Hao Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Hao Zhang has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
- Mingyue Cheng
University of Science and Technology of China
4 shared publications - Qi Liu
University of Science and Technology of China
4 shared publications - Enhong Chen
University of Science and Technology of China
3 shared publications - Rujiao Zhang
State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, Anhui Province, China
2 shared publications - Xiaoyu Tao
State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China
2 shared publications - Zhiding Liu
State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China
2 shared publications
Latest Publications
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 7422-7431
MixFormer: Co-Scaling Up Dense and Sequence in Industrial Recommenders
As industrial recommender systems enter a scaling-driven regime, Transformer architectures have become increasingly attractive for scaling models towards larger capacity and longer sequence. However, existing Transformer-based recommendation models remain structurally fragmented, where sequence modeling and feature interaction are implemented as separate modules with independent parameterization. Such designs introduce a fundamental co-scaling challenge, as model capacity must be suboptimally allocated between dense feature interaction and sequence modeling under a limited computational budget. In this work, we propose MixFormer, a unified Transformer-style architecture tailored for recommender systems, which jointly models sequential behaviors and feature interactions within a single backbone. Through a unified parameterization, MixFormer enables effective co-scaling across both dense capacity and sequence length, mitigating the trade-off observed in decoupled designs. Moreover, the integrated architecture facilitates deep interaction between sequential and non-sequential representations, allowing high-order feature semantics to directly inform sequence aggregation and enhancing overall expressiveness. To ensure industrial practicality, we further introduce a user-item decoupling strategy for efficiency optimizations that significantly reduce redundant computation and inference latency. Extensive experiments on large-scale industrial datasets demonstrate that MixFormer consistently exhibits superior accuracy and efficiency. Furthermore, large-scale online A/B tests on two production recommender systems, Douyin and Douyin Lite, show consistent improvements in user engagement metrics, including active days and in-app usage duration.
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 7422-7431
Open AccessMixFormer: Co-Scaling Up Dense and Sequence in Industrial Recommenders
As industrial recommender systems enter a scaling-driven regime, Transformer architectures have become increasingly attractive for scaling models towards larger capacity and longer sequence. However, existing Transformer-based recommendation models remain structurally fragmented, where sequence modeling and feature interaction are implemented as separate modules with independent parameterization. Such designs introduce a fundamental co-scaling challenge, as model capacity must be suboptimally allocated between dense feature interaction and sequence modeling under a limited computational budget. In this work, we propose MixFormer, a unified Transformer-style architecture tailored for recommender systems, which jointly models sequential behaviors and feature interactions within a single backbone. Through a unified parameterization, MixFormer enables effective co-scaling across both dense capacity and sequence length, mitigating the trade-off observed in decoupled designs. Moreover, the integrated architecture facilitates deep interaction between sequential and non-sequential representations, allowing high-order feature semantics to directly inform sequence aggregation and enhancing overall expressiveness. To ensure industrial practicality, we further introduce a user-item decoupling strategy for efficiency optimizations that significantly reduce redundant computation and inference latency. Extensive experiments on large-scale industrial datasets demonstrate that MixFormer consistently exhibits superior accuracy and efficiency. Furthermore, large-scale online A/B tests on two production recommender systems, Douyin and Douyin Lite, show consistent improvements in user engagement metrics, including active days and in-app usage duration.
- Top Cited PapersOpen Access
- 21 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 498-508
TimeMAE: Self-Supervised Representations of Time Series with Decoupled Masked Autoencoders
- 21 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 498-508
Top Cited PapersOpen AccessTimeMAE: Self-Supervised Representations of Time Series with Decoupled Masked Autoencoders
- Open Access
- 10 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 175-183
Cross-Domain Pre-training with Language Models for Transferable Time Series Representations
Pre-training universal models across multiple domains to enhance downstream tasks is a prevalent learning paradigm. However, there has been minimal progress in pre-training transferable models across domains for time series representation. This dilemma is incurred by two key factors: the limited availability of training set within each domain and the substantial differences in data characteristics between domains. To address these challenges, we present a novel framework, namely CrossTimeNet, designed to perform cross-domain self-supervised pre-training to benefit target tasks. Specifically, to address the issue of data scarcity, we utilize a pre-trained language model as the backbone network to effectively capture the sequence dependencies of the input time series. Meanwhile, we adopt the recovery of corrupted region inputs as a self-supervised optimization objective, taking into account the locality of the time series. To address discrepancies in data characteristics, we introduce a novel tokenization module that converts continuous time series inputs into discrete token sequences using vector quantization techniques. This approach facilitates the learning of transferable time series models across different domains. Extensive experimental results on diverse time series tasks, including classification and forecasting, demonstrate the effectiveness of our approach. Our codes are publicly available at https://github.com/Mingyue-Cheng/CrossTimeNet.
- 10 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 175-183
Open AccessCross-Domain Pre-training with Language Models for Transferable Time Series Representations
Pre-training universal models across multiple domains to enhance downstream tasks is a prevalent learning paradigm. However, there has been minimal progress in pre-training transferable models across domains for time series representation. This dilemma is incurred by two key factors: the limited availability of training set within each domain and the substantial differences in data characteristics between domains. To address these challenges, we present a novel framework, namely CrossTimeNet, designed to perform cross-domain self-supervised pre-training to benefit target tasks. Specifically, to address the issue of data scarcity, we utilize a pre-trained language model as the backbone network to effectively capture the sequence dependencies of the input time series. Meanwhile, we adopt the recovery of corrupted region inputs as a self-supervised optimization objective, taking into account the locality of the time series. To address discrepancies in data characteristics, we introduce a novel tokenization module that converts continuous time series inputs into discrete token sequences using vector quantization techniques. This approach facilitates the learning of transferable time series models across different domains. Extensive experimental results on diverse time series tasks, including classification and forecasting, demonstrate the effectiveness of our approach. Our codes are publicly available at https://github.com/Mingyue-Cheng/CrossTimeNet.
- Open Access
- 21 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 4288-4292
Learning the Dynamics in Sequential Recommendation by Exploiting Real-time Information
Sequential recommender systems offer personalized suggestions by modeling users' interactions chronologically to capture dynamic user interest. Existing approaches typically fail to adequately describe the dynamics of the entire recommender system, including shifts in both user interest and item availability. To address this, we propose a simple yet effective framework with three key perspectives, tailored to the dynamics of recommender system by fully exploiting the time information. Firstly, we propose a dynamic candidate set construction approach to prevent the model from learning future interactions. Secondly, assuming that user behaviors remain consistent over short terms but may evolve over long terms, we employ a interval-weighted optimization target to model the correlation of users' historical interactions. Finally, we introduce a specialized time-aware attention module to enhance recommendations within specific temporal contexts. Extensive experiments demonstrate the effectiveness and generalizability of our framework. We make our codes publicly available.
- 21 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 4288-4292
Open AccessLearning the Dynamics in Sequential Recommendation by Exploiting Real-time Information
Sequential recommender systems offer personalized suggestions by modeling users' interactions chronologically to capture dynamic user interest. Existing approaches typically fail to adequately describe the dynamics of the entire recommender system, including shifts in both user interest and item availability. To address this, we propose a simple yet effective framework with three key perspectives, tailored to the dynamics of recommender system by fully exploiting the time information. Firstly, we propose a dynamic candidate set construction approach to prevent the model from learning future interactions. Secondly, assuming that user behaviors remain consistent over short terms but may evolve over long terms, we employ a interval-weighted optimization target to model the correlation of users' historical interactions. Finally, we introduce a specialized time-aware attention module to enhance recommendations within specific temporal contexts. Extensive experiments demonstrate the effectiveness and generalizability of our framework. We make our codes publicly available.
- Open Access
- 13 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 1035-1038
Towards Personalized Evaluation of Large Language Models with An Anonymous Crowd-Sourcing Platform
Large language model evaluation plays a pivotal role in the enhancement of its capacity. Previously, numerous methods for evaluating large language models have been proposed in this area. Despite their effectiveness, these existing works mainly focus on assessing objective questions, overlooking the capability to evaluate subjective questions which is extremely common for large language models. Additionally, these methods predominantly utilize centralized datasets for evaluation, with question banks concentrated within the evaluation platforms themselves. Moreover, the evaluation processes employed by these platforms often overlook personalized factors, neglecting to consider the individual characteristics of both the evaluators and the models being evaluated. To address these limitations, we propose a novel anonymous crowd-sourcing evaluation platform, BingJian, for large language models that employs a competitive scoring mechanism where users participate in ranking models based on their performance. This platform stands out not only for its support of centralized evaluations to assess the general capabilities of models but also for offering an open evaluation gateway. Through this gateway, users have the opportunity to submit their questions, testing the models on a personalized and potentially broader range of capabilities. Furthermore, our platform introduces personalized evaluation scenarios, leveraging various forms of human-computer interaction to assess large language models in a manner that accounts for individual user preferences and contexts. The demonstration of BingJian can be accessed at https://github.com/Mingyue-Cheng/Bingjian.
- 13 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 1035-1038
Open AccessTowards Personalized Evaluation of Large Language Models with An Anonymous Crowd-Sourcing Platform
Large language model evaluation plays a pivotal role in the enhancement of its capacity. Previously, numerous methods for evaluating large language models have been proposed in this area. Despite their effectiveness, these existing works mainly focus on assessing objective questions, overlooking the capability to evaluate subjective questions which is extremely common for large language models. Additionally, these methods predominantly utilize centralized datasets for evaluation, with question banks concentrated within the evaluation platforms themselves. Moreover, the evaluation processes employed by these platforms often overlook personalized factors, neglecting to consider the individual characteristics of both the evaluators and the models being evaluated. To address these limitations, we propose a novel anonymous crowd-sourcing evaluation platform, BingJian, for large language models that employs a competitive scoring mechanism where users participate in ranking models based on their performance. This platform stands out not only for its support of centralized evaluations to assess the general capabilities of models but also for offering an open evaluation gateway. Through this gateway, users have the opportunity to submit their questions, testing the models on a personalized and potentially broader range of capabilities. Furthermore, our platform introduces personalized evaluation scenarios, leveraging various forms of human-computer interaction to assess large language models in a manner that accounts for individual user preferences and contexts. The demonstration of BingJian can be accessed at https://github.com/Mingyue-Cheng/Bingjian.
- 22 March 2019
- Published by Springer Nature in World Wide Web
- Vol. 23 (2) , 991-1010
MALDC: a depth detection method for malware based on behavior chains
- 22 March 2019
- Published by Springer Nature in World Wide Web
- Vol. 23 (2) , 991-1010
MALDC: a depth detection method for malware based on behavior chains