Shiqi Zhao

AAAI Conference 2026 Conference Paper

Personality-guided Public-Private Domain Disentangled Hypergraph-Former Network for Multimodal Depression Detection

• Changzeng Fu
• Shiwen Zhao
• Yunze Zhang
• Zhongquan Jian
• Shiqi Zhao
• Chaoran Liu

Depression represents a global mental health challenge requiring efficient and reliable automated detection methods. Current Transformer- or Graph Neural Networks (GNNs)-based multimodal depression detection methods face significant challenges in modeling individual differences and cross-modal temporal dependencies across diverse behavioral contexts. Therefore, we propose P³HF (Personality-guided Public-Private Domain Disentangled Hypergraph-Former Network) with three key innovations: (1) personality-guided representation learning using LLMs to transform discrete individual features into contextual descriptions for personalized encoding; (2) Hypergraph-Former architecture modeling high-order cross-modal temporal relationships; (3) event-level domain disentanglement with contrastive learning for improved generalization across behavioral contexts. Experiments on MPDD-Young dataset show P³HF achieves around 10% improvement on accuracy and weighted F1 for binary and ternary depression classification task over existing methods. Extensive ablation studies validate the independent contribution of each architectural component, confirming that personality-guided representation learning and high-order hypergraph reasoning are both essential for generating robust, individual-aware depression-related representations.

JBHI Journal 2025 Journal Article

Memory-Efficient Intrinsic Gating Adaptation for Enhanced On-Device Epilepsy Diagnosis

• Shanjin Li
• Di Wu
• Shiqi Zhao
• Jie Yang
• Mohamad Sawan

Recently, advances in neuroscience and the rise of artificial intelligence have significantly enhanced the capabilities of epilepsy diagnosis. While EEG-based diagnosis offer a promising avenue for detecting and predicting seizure activity, practical implementation in real-world scenarios remains hindered by the heterogeneity of epilepsy and the variability of patient-specific biomarkers over time. Conventional deep learning models, trained on historical EEG, often fail to adapt to such biomarker variations, leading to degraded performance. Moreover, the computational and memory constraints of edge devices further exacerbate the challenge of on-device learning. To address these challenges, we introduce a novel framework, Memory-Efficient Intrinsic Gating Adaptation (MEIGA), designed to enhance real-world epilepsy diagnosis on resource-constrained edge devices. Our approach pre-trains a model using historical EEG data and employs lightweight adapter networks for efficient on-device tuning across new sessions, addressing session-to-session variability. By leveraging Direct Feedback Alignment (DFA), MEIGA reduces memory usage and computational overhead while maintaining high classification accuracy. Extensive experiments on the CHB-MIT epilepsy dataset demonstrate that MEIGA outperforms the pretrained-only Vision Transformer baseline, raising seizure prediction accuracy from 47. 88% to 86. 77% with only 3, 908 tunable parameters (5. 05% of the backbone). For seizure detection, MEIGA improves accuracy from 85. 06% to 96. 29% by adapting 2, 008 parameters (17. 40% of the base architecture). Further experiments on the AES dataset demonstrate that MEIGA consistently delivers strong performance across subjects and scales effectively to larger networks.

IJCAI Conference 2017 Conference Paper

Learning to Explain Entity Relationships by Pairwise Ranking with Convolutional Neural Networks

• Jizhou Huang
• Wei Zhang
• Shiqi Zhao
• Shiqiang Ding
• Haifeng Wang

Providing a plausible explanation for the relationship between two related entities is an important task in some applications of knowledge graphs, such as in search engines. However, most existing methods require a large number of manually labeled training data, which cannot be applied in large-scale knowledge graphs due to the expensive data annotation. In addition, these methods typically rely on costly handcrafted features. In this paper, we propose an effective pairwise ranking model by leveraging clickthrough data of a Web search engine to address these two problems. We first construct large-scale training data by leveraging the query-title pairs derived from clickthrough data of a Web search engine. Then, we build a pairwise ranking model which employs a convolutional neural network to automatically learn relevant features. The proposed model can be easily trained with backpropagation to perform the ranking task. The experiments show that our method significantly outperforms several strong baselines.

IJCAI Conference 2016 Conference Paper

Generating Recommendation Evidence Using Translation Model

• Jizhou Huang
• Shiqi Zhao
• Shiqiang Ding
• Haiyang Wu
• Mingming Sun
• Haifeng Wang

Entity recommendation, providing entity suggestions relevant to the query that a user is searching for, has become a key feature of today's web search engine. Despite the fact that related entities are relevant to users' search queries, sometimes users cannot easily understand the recommended entities without evidences. This paper proposes a statistical model consisting of four sub-models to generate evidences for entities, which can help users better understand each recommended entity, and figure out the connections between the recommended entities and a given query. The experiments show that our method is domain independent, and can generate catchy and interesting evidences in the application of entity recommendation.

TIST Journal 2013 Journal Article

Introduction to special section on paraphrasing

• Haifeng Wang
• Bill Dolan
• Idan Szpektor
• Shiqi Zhao

IJCAI Conference 2007 Conference Paper

• Shiqi Zhao
• Ming Zhou
• Ting Liu

Question paraphrasing is critical in many Natural Language Processing (NLP) applications, especially for question reformulation in question answering (QA). However, choosing an appropriate data source and developing effective methods are challenging tasks. In this paper, we propose a method that exploits Encarta logs to automatically identify question paraphrases and extract templates. Questions from Encarta logs are partitioned into small clusters, within which a perceptron classier is used for identifying question paraphrases. Experiments are conducted and the results have shown: (1) Encarta log data is an eligible data source for question paraphrasing and the user clicks in the data are indicative clues for recognizing paraphrases; (2) the supervised method we present is effective, which can evidently outperform the unsupervised method. Besides, the features introduced to identify paraphrases are sound; (3) the obtained question paraphrase templates are quite effective in question reformulation, enhancing the MRR from 0. 2761 to 0. 4939 with the questions of TREC QA 2003.

IJCAI Conference 2007 Conference Paper

• Shiqi Zhao
• Ting Liu
• Xincheng Yuan
• Sheng Li
• Yu Zhang

Lexical paraphrasing aims at acquiring word-level paraphrases. It is critical for many Natural Language Processing (NLP) applications, such as Question Answering (QA), Information Extraction (IE), and Machine Translation (MT). Since the meaning and usage of a word can vary in distinct contexts, different paraphrases should be acquired according to the contexts. However, most of the existing researches focus on constructing paraphrase corpora, in which little contextual constraints for paraphrase application are imposed. This paper presents a method that automatically acquires context-specific lexical paraphrases. In this method, the obtained paraphrases of a word depend on the specific sentence the word occurs in. Two stages are included, i. e. candidate paraphrase extraction and paraphrase validation, both of which are mainly based on web mining. Evaluations are conducted on a news title corpus and the presented method is compared with a paraphrasing method that exploits a Chinese thesaurus of synonyms -- Tongyi Cilin (Extended) (CilinE for short). Results show that the f-measure of our method (0. 4852) is significantly higher than that using CilinE (0. 1127). In addition, over 85% of the correct paraphrases derived by our method cannot be found in CilinE, which suggests that our method is effective in acquiring out-of-thesaurus paraphrases.