With the recent success of embeddings in natural language processing, research has been conducted into applying similar methods to code analysis. Most works attempt to process the code directly or use a syntactic tree representation, treating it like sentences written in a natural language. However, none of the existing methods are sufficient to comprehend program semantics robustly, due to structural features such as function calls, branching, and interchangeable order of statements. In this paper, we propose a novel processing technique to learn code semantics, and apply it to a variety of program analysis tasks. In particular, we stipulate that a robust distributional hypothesis of code applies to both human- and machine-generated programs. Following this hypothesis, we define an embedding space, inst2vec, based on an Intermediate Representation (IR) of the code that is independent of the source programming language. We provide a novel definition of contextual flow for this IR, leveraging both the underlying data- and control-flow of the program. We then analyze the embeddings qualitatively using analogies and clustering, and evaluate the learned representation on three different high-level tasks. We show that even without fine-tuning, a single RNN architecture and fixed inst2vec embeddings outperform specialized approaches for performance prediction (compute device mapping, optimal thread coarsening); and algorithm classification from raw code (104 classes), where we set a new state-of-the-art.
Robust Image Semantic Coding with Learnable CSI Fusion Masking over MIMO Fading Channels
Shanghai Jiao Tong University(上海交通大学);The Chinese University of Hong Kong (Shenzhen)(香港中文大学(深圳));Shenzhen Research Institute of Big Data(深圳大数据研究院);Peng Cheng Laboratory(鹏城实验室);Khalifa University of Science and Technology(哈利法科技大学);CentraleSupelec(中央高等电力学院);University Paris-Saclay(巴黎萨克雷大学)
Learnable Residual-Based Latent Denoising in Semantic Communication
Department of Electronic Engineering, Shanghai Jiao Tong University(电子工程系,上海交通大学);School of Cyber and Engineering, Shanghai Jiao Tong University(网络与工程学院,上海交通大学);Department of Electrical and Computer Engineering, University of Delaware(电气与计算机工程系,德雷塞尔大学);State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications(网络与交换技术国家重点实验室,北京邮电大学)
Testing the Quantitative Spacetime Hypothesis using Artificial Narrative Comprehension (I) : Bootstrapping Meaning from Episodic Narrative viewed as a Feature Landscape
Learnable Structural Semantic Readout for Graph Classification
University of Illinois at Urbana-Champaign (UIUC)(伊利诺伊大学厄巴纳-香槟分校 (UIUC));Pohang University of Science and Technology (POSTECH)(浦项科技大学 (POSTECH));Korea Advanced Institute of Science and Technology (KAIST)(韩国科学技术院 (KAIST))
Narrowing the semantic gaps in U-Net with learnable skip connections: The case of medical image segmentation
Northeastern University(东北大学);Key Laboratory of Intelligent Computing in Medical Image of Ministry of Education(教育部医学图像智能计算重点实验室);DAMO Academy, Alibaba Group(阿里巴巴达摩院);University of Alberta(阿尔伯塔大学)
Structure Matters: Brain Graph Augmentation via Learnable Edge Masking for Data-efficient Psychiatric Diagnosis
Institute of Innovation, Science and Sustainability(创新、科学与可持续发展研究所);Federation University Australia(联邦大学澳大利亚分校);School of Information and Electronic Engineering(信息与电子工程学院);Zhejiang Gongshang University(浙江工商大学);School of Computing Technologies(计算技术学院);RMIT University(皇家墨尔本理工学院);School of Computing and Information Systems(计算与信息系统学院);The University of Melbourne(墨尔本大学)
Learnable Tree Filter for Structure-preserving Feature Transform
Megvii Research(旷视研究院);Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong Univeristy(西安交通大学人工智能与机器人研究所);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);University of Chinese Academy of Sciences(中国科学院大学);Megvii Inc. (Face++)(旷视科技(Face++))