ZCZhongteng Cai

Zhongteng Cai

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Zhongteng Cai has a total of 12 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Graph Neural Network-Enhanced Reinforcement Learning for Payment Channel Rebalancing

    by Wuhui Chen, Xiaoyu Qiu, Zhongteng Cai, Bingxin Tang, Linlin Du, Zibin Zheng

    Building on top of blockchain, payment channel networks-backed (PCNs) cryptocurrencies emerge as a promising solution for a mobile payment system with fewer intermediaries, more security, higher speed, and lower cost. A key problem for PCN is payment channel rebalancing, that is, finding a set of circular transactions that restore a PCN with skewed channel balances back into an equilibrium state. However, existing practice on payment channel rebalancing either has a hard limit on the problem size or tends to fall into local optimum. To address these challenges, we propose DRL-PCR, a D eep R einforcement L earning-based P ayment C hannel R ebalancing algorithm. On one hand, DRL-PCR leverages the strong approximation ability of deep neural networks to handle large problem spaces. On the other hand, DRL-PCR decomposes the rebalancing problem into a sequence of decision-making problems and progressively builds the final solution. By aiming to find a globally optimized solution and solving the long-term optimization model of DRL, DRL-PCR is superior to greedy-based algorithms and can mitigate the risk of getting trapped in a local optimum. In particular, payment channel rebalancing typically involves dealing with graph-structured data, where the major obstacle lies in understanding the sophisticated circular dependencies between payment channels and routing paths. DRL-PCR achieves this by encoding the input data with a novel graph neural network-based model and capturing the circular dependencies through a customized message passing process. In addition, considering the distributed nature of PCN, DRL-PCR uses a leadership election protocol to elect leaders for decision-making. Evaluations on the historical data of two real-world PCNs demonstrate that DRL-PCR can restore the PCN to a more balanced state and improve the transaction throughput and success ratios by up to 2.1x and 1.6x, respectively.


  • MDRL-IR: Incentive Routing for Blockchain Scalability With Memory-Based Deep Reinforcement Learning

    by Bingxin Tang, Junyuan Liang, Zhongteng Cai, Ting Cai, Xiaocong Zhou, Yingye Chen

    Blockchain-based cryptocurrencies have developed rapidly in recent years, however, scalability is one of the biggest challenge. Payment channel networks (PCNs) are one of the important solutions to blockchain scalability and routing is the most critical problem in PCN. Routing algorithms in PCNs have evolved fast and achieved high throughput. However, most of these routing algorithms are designed from the perspective of technical feasibility, and few algorithms focus on the incentives of each off-chain participant, especially the economic incentives for intermediate routing nodes. Besides, due to the highly dynamic nature of off-chain channel deposits, existing routing algorithms rely heavily on channel deposit probing in order to ensure high throughput. In this paper, we design routing algorithms from an incentive perspective to improve the profit of intermediate nodes and use deep learning to reduce the dependency of off-chain routing on channel deposit probing. Our experiments show that under the same model, MDRL-IR can increase the profit of intermediate nodes by up to 1.87x and increase the throughput by up to 2.0x compared to the state-of-the-art routing algorithm, while ensuring that the user routing cost per unit throughput remains unchanged. Moreover, approximate performance can be achieved when deposit probing is greatly reduced.


  • Benzene: Scaling Blockchain With Cooperation-Based Sharding

    by Zhongteng Cai, Junyuan Liang, Wuhui Chen, Zicong Hong, Hong-Ning Dai, Jianting Zhang, Zibin Zheng

    Sharding has been considered as a prominent approach to enhance the limited performance of blockchain. However, most sharding systems leverage a non-cooperative design, which lowers the fault tolerance resilience due to the decreased mining power as the consensus execution is limited to each separated shard. To this end, we present Benzene, a novel sharding system that enhances the performance by cooperation-based sharding while defending the per-shard security. Firstly, we establish a double-chain architecture for function decoupling. This architecture separates transaction-recording functions from consensus-execution functions, thereby enabling the cross-shard cooperation during consensus execution while preserving the concurrency nature of sharding. Secondly, we design a cross-shard block verification mechanism leveraging Trusted Execution Environment (TEE), via which miners can verify blocks from other shards during the cooperation process with the minimized overheads. Finally, we design a voting-based consensus protocol for cross-shard cooperation. Transactions in each shard are confirmed by all shards that simultaneously cast votes, consequently achieving an enhanced fault tolerance and lowering the confirmation latency. We implement Benzene and conduct both prototype experiments and large-scale simulations to evaluate the performance of Benzene. Results show that Benzene achieves superior performance than existing sharding/non-sharding blockchain protocols. In particular, Benzene achieves a linearly-improved throughput with the increased number of shards (e.g., 32,370 transactions per second with 50 shards) and maintains a lower confirmation latency than Bitcoin (with more than 50 shards). Meanwhile, Benzene maintains a fixed fault tolerance at 1/3 even with the increased number of shards.