Jianyu Zhao

Jianyu Zhao, Chenyang Yang, Tingting Liu

Graph neural networks (GNNs) have been designed for learning a variety of wireless policies, i.e., the mappings from environment parameters to decision variables, thanks to their superior performance, and the potential in enabling scalability and size generalizability. These merits are rooted in leveraging permutation prior, i.e., satisfying the permutation property of the policy to be learned (referred to as desired permutation property). Many wireless policies are with complicated permutation properties. To satisfy these properties, heterogeneous GNNs (HetGNNs) should be used to learn such policies. There are two critical factors that enable a HetGNN to satisfy a desired permutation property: constructing an appropriate heterogeneous graph and judiciously designing the architecture of the HetGNN. However, both the graph and the HetGNN are designed heuristically so far. In this paper, we strive to provide a systematic approach for the design to satisfy the desired permutation property. We first propose a method for constructing a graph for a policy, where the edges and their types are defined for the sake of satisfying complicated permutation properties. Then, we provide and prove three sufficient conditions to design a HetGNN such that it can satisfy the desired permutation property when learning over an appropriate graph. These conditions suggest a method of designing the HetGNN with desired permutation property by sharing the processing, combining, and pooling functions according to the types of vertices and edges of the graph. We take power allocation and hybrid precoding policies as examples for demonstrating how to apply the proposed methods and validating the impact of the permutation prior by simulations.

Feihu Huang, Jianyu Zhao

Decentralized learning recently has received increasing attention in machine learning due to its advantages in implementation simplicity and system robustness, data privacy. Meanwhile, the adaptive gradient methods show superior performances in many machine learning tasks such as training neural networks. Although some works focus on studying decentralized optimization algorithms with adaptive learning rates, these adaptive decentralized algorithms still suffer from high sample complexity. To fill these gaps, we propose a class of faster adaptive decentralized algorithms (i.e., AdaMDOS and AdaMDOF) for distributed nonconvex stochastic and finite-sum optimization, respectively. Moreover, we provide a solid convergence analysis framework for our methods. In particular, we prove that our AdaMDOS obtains a near-optimal sample complexity of $\tilde{O}(ε^{-3})$ for finding an $ε$-stationary solution of nonconvex stochastic optimization. Meanwhile, our AdaMDOF obtains a near-optimal sample complexity of $O(\sqrt{n}ε^{-2})$ for finding an $ε$-stationary solution of nonconvex finite-sum optimization, where $n$ denotes the sample size. To the best of our knowledge, our AdaMDOF algorithm is the first adaptive decentralized algorithm for nonconvex finite-sum optimization. Some experimental results demonstrate efficiency of our algorithms.

Jianyu Zhao, Wei Quan, Bogdan J. Matuszewski

Estimating rigid objects' poses is one of the fundamental problems in computer vision, with a range of applications across automation and augmented reality. Most existing approaches adopt one network per object class strategy, depend heavily on objects' 3D models, depth data, and employ a time-consuming iterative refinement, which could be impractical for some applications. This paper presents a novel approach, CVAM-Pose, for multi-object monocular pose estimation that addresses these limitations. The CVAM-Pose method employs a label-embedded conditional variational autoencoder network, to implicitly abstract regularised representations of multiple objects in a single low-dimensional latent space. This autoencoding process uses only images captured by a projective camera and is robust to objects' occlusion and scene clutter. The classes of objects are one-hot encoded and embedded throughout the network. The proposed label-embedded pose regression strategy interprets the learnt latent space representations utilising continuous pose representations. Ablation tests and systematic evaluations demonstrate the scalability and efficiency of the CVAM-Pose method for multi-object scenarios. The proposed CVAM-Pose outperforms competing latent space approaches. For example, it is respectively 25% and 20% better than AAE and Multi-Path methods, when evaluated using the $\mathrm{AR_{VSD}}$ metric on the Linemod-Occluded dataset. It also achieves results somewhat comparable to methods reliant on 3D models reported in BOP challenges. Code available: https://github.com/JZhao12/CVAM-Pose

Jianyu Zhao, Yuyang Rong, Yiwen Guo et al.

Semantic understanding of programs has attracted great attention in the community. Inspired by recent successes of large language models (LLMs) in natural language understanding, tremendous progress has been made by treating programming language as another sort of natural language and training LLMs on corpora of program code. However, programs are essentially different from texts after all, in a sense that they are normally heavily structured and syntax-strict. In particular, programs and their basic units (i.e., functions and subroutines) are designed to demonstrate a variety of behaviors and/or provide possible outputs, given different inputs. The relationship between inputs and possible outputs/behaviors represents the functions/subroutines and profiles the program as a whole. Therefore, we propose to incorporate such a relationship into learning, for achieving a deeper semantic understanding of programs. To obtain inputs that are representative enough to trigger the execution of most part of the code, we resort to fuzz testing and propose fuzz tuning to boost the performance of program understanding and code representation learning, given a pre-trained LLM. The effectiveness of the proposed method is verified on two program understanding tasks including code clone detection and code classification, and it outperforms current state-of-the-arts by large margins. Code is available at https://github.com/rabbitjy/FuzzTuning.

Jiabo Huang, Jianyu Zhao, Yuyang Rong et al.

Large language models (LLMs) for natural language processing have been grafted onto programming language modeling for advancing code intelligence. Although it can be represented in the text format, code is syntactically more rigorous in order to be properly compiled or interpreted to perform a desired set of behaviors given any inputs. In this case, existing works benefit from syntactic representations to learn from code less ambiguously in the forms of abstract syntax tree, control-flow graph, etc. However, programs with the same purpose can be implemented in various ways showing different syntactic representations while the ones with similar implementations can have distinct behaviors. Though trivially demonstrated during executions, such semantics about functionality are challenging to be learned directly from code, especially in an unsupervised manner. Hence, in this paper, we propose FuzzPretrain to explore the dynamic information of programs revealed by their test cases and embed it into the feature representations of code as complements. The test cases are obtained with the assistance of a customized fuzzer and are only required during pre-training. FuzzPretrain yielded more than 6%/9% mAP improvements on code search over its counterparts trained with only source code or AST, respectively. Our extensive experimental results show the benefits of learning discriminative code representations with program executions.

Jianyu Zhao, Chenyang Yang

Deep reinforcement learning has been applied for a variety of wireless tasks, which is however known with high training and inference complexity. In this paper, we resort to deep deterministic policy gradient (DDPG) algorithm to optimize predictive power allocation among K mobile users requesting video streaming, which minimizes the energy consumption of the network under the no-stalling constraint of each user. To reduce the sampling complexity and model size of the DDPG, we exploit a kind of symmetric prior inherent in the actor and critic networks: permutation invariant and equivariant properties, to design the neural networks. Our analysis shows that the free model parameters of the DDPG can be compressed by 2/K^2. Simulation results demonstrate that the episodes required by the learning model with the symmetric prior to achieve the same performance as the vanilla policy reduces by about one third when K = 10.

Dong Liu, Jianyu Zhao, Chenyang Yang et al.

Predictive power allocation is conceived for energy-efficient video streaming over mobile networks using deep reinforcement learning. The goal is to minimize the accumulated energy consumption of each base station over a complete video streaming session under the constraint that avoids video playback interruptions. To handle the continuous state and action spaces, we resort to deep deterministic policy gradient (DDPG) algorithm for solving the formulated problem. In contrast to previous predictive power allocation policies that first predict future information with historical data and then optimize the power allocation based on the predicted information, the proposed policy operates in an on-line and end-to-end manner. By judiciously designing the action and state that only depend on slowly-varying average channel gains, we reduce the signaling overhead between the edge server and the base stations, and make it easier to learn a good policy. To further avoid playback interruption throughout the learning process and improve the convergence speed, we exploit the partially known model of the system dynamics by integrating the concepts of safety layer, post-decision state, and virtual experiences into the basic DDPG algorithm. Our simulation results show that the proposed policies converge to the optimal policy that is derived based on perfect large-scale channel prediction and outperform the first-predict-then-optimize policy in the presence of prediction errors. By harnessing the partially known model, the convergence speed can be dramatically improved.

Jianyu Zhao, Zhuoran Ji

Deep learning based natural language processing model is proven powerful, but need large-scale dataset. Due to the significant gap between the real-world tasks and existing Chinese corpus, in this paper, we introduce a large-scale corpus of informal Chinese. This corpus contains around 37 million book reviews and 50 thousand netizen's comments to the news. We explore the informal words frequencies of the corpus and show the difference between our corpus and the existing ones. The corpus can be further used to train deep learning based natural language processing tasks such as Chinese word segmentation, sentiment analysis.