Jin Zhang

Jin Zhang

Auto-generated profile, based on publicly available information

Jin Zhang

School of Artificial Intelligence and Data Science, University of Science and Technology of China, Hefei, Anhui, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
30 April 2023
Verified
Conference Paper
Open access
ZLZepu Lu
Zepu Lu
DLDefu Lian
Defu Lian
JZJin Zhang
Jin Zhang
ZZZaixi Zhang
Zaixi Zhang
CFChao Feng
Chao Feng
ECEnhong Chen
Enhong Chen
Vector quantization techniques, such as Product Quantization (PQ), play a vital role in approximate nearest neighbor search (ANNs) and maximum inner product search (MIPS) owing to their remarkable search and storage efficiency. However, the indexes in vector quantization cannot be trained together with the inference models since data indexing is not differentiable. To this end, differentiable vector quantization approaches, such as DiffPQ and DeepPQ, have been recently proposed, but existing methods have two drawbacks. First, they do not impose any constraints on codebooks, such that the resultant codebooks lack diversity, leading to limited retrieval performance. Second, since data indexing resorts to operator, differentiability is usually achieved by either relaxation or Straight-Through Estimation (STE), which leads to biased gradient and slow convergence. To address these problems, we propose a Differentiable Optimized Product Quantization method (DOPQ) and beyond in this paper. Particularly, each data is projected into multiple orthogonal spaces, to generate multiple views of data. Thus, each codebook is learned with one view of data, guaranteeing the diversity of codebooks. Moreover, instead of simple differentiable relaxation, DOPQ optimizes the loss based on direct loss minimization, significantly reducing the gradient bias problem. Finally, DOPQ is evaluated with seven datasets of both recommendation and image search tasks. Extensive experimental results show that DOPQ outperforms state-of-the-art baselines by a large margin.

26 December 2025 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
ZLZe Liu
Ze Liu
JZJin Zhang
Jin Zhang
DLDefu Lian
Defu Lian
CFChao Feng
Chao Feng
JWJie Wang
Jie Wang
ECEnhong Chen
Enhong Chen
With the advancement of deep learning, deep recommendation models have achieved remarkable improvements in recommendation accuracy. However, due to the large number of candidate items in practice and the high cost of preference computation, these methods still suffer from low recommendation efficiency. The recently proposed tree-based deep recommendation models alleviate the problem by directly learning tree structure and representations under the guidance of recommendation objectives. To guarantee the effectiveness of beam search for recommendation accuracy, these models strive to ensure that the tree adheres to the max-heap assumption, where a parent node’s preference should be the maximum among its children’s preferences. However, they employ a one-versus-all strategy, framing the training task as a series of independent binary classification objectives for each node, which limits their ability to fully satisfy the max-heap assumption. To this end, we propose a Deep Tree-based Retriever (DTR for short) for efficient recommendation. DTR frames the training task as a softmax-based multi-class classification over tree nodes at the same level, enabling explicit horizontal competition and more discriminative top-k selection among them, which mimics the beam search behavior during training. To mitigate the suboptimality induced by the labeling of non-leaf nodes, we propose a rectification method for the loss function, which further aligns with the max-heap assumption in expectation. As the number of tree nodes grows exponentially with the levels, we employ sampled softmax to approximate optimization and thereby enhance efficiency. Furthermore, we propose a tree-based sampling method to reduce the bias inherent in sampled softmax. Theoretical results reveal DTR’s generalization capability, and both the rectification method and tree-based sampling contribute to improved generalization. The experiments are conducted on four real-world datasets, validating the effectiveness of the proposed method.

24 March 2026 in Artificial Intelligence
Verified
Journal Article
Closed access
JZJin Zhang
Jin Zhang
DLDefu Lian
Defu Lian
HXHong Xie
Hong Xie
YLYawen Li
Yawen Li
ECEnhong Chen
Enhong Chen

27 October 2025
Verified
Conference Paper
Open access
MYMianzimei Yang
Mianzimei Yang
ZZZhipeng Zhou
Zhipeng Zhou
JZJin Zhang
Jin Zhang
YPYuanhao Pu
Yuanhao Pu
HXHong Xie
Hong Xie
DLDefu Lian
Defu Lian