Da Zheng

Da Zheng

Auto-generated profile, based on publicly available information

Da Zheng

Ant Group, Hangzhou, 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
SZShichang Zhang
Shichang Zhang
JZJiani Zhang
Jiani Zhang
XSXiang Song
Xiang Song
SASoji Adeshina
Soji Adeshina
DZDa Zheng
Da Zheng
YSYizhou Sun
Yizhou Sun
Transparency and accountability have become major concerns for black-box machine learning (ML) models. Proper explanations for the model behavior increase model transparency and help researchers develop more accountable models. Graph neural networks (GNN) have recently shown superior performance in many graph ML problems than traditional methods, and explaining them has attracted increased interest. However, GNN explanation for link prediction (LP) is lacking in the literature. LP is an essential GNN task and corresponds to web applications like recommendation and sponsored search on web. Given existing GNN explanation methods only address node/graph-level tasks, we propose Path-based GNN Explanation for heterogeneous Link prediction (PaGE-Link) that generates explanations with connection interpretability, enjoys model scalability, and handles graph heterogeneity. Qualitatively, PaGE-Link can generate explanations as paths connecting a node pair, which naturally captures connections between the two nodes and easily transfer to human-interpretable explanations. Quantitatively, explanations generated by PaGE-Link improve AUC for recommendation on citation and user-item graphs by 9 - 35% and are chosen as better by 78.79% of responses in human evaluation.

4 August 2023 in Proceedings of the Acm Sigkdd Conference on Knowledge Discovery and Data Mining
Verified
Conference Paper
Open access
HXHan Xie
Han Xie
DZDa Zheng
Da Zheng
JMJun Ma
Jun Ma
HZHouyu Zhang
Houyu Zhang
VIVassilis N. Ioannidis
Vassilis N. Ioannidis
TCTrishul Chilimbi
Trishul Chilimbi
Model pre-training on large text corpora has been demonstrated effective for various downstream applications in the NLP domain. In the graph mining domain, a similar analogy can be drawn for pre-training graph models on large graphs in the hope of benefiting downstream graph applications, which has also been explored by several recent studies. However, no existing study has ever investigated the pre-training of text plus graph models on large heterogeneous graphs with abundant textual information (a.k.a. large graph corpora) and then fine-tuning the model on different related downstream applications with different graph schemas. To address this problem, we propose a framework of graph-aware language model pre-training (GaLM) on a large graph corpus, which incorporates large language models and graph neural networks, and a variety of fine-tuning methods on downstream applications. We conduct extensive experiments on Amazon's real internal datasets and large public datasets. Comprehensive empirical results and in-depth analysis demonstrate the effectiveness of our proposed methods along with lessons learned.

11 November 2023
Verified
Conference Paper
Open access
HZhongkuan zhou
hongkuan zhou
DZDa Zheng
Da Zheng
XSXiang Song
Xiang Song
GKGeorge Karypis
George Karypis
VPViktor Prasanna
Viktor Prasanna

8 May 2025
Verified
Conference Paper
Open access
YLYujie Luo
Yujie Luo
XRXiangyuan Ru
Xiangyuan Ru
KLKangwei Liu
Kangwei Liu
LYLin Yuan
Lin Yuan
MSMengshu Sun
Mengshu Sun
HCHuajun Chen
Huajun Chen

11 November 2023
Verified
Conference Paper
Open access
SCShiyang Chen
Shiyang Chen
DZDa Zheng
Da Zheng
CDCaiwen Ding
Caiwen Ding
CHChengying Huan
Chengying Huan
YJYuede Ji
Yuede Ji
HLHang Liu
Hang Liu
Graph learning is becoming increasingly popular due to its superior performance in tackling many grand challenges. While quantization is widely used to accelerate Graph Neural Network (GNN) computation, quantized training faces remarkable roadblocks. Current quantized GNN training systems often experience longer training time than their full-precision counterparts for two reasons: (i) addressing the quantization accuracy challenge leads to excessive overhead, and (ii) the optimization potential exposed by quantization is not adequately leveraged. This paper introduces Tango which re-thinks quantization challenges and opportunities for graph neural network training on GPUs with three contributions: Firstly, we introduce efficient rules to maintain accuracy during quantized GNN training. Secondly, we design and implement quantization-aware primitives and inter-primitive optimizations to speed up GNN training. Finally, we integrate Tango with the popular Deep Graph Library (DGL) system and demonstrate its superior performance over the state-of-the-art approaches on various GNN models and datasets.

27 April 2024
Verified
Conference Paper
Open access
ZWZheng Wang
Zheng Wang
YWYuke Wang
Yuke Wang
JDJiaqi Deng
Jiaqi Deng
DZDa Zheng
Da Zheng
ALAng Li
Ang Li
YDYufei Ding
Yufei Ding
Ensuring high-quality recommendations for newly onboarded users requires the continuous retraining of Deep Learning Recommendation Models (DLRMs) with freshly generated data. To serve the online DLRM retraining, existing solutions use hundreds of CPU computing nodes designated for input preprocessing, causing significant power consumption that surpasses even the power usage of GPU trainers. To this end, we propose RAP, an end-to-end DLRM training framework that supports Resource-aware Automated GPU sharing for DLRM input Preprocessing and Training. The core idea of RAP is to accurately capture the remaining GPU computing resources during DLRM training for input preprocessing, achieving superior training efficiency without requiring additional resources. Specifically, RAP utilizes a co-running cost model to efficiently assess the costs of various input preprocessing operations, and it implements a resource-aware horizontal fusion technique that adaptively merges smaller kernels according to GPU availability, circumventing any interference with DLRM training. In addition, RAP leverages a heuristic searching algorithm that jointly optimizes both the input preprocessing graph mapping and the co-running schedule to maximize the end-to-end DLRM training throughput. The comprehensive evaluation shows that RAP achieves 1.99× speedup on average over the sequential GPU-based DLRM input preprocessing baseline. In addition, the end-to-end training throughput of RAP is only 3.24% lower than the ideal case, which has no input preprocessing overhead.