et al.

Data augmentation methods in combination with deep neural networks have been used extensively in computer vision on classification tasks, achieving great success; however, their use in time series classification is still at an early stage. This is even more so in the field of financial prediction, where data tends to be small, noisy and non-stationary. In this paper we evaluate several augmentation methods applied to stocks datasets using two state-of-the-art deep learning models. The results show that several augmentation methods significantly improve financial performance when used in combination with a trading strategy. For a relatively small dataset ($\approx30K$ samples), augmentation methods achieve up to $400\%$ improvement in risk adjusted return performance; for a larger stock dataset ($\approx300K$ samples), results show up to $40\%$ improvement.

Elizabeth Fons, Paula Dawson, Jeffrey Yau et al.

The financial crisis of 2008 generated interest in more transparent, rules-based strategies for portfolio construction, with Smart beta strategies emerging as a trend among institutional investors. While they perform well in the long run, these strategies often suffer from severe short-term drawdown (peak-to-trough decline) with fluctuating performance across cycles. To address cyclicality and underperformance, we build a dynamic asset allocation system using Hidden Markov Models (HMMs). We test our system across multiple combinations of smart beta strategies and the resulting portfolios show an improvement in risk-adjusted returns, especially on more return oriented portfolios (up to 50$\%$ in excess of market annually). In addition, we propose a novel smart beta allocation system based on the Feature Saliency HMM (FSHMM) algorithm that performs feature selection simultaneously with the training of the HMM, to improve regime identification. We evaluate our systematic trading system with real life assets using MSCI indices; further, the results (up to 60$\%$ in excess of market annually) show model performance improvement with respect to portfolios built using full feature HMMs.

Fan-Lin Meng, Xiao-Jun Zeng

This paper proposes a hybrid approach to optimal day-ahead pricing for demand response management. At the customer-side, compared with the existing work, a detailed, comprehensive and complete energy management system, which includes all possible types of appliances, all possible applications, and an effective waiting time cost model is proposed to manage the energy usages in households (lower level problem). At the retailer-side, the best retail prices are determined to maximize the retailer's profit (upper level problem). The interactions between the electricity retailer and its customers can be cast as a bilevel optimization problem. To overcome the weakness and infeasibility of conventional Karush--Kuhn--Tucker (KKT) approach for this particular type of bilevel problem, a hybrid pricing optimization approach, which adopts the multi-population genetic algorithms for the upper level problem and distributed individual optimization algorithms for the lower level problem, is proposed. Numerical results show the applicability and effectiveness of the proposed approach and its benefit to the retailer and its customers by improving the retailer's profit and reducing the customers' bills.