As Pre-trained Language Models (PLMs), a popular approach for code intelligence, continue to grow in size, the computational cost of their usage has become prohibitively expensive. Prompt learning, a recent development in the field of natural language processing, emerges as a potential solution to address this challenge. In this paper, we investigate the effectiveness of prompt learning in code intelligence tasks. We unveil its reliance on manually designed prompts, which often require significant human effort and expertise. Moreover, we discover existing automatic prompt design methods are very limited to code intelligence tasks due to factors including gradient dependence, high computational demands, and limited applicability. To effectively address both issues, we propose Genetic Auto Prompt (GenAP), which utilizes an elaborate genetic algorithm to automatically design prompts. With GenAP, non-experts can effortlessly generate superior prompts compared to meticulously manual-designed ones. GenAP operates without the need for gradients or additional computational costs, rendering it gradient-free and cost-effective. Moreover, GenAP supports both understanding and generation types of code intelligence tasks, exhibiting great applicability. We conduct GenAP on three popular code intelligence PLMs with three canonical code intelligence tasks including defect prediction, code summarization, and code translation. The results suggest that GenAP can effectively automate the process of designing prompts. Specifically, GenAP outperforms all other methods across all three tasks (e.g., improving accuracy by an average of 2.13% for defect prediction). To the best of our knowledge, GenAP is the first work to automatically design prompts for code intelligence PLMs.
Evolutionary neural architecture search (ENAS) employs evolutionary algorithms to find high-performing neural architectures automatically, and has achieved great success. However, compared to the empirical success, its rigorous theoretical analysis has yet to be touched. This work goes preliminary steps toward the mathematical runtime analysis of ENAS. In particular, we define a binary classification problem UNIFORM, and formulate an explicit fitness function to represent the relationship between neural architecture and classification accuracy. Furthermore, we consider (1+1)-ENAS algorithm with mutation to optimize the neural architecture, and obtain the following runtime bounds: 1) the one-bit mutation finds the optimum in an expected runtime of $O(n)$ and $\Omega(\log n)$; 2) the multi-bit mutation finds the optimum in an expected runtime of $\Theta(n)$. These theoretical results show that one-bit and multi-bit mutations achieve nearly the same performance on UNIFORM. We provide insight into the choices of mutation in the ENAS community: although multi-bit mutation can change the step size to prevent a local trap, this may not always improve runtime. Empirical results also verify the equivalence of these two mutation operators. This work begins the runtime analysis of ENAS, laying the foundation for further theoretical studies to guide the design of ENAS.
In contrast to extensive studies on general vision, pre-training for scalable visual autonomous driving remains seldom explored. Visual autonomous driving applications require features encompassing semantics, 3D geometry, and temporal information simultaneously for joint perception, prediction, and planning, posing dramatic challenges for pre-training. To resolve this, we bring up a new pre-training task termed as visual point cloud forecasting - predicting future point clouds from historical visual input. The key merit of this task captures the synergic learning of semantics, 3D structures, and temporal dynamics. Hence it shows superiority in various downstream tasks. To cope with this new problem, we present ViDAR, a general model to pre-train downstream visual encoders. It first extracts historical embeddings by the encoder. These representations are then transformed to 3D geometric space via a novel Latent Rendering operator for future point cloud prediction. Experiments show significant gain in downstream tasks, e.g., 3.1% NDS on 3D detection, ~10% error reduction on motion forecasting, and ~15% less collision rate on planning.
Decentralized training of large language models has emerged as an effective way to democratize this technology. However, the potential threats associated with this approach have not been carefully discussed, which would hinder the development of decentralized training infrastructures. This paper aims to initiate discussion towards this end by exploring the robustness of decentralized training from three main perspectives. First, we demonstrate the vulnerabilities inherent in decentralized training frameworks in terms of hardware, data, and models. Second, we highlight the fundamental difference between decentralized foundation model training and vanilla federated learning, where the security techniques employed in federated learning cannot be applied directly. Third, we discuss the essential components required for a robust and efficient decentralized training framework and present a case study by modeling a concrete threat model. Our objective in this vision paper is to emphasize the importance of addressing security concerns in the context of decentralized training for large language models.
Large-scale joint training of multimodal models, e.g., CLIP, have demonstrated great performance in many vision-language tasks. However, image-text pairs for pre-training are restricted to the intersection of images and texts, limiting their ability to cover a large distribution of real-world data, where noise can also be introduced as misaligned pairs during pre-processing. Conversely, unimodal models trained on text or image data alone through unsupervised techniques can achieve broader coverage of diverse real-world data and are not constrained by the requirement of simultaneous presence of image and text. In this paper, we demonstrate that using large-scale unsupervised unimodal models as pre-training can enhance the zero-shot performance of image-text pair models. Our thorough studies validate that models pre-trained as such can learn rich representations of both modalities, improving their ability to understand how images and text relate to each other. Our experiments show that unimodal pre-training outperforms state-of-the-art CLIP-based models by 6.5% (52.3% $\rightarrow$ 58.8%) on PASCAL-5$^i$ and 6.2% (27.2% $\rightarrow$ 33.4%) on COCO-20$^i$ semantic segmentation under zero-shot setting respectively. By learning representations of both modalities, unimodal pre-training offers broader coverage, reduced misalignment errors, and the ability to capture more complex features and patterns in the real-world data resulting in better performance especially for zero-shot vision-language tasks.
Symbolic regression (SR) is the process of discovering hidden relationships from data with mathematical expressions, which is considered an effective way to reach interpretable machine learning (ML). Genetic programming (GP) has been the dominator in solving SR problems. However, as the scale of SR problems increases, GP often poorly demonstrates and cannot effectively address the real-world high-dimensional problems. This limitation is mainly caused by the stochastic evolutionary nature of traditional GP in constructing the trees. In this paper, we propose a differentiable approach named DGP to construct GP trees towards high-dimensional SR for the first time. Specifically, a new data structure called differentiable symbolic tree is proposed to relax the discrete structure to be continuous, thus a gradient-based optimizer can be presented for the efficient optimization. In addition, a sampling method is proposed to eliminate the discrepancy caused by the above relaxation for valid symbolic expressions. Furthermore, a diversification mechanism is introduced to promote the optimizer escaping from local optima for globally better solutions. With these designs, the proposed DGP method can efficiently search for the GP trees with higher performance, thus being capable of dealing with high-dimensional SR. To demonstrate the effectiveness of DGP, we conducted various experiments against the state of the arts based on both GP and deep neural networks. The experiment results reveal that DGP can outperform these chosen peer competitors on high-dimensional regression benchmarks with dimensions varying from tens to thousands. In addition, on the synthetic SR problems, the proposed DGP method can also achieve the best recovery rate even with different noisy levels. It is believed this work can facilitate SR being a powerful alternative to interpretable ML for a broader range of real-world problems.
Facial expression is one of the most powerful, natural, and universal signals for human beings to express emotional states and intentions. Thus, it is evident the importance of correct and innovative facial expression recognition (FER) approaches in Artificial Intelligence. The current common practice for FER is to correctly design convolutional neural networks' architectures (CNNs) using human expertise. However, finding a well-performing architecture is often a very tedious and error-prone process for deep learning researchers. Neural architecture search (NAS) is an area of growing interest as demonstrated by the large number of scientific works published in recent years thanks to the impressive results achieved in recent years. We propose a genetic algorithm approach that uses an ingenious encoding-decoding mechanism that allows to automatically evolve CNNs on FER tasks attaining high accuracy classification rates. The experimental results demonstrate that the proposed algorithm achieves the best-known results on the CK+ and FERG datasets as well as competitive results on the JAFFE dataset.
Reducing communication overhead in federated learning (FL) is challenging but crucial for large-scale distributed privacy-preserving machine learning. While methods utilizing sparsification or others can largely lower the communication overhead, the convergence rate is also greatly compromised. In this paper, we propose a novel method, named single-step synthetic features compressor (3SFC), to achieve communication-efficient FL by directly constructing a tiny synthetic dataset based on raw gradients. Thus, 3SFC can achieve an extremely low compression rate when the constructed dataset contains only one data sample. Moreover, 3SFC's compressing phase utilizes a similarity-based objective function so that it can be optimized with just one step, thereby considerably improving its performance and robustness. In addition, to minimize the compressing error, error feedback (EF) is also incorporated into 3SFC. Experiments on multiple datasets and models suggest that 3SFC owns significantly better convergence rates compared to competing methods with lower compression rates (up to 0.02%). Furthermore, ablation studies and visualizations show that 3SFC can carry more information than competing methods for every communication round, further validating its effectiveness.
Neural Architecture Search (NAS) has received increasing attention because of its exceptional merits in automating the design of Deep Neural Network (DNN) architectures. However, the performance evaluation process, as a key part of NAS, often requires training a large number of DNNs. This inevitably causes NAS computationally expensive. In past years, many Efficient Evaluation Methods (EEMs) have been proposed to address this critical issue. In this paper, we comprehensively survey these EEMs published up to date, and provide a detailed analysis to motivate the further development of this research direction. Specifically, we divide the existing EEMs into four categories based on the number of DNNs trained for constructing these EEMs. The categorization can reflect the degree of efficiency in principle, which can in turn help quickly grasp the methodological features. In surveying each category, we further discuss the design principles and analyze the strength and weaknesses to clarify the landscape of existing EEMs, thus making easily understanding the research trends of EEMs. Furthermore, we also discuss the current challenges and issues to identify future research directions in this emerging topic. To the best of our knowledge, this is the first work that extensively and systematically surveys the EEMs of NAS.