Tianhao Wu
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
Tianhao Wu has a total of 29 co-authors. Here are the top co-authors by number of shared publications:
- Zhongyi Huang
Tsinghua University, Beijing, China
4 shared publications - Da Yan
Indiana University Bloomington, Bloomington, USA
3 shared publications - Qihao Cheng
Tsinghua University, Beijing, China
3 shared publications - Bo Bai
Huawei Technologies Company Ltd., Shenzhen, China
2 shared publications - Chaorui Zhang
Information Engineering, Chinese University of Hong Kong, 26451 New Territories Hong Kong
2 shared publications - He Wang
Peking University
2 shared publications
Latest Publications
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 568-579
NodeBits: A Plug-and-Play Framework for Accelerating Graph Inference by Post-Hoc Binary Quantization
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 568-579
Open AccessNodeBits: A Plug-and-Play Framework for Accelerating Graph Inference by Post-Hoc Binary Quantization
- Open Access
- 8 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 710-719
CompreGel: Efficient Distributed Graph Propagation via Error-Bounded Lossy Message Compression
- 8 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 710-719
Open AccessCompreGel: Efficient Distributed Graph Propagation via Error-Bounded Lossy Message Compression
- Open Access
- 10 February 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Management of Data
- Vol. 3 (1) , 1-26
Computing Approximate Graph Edit Distance via Optimal Transport
Given a graph pair (G 1 , G 2 ), graph edit distance (GED) is defined as the minimum number of edit operations converting G 1 to G 2 . GED is a fundamental operation widely used in many applications, but its exact computation is NP-hard, so the approximation of GED has gained a lot of attention. Data-driven learning-based methods have been found to provide superior results compared to classical approximate algorithms, but they directly fit the coupling relationship between a pair of vertices from their vertex features. We argue that while pairwise vertex features can capture the coupling cost (discrepancy) of a pair of vertices, the vertex coupling matrix should be derived from the vertex-pair cost matrix through a more well-established method that is aware of the global context of the graph pair, such as optimal transport. In this paper, we propose an ensemble approach that integrates a supervised learning-based method and an unsupervised method, both based on optimal transport. Our learning method, GEDIOT, is based on inverse optimal transport that leverages a learnable Sinkhorn algorithm to generate the coupling matrix. Our unsupervised method, GEDGW, models GED computation as a linear combination of optimal transport and its variant, Gromov-Wasserstein discrepancy, for node and edge operations, respectively, which can be solved efficiently without needing the ground truth. Our ensemble method, GEDHOT, combines GEDIOT and GEDGW to further boost the performance. Extensive experiments demonstrate that our methods significantly outperform the existing methods in terms of the performance of GED computation, edit path generation, and model generalizability.
- 10 February 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Management of Data
- Vol. 3 (1) , 1-26
Open AccessComputing Approximate Graph Edit Distance via Optimal Transport
Given a graph pair (G 1 , G 2 ), graph edit distance (GED) is defined as the minimum number of edit operations converting G 1 to G 2 . GED is a fundamental operation widely used in many applications, but its exact computation is NP-hard, so the approximation of GED has gained a lot of attention. Data-driven learning-based methods have been found to provide superior results compared to classical approximate algorithms, but they directly fit the coupling relationship between a pair of vertices from their vertex features. We argue that while pairwise vertex features can capture the coupling cost (discrepancy) of a pair of vertices, the vertex coupling matrix should be derived from the vertex-pair cost matrix through a more well-established method that is aware of the global context of the graph pair, such as optimal transport. In this paper, we propose an ensemble approach that integrates a supervised learning-based method and an unsupervised method, both based on optimal transport. Our learning method, GEDIOT, is based on inverse optimal transport that leverages a learnable Sinkhorn algorithm to generate the coupling matrix. Our unsupervised method, GEDGW, models GED computation as a linear combination of optimal transport and its variant, Gromov-Wasserstein discrepancy, for node and edge operations, respectively, which can be solved efficiently without needing the ground truth. Our ensemble method, GEDHOT, combines GEDIOT and GEDGW to further boost the performance. Extensive experiments demonstrate that our methods significantly outperform the existing methods in terms of the performance of GED computation, edit path generation, and model generalizability.
- Open Access
- 26 May 2023
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Management of Data
- Vol. 1 (1) , 1-26
ClipSim: A GPU-friendly Parallel Framework for Single-Source SimRank with Accuracy Guarantee
SimRank is an important metric to measure the topological similarity between two nodes in a graph. In particular, single-source and top-k SimRank has numerous applications in recommendation systems, network analysis, and web mining, etc. Mathematically, given a vertex, the computation of single-machine and single-source SimRank mainly lies in matrix-matrix operations. However, it is almost impossible to directly compute on large graphs. Thus, existing works yield to two main operations: a series of random walks, and sparse matrix and dense vector multiplication operations. This brings about high computation cost for SimRank on large graphs. In real-world applications, there is always the query time and accuracy trade-off, which hinders the computation of high-precision SimRank on large-scale graphs. To handle this problem, this paper proposesClipSim, the first GPU-friendly parallel framework that accelerates the single-source SimRank on GPU with accuracy guarantee. We design a novel data structure and GPU-friendly parallel algorithms for efficient computation of all the operations of SimRank on GPU. Moreover, our theoretical derivation enables ClipSim to largely reduce the number of random walks required for each node, while maintaining the same theoretical accuracy as the state-of-the-art algorithm, ExactSim. We conduct extensive experiments on real-world and synthetic datasets to demonstrate the accuracy and efficiency of ClipSim. The results show that compared with ExactSim, ClipSim obtains single-source SimRank vectors with the same accuracy and up to 160× faster computation time.
- 26 May 2023
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Management of Data
- Vol. 1 (1) , 1-26
Open AccessClipSim: A GPU-friendly Parallel Framework for Single-Source SimRank with Accuracy Guarantee
SimRank is an important metric to measure the topological similarity between two nodes in a graph. In particular, single-source and top-k SimRank has numerous applications in recommendation systems, network analysis, and web mining, etc. Mathematically, given a vertex, the computation of single-machine and single-source SimRank mainly lies in matrix-matrix operations. However, it is almost impossible to directly compute on large graphs. Thus, existing works yield to two main operations: a series of random walks, and sparse matrix and dense vector multiplication operations. This brings about high computation cost for SimRank on large graphs. In real-world applications, there is always the query time and accuracy trade-off, which hinders the computation of high-precision SimRank on large-scale graphs. To handle this problem, this paper proposesClipSim, the first GPU-friendly parallel framework that accelerates the single-source SimRank on GPU with accuracy guarantee. We design a novel data structure and GPU-friendly parallel algorithms for efficient computation of all the operations of SimRank on GPU. Moreover, our theoretical derivation enables ClipSim to largely reduce the number of random walks required for each node, while maintaining the same theoretical accuracy as the state-of-the-art algorithm, ExactSim. We conduct extensive experiments on real-world and synthetic datasets to demonstrate the accuracy and efficiency of ClipSim. The results show that compared with ExactSim, ClipSim obtains single-source SimRank vectors with the same accuracy and up to 160× faster computation time.
- Open Access
Domain Randomization-Enhanced Depth Simulation and Restoration for Perceiving and Grasping Specular and Transparent Objects
Commercial depth sensors usually generate noisy and missing depths, especially on specular and transparent objects, which poses critical issues to downstream depth or point cloud-based tasks. To mitigate this problem, we propose a powerful RGBD fusion network, SwinDRNet, for depth restoration. We further propose Domain Randomization-Enhanced Depth Simulation (DREDS) approach to simulate an active stereo depth system using physically based rendering and generate a large-scale synthetic dataset that contains 130K photorealistic RGB images along with their simulated depths carrying realistic sensor noises. To evaluate depth restoration methods, we also curate a real-world dataset, namely STD, that captures 30 cluttered scenes composed of 50 objects with different materials from specular, transparent, to diffuse. Experiments demonstrate that the proposed DREDS dataset bridges the sim-to-real domain gap such that, trained on DREDS, our SwinDRNet can seamlessly generalize to other real depth datasets, e.g. ClearGrasp, and outperform the competing methods on depth restoration with a real-time speed. We further show that our depth restoration effectively boosts the performance of downstream tasks, including category-level pose estimation and grasping tasks. Our data and code are available at https://github.com/PKU-EPIC/DREDS
Open AccessDomain Randomization-Enhanced Depth Simulation and Restoration for Perceiving and Grasping Specular and Transparent Objects
Commercial depth sensors usually generate noisy and missing depths, especially on specular and transparent objects, which poses critical issues to downstream depth or point cloud-based tasks. To mitigate this problem, we propose a powerful RGBD fusion network, SwinDRNet, for depth restoration. We further propose Domain Randomization-Enhanced Depth Simulation (DREDS) approach to simulate an active stereo depth system using physically based rendering and generate a large-scale synthetic dataset that contains 130K photorealistic RGB images along with their simulated depths carrying realistic sensor noises. To evaluate depth restoration methods, we also curate a real-world dataset, namely STD, that captures 30 cluttered scenes composed of 50 objects with different materials from specular, transparent, to diffuse. Experiments demonstrate that the proposed DREDS dataset bridges the sim-to-real domain gap such that, trained on DREDS, our SwinDRNet can seamlessly generalize to other real depth datasets, e.g. ClearGrasp, and outperform the competing methods on depth restoration with a real-time speed. We further show that our depth restoration effectively boosts the performance of downstream tasks, including category-level pose estimation and grasping tasks. Our data and code are available at https://github.com/PKU-EPIC/DREDS
- 23 October 2022
- Published by Springer Nature
- p. 374-391
Domain Randomization-Enhanced Depth Simulation and Restoration for Perceiving and Grasping Specular and Transparent Objects
- 23 October 2022
- Published by Springer Nature
- p. 374-391
Domain Randomization-Enhanced Depth Simulation and Restoration for Perceiving and Grasping Specular and Transparent Objects
- 21 September 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Wireless Communications
- Vol. 21 (4) , 2462-2475
A Novel AI-Based Framework for AoI-Optimal Trajectory Planning in UAV-Assisted Wireless Sensor Networks
Information freshness, which is characterized by a new performance metric called age of information (AoI), significantly influences decision making in numerous applications. In wireless sensor networks, unmanned aerial vehicle (UAV) has been widely adopted for fresh data collection. The key to applying UAV lies in UAV trajectory planning. Considering several fixed waypoints in UAV trajectory, the trajectory planning is an NP-hard combinatorial optimization problem, and is difficult to solve in practice. To well balance between the accuracy and efficiency, we propose an end-to-end AI-based framework in this paper to deal with the UAV trajectory planning within two stages. First, the hover positions of UAV and data transmission time are decided using a clustering module. Then, the AoI-minimal flight path is obtained through a neural trajectory solver. Compared with classic heuristic algorithms, the proposed AI-based framework achieves a smaller AoI with two orders of magnitude lower computational time. Besides, the proposed AI-based framework can be easily generalized to larger-scale scenarios (e.g., up to 2,000 sensor nodes) which cannot be solved by exact algorithms (e.g., dynamic programming) in a limited time. Moreover, the AI-based framework is comparable in accuracy with the commercial open-source solver Google OR-tools, but the efficiency is increased by 200%.
- 21 September 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Wireless Communications
- Vol. 21 (4) , 2462-2475
A Novel AI-Based Framework for AoI-Optimal Trajectory Planning in UAV-Assisted Wireless Sensor Networks
Information freshness, which is characterized by a new performance metric called age of information (AoI), significantly influences decision making in numerous applications. In wireless sensor networks, unmanned aerial vehicle (UAV) has been widely adopted for fresh data collection. The key to applying UAV lies in UAV trajectory planning. Considering several fixed waypoints in UAV trajectory, the trajectory planning is an NP-hard combinatorial optimization problem, and is difficult to solve in practice. To well balance between the accuracy and efficiency, we propose an end-to-end AI-based framework in this paper to deal with the UAV trajectory planning within two stages. First, the hover positions of UAV and data transmission time are decided using a clustering module. Then, the AoI-minimal flight path is obtained through a neural trajectory solver. Compared with classic heuristic algorithms, the proposed AI-based framework achieves a smaller AoI with two orders of magnitude lower computational time. Besides, the proposed AI-based framework can be easily generalized to larger-scale scenarios (e.g., up to 2,000 sensor nodes) which cannot be solved by exact algorithms (e.g., dynamic programming) in a limited time. Moreover, the AI-based framework is comparable in accuracy with the commercial open-source solver Google OR-tools, but the efficiency is increased by 200%.