1 October 2022 in Data Intelligence
Making medication prescriptions in response to the patient's diagnosis is a challenging task. The number of pharmaceutical companies, their inventory of medicines, and the recommended dosage confront a doctor with the well-known problem of information and cognitive overload. To assist a medical practitioner in making informed decisions regarding a medical prescription to a patient, researchers have exploited electronic health records (EHRs) in automatically recommending medication. In recent years, medication recommendation using EHRs has been a salient research direction, which has attracted researchers to apply various deep learning (DL) models to the EHRs of patients in recommending prescriptions. Yet, in the absence of a holistic survey article, it needs a lot of effort and time to study these publications in order to understand the current state of research and identify the best-performing models along with the trends and challenges. To fill this research gap, this survey reports on state-of-the-art DL-based medication recommendation methods. It reviews the classification of DL-based medication recommendation (MR) models, compares their performance, and the unavoidable issues they face. It reports on the most common datasets and metrics used in evaluating MR models. The findings of this study have implications for researchers interested in MR models.
5 January 2024 in Intelligent Computing
With the widespread deployment of 5G networks and the proliferation of mobile devices, mobile network operators are confronted not only with massive data growth in mobile traffic, but also with highly complex and dynamic traffic patterns. Given these challenges to network operation, cellular traffic prediction is becoming an essential network capability for ensuring quality of service and reducing costs. Accurate and timely cellular traffic prediction is essential for resource allocation, base station energy conservation, and network optimization. Recent years have seen widespread adoption of deep-learning-based models for cellular traffic prediction, with notable performance improvements. This survey encompasses representative data, model architectures, and state-of-the-art performance to provide a comprehensive account of deep learning techniques for cellular traffic prediction. After defining the problem of cellular traffic prediction and describing the available data, we describe in detail how deep learning techniques are used to capture the most crucial temporal and spatial dependencies of cellular traffic. We then summarize the state-of-the-art performance on 2 popular open datasets with multiple data settings to facilitate the comparison of deep-learning-based methods. Finally, we briefly outline the applications of cellular traffic prediction and discuss the remaining challenges and future research directions.
17 April 2023 in Frontiers in Psychiatry
As psychological diseases become more prevalent and are identified as the leading cause of acquired disability, it is essential to assist people in improving their mental health. Digital therapeutics (DTx) has been widely studied to treat psychological diseases with the advantage of cost savings. Among the techniques of DTx, a conversational agent can interact with patients through natural language dialog and has become the most promising one. However, conversational agents' ability to accurately show emotional support (ES) limits their role in DTx solutions, especially in mental health support. One of the main reasons is that the prediction of emotional support systems does not extract effective information from historical dialog data and only depends on the data derived from one single-turn interaction with users. To address this issue, we propose a novel emotional support conversation agent called the STEF agent that generates more supportive responses based on a thorough view of past emotions. The proposed STEF agent consists of the emotional fusion mechanism and strategy tendency encoder. The emotional fusion mechanism focuses on capturing the subtle emotional changes throughout a conversation. The strategy tendency encoder aims at foreseeing strategy evolution through multi-source interactions and extracting latent strategy semantic embedding. Experimental results on the benchmark dataset ESConv demonstrate the effectiveness of the STEF agent compared with competitive baselines.
11 April 2025 in Proceedings of the AAAI Conference on Artificial Intelligence
Large Language Models (LLMs) are often English-centric due to the disproportionate distribution of languages in their pre-training data. Enhancing non-English language capabilities through post-pretraining often results in catastrophic forgetting of high-resource languages. Previous methods either achieve good expansion with severe forgetting or slight forgetting with poor expansion, indicating the challenge of balancing language expansion while preventing forgetting. In this paper, we propose a method called MoE-LPR (Mixture-of-Experts with Language Priors Routing) to alleviate this problem. MoE-LPR employs a two-stage training approach to enhance the multilingual capability. First, the model is post-pretrained into a Mixture-of-Experts(MoE) architecture by upcycling, where all the original parameters are frozen and new experts are added. In this stage, we focus improving the ability on expanded languages, without using any original language data. Then, the model reviews the knowledge of the original languages with replay data amounting to less than 1% of post-pretraining, where we incorporate language priors routing to better recover the abilities of the original languages. Evaluations on multiple benchmarks show that MoE-LPR outperforms other post-pretraining methods. Freezing original parameters preserves original language knowledge while adding new experts preserves the learning ability. Reviewing with LPR enables effective utilization of multilingual knowledge within the parameters. Additionally, the MoE architecture maintains the same inference overhead while increasing total model parameters. Extensive experiments demonstrate MoE-LPR’s effectiveness in improving expanded languages and preserving original language proficiency with superior scalability.