Meng Li

Zechun Liu, Barlas Oguz, Aasish Pappu et al. · meta-ai, pku

Modern pre-trained transformers have rapidly advanced the state-of-the-art in machine learning, but have also grown in parameters and computational complexity, making them increasingly difficult to deploy in resource-constrained environments. Binarization of the weights and activations of the network can significantly alleviate these issues, however, is technically challenging from an optimization perspective. In this work, we identify a series of improvements that enables binary transformers at a much higher accuracy than what was possible previously. These include a two-set binarization scheme, a novel elastic binary activation function with learned parameters, and a method to quantize a network to its limit by successively distilling higher precision models into lower precision students. These approaches allow for the first time, fully binarized transformer models that are at a practical level of accuracy, approaching a full-precision BERT baseline on the GLUE language understanding benchmark within as little as 5.9%. Code and models are available at: https://github.com/facebookresearch/bit.

Shuzhang Zhong, Ling Liang, Yuan Wang et al.

Mixture-of-Experts (MoE) models are designed to enhance the efficiency of large language models (LLMs) without proportionally increasing the computational demands. However, their deployment on edge devices still faces significant challenges due to high on-demand loading overheads from managing sparsely activated experts. This paper introduces AdapMoE, an algorithm-system co-design framework for efficient MoE inference. AdapMoE features adaptive expert gating and management to reduce the on-demand loading overheads. We observe the heterogeneity of experts loading across layers and tokens, based on which we propose a sensitivity-based strategy to adjust the number of activated experts dynamically. Meanwhile, we also integrate advanced prefetching and cache management techniques to further reduce the loading latency. Through comprehensive evaluations on various platforms, we demonstrate AdapMoE consistently outperforms existing techniques, reducing the average number of activated experts by 25% and achieving a 1.35x speedup without accuracy degradation. Code is available at: https://github.com/PKU-SEC-Lab/AdapMoE.

Shuzhang Zhong, Meng Li, Yun Liang et al.

Memory-aware network scheduling is becoming increasingly important for deep neural network (DNN) inference on resource-constrained devices. However, due to the complex cell-level and network-level topologies, memory-aware scheduling becomes very challenging. While previous algorithms all suffer from poor scalability, in this paper, we propose an efficient memory-aware scheduling framework based on iterative computation graph optimization. Our framework features an iterative graph fusion algorithm that simplifies the computation graph while preserving the scheduling optimality. We further propose an integer linear programming formulation together with topology-aware variable pruning to schedule the simplified graph efficiently. We evaluate our method against prior-art algorithms on different networks and demonstrate that our method outperforms existing techniques in all the benchmarks, reducing the peak memory footprint by 13.4%, and achieving better scalability for networks with complex network-level topologies.

Zhibo Xing, Zijian Zhang, Ziang Zhang et al.

Over recent decades, machine learning has significantly advanced network communication, enabling improved decision-making, user behavior analysis, and fault detection. Decentralized approaches, where participants exchange computation results instead of raw private data, mitigate these risks but introduce challenges related to trust and verifiability. A critical issue arises: How can one ensure the integrity and validity of computation results shared by other participants? Existing survey articles predominantly address security and privacy concerns in decentralized machine learning, whereas this survey uniquely highlights the emerging issue of verifiability. Recognizing the critical role of zero-knowledge proofs in ensuring verifiability, we present a comprehensive review of Zero-Knowledge Proof-based Verifiable Machine Learning (ZKP-VML). To clarify the research problem, we present a definition of ZKP-VML consisting of four algorithms, along with several corresponding key security properties. Besides, we provide an overview of the current research landscape by systematically organizing the research timeline and categorizing existing schemes based on their security properties. Furthermore, through an in-depth analysis of each existing scheme, we summarize their technical contributions and optimization strategies, aiming to uncover common design principles underlying ZKP-VML schemes. Building on the reviews and analysis presented, we identify current research challenges and suggest future research directions. To the best of our knowledge, this is the most comprehensive survey to date on verifiable decentralized machine learning and ZKP-VML.

Li Meng, Morten Goodwin, Anis Yazidi et al.

Transformers are neural network models that utilize multiple layers of self-attention heads and have exhibited enormous potential in natural language processing tasks. Meanwhile, there have been efforts to adapt transformers to visual tasks of machine learning, including Vision Transformers and Swin Transformers. Although some researchers use Vision Transformers for reinforcement learning tasks, their experiments remain at a small scale due to the high computational cost. This article presents the first online reinforcement learning scheme that is based on Swin Transformers: Swin DQN. In contrast to existing research, our novel approach demonstrate the superior performance with experiments on 49 games in the Arcade Learning Environment. The results show that our approach achieves significantly higher maximal evaluation scores than the baseline method in 45 of all the 49 games (92%), and higher mean evaluation scores than the baseline method in 40 of all the 49 games (82%).

Li Meng, Morten Goodwin, Anis Yazidi et al.

State representation learning aims to capture latent factors of an environment. Contrastive methods have performed better than generative models in previous state representation learning research. Although some researchers realize the connections between masked image modeling and contrastive representation learning, the effort is focused on using masks as an augmentation technique to represent the latent generative factors better. Partially observable environments in reinforcement learning have not yet been carefully studied using unsupervised state representation learning methods. In this article, we create an unsupervised state representation learning scheme for partially observable states. We conducted our experiment on a previous Atari 2600 framework designed to evaluate representation learning models. A contrastive method called Spatiotemporal DeepInfomax (ST-DIM) has shown state-of-the-art performance on this benchmark but remains inferior to its supervised counterpart. Our approach improves ST-DIM when the environment is not fully observable and achieves higher F1 scores and accuracy scores than the supervised learning counterpart. The mean accuracy score averaged over categories of our approach is ~66%, compared to ~38% of supervised learning. The mean F1 score is ~64% to ~33%.

Shuzhang Zhong, Yanfan Sun, Ling Liang et al.

The Mixture of Experts (MoE) architecture has demonstrated significant advantages as it enables to increase the model capacity without a proportional increase in computation. However, the large MoE model size still introduces substantial memory demands, which usually requires expert offloading on resource-constrained platforms and incurs significant overhead. Hybrid CPU-GPU inference has been proposed to leverage CPU computation to reduce expert loading overhead but faces major challenges: on one hand, the expert activation patterns of MoE models are highly unstable, rendering the fixed mapping strategies in existing works inefficient; on the other hand, the hybrid CPU-GPU schedule for MoE is inherently complex due to the diverse expert sizes, structures, uneven workload distribution, etc. To address these challenges, in this paper, we propose HybriMoE, a hybrid CPU-GPU inference framework that improves resource utilization through a novel CPU-GPU scheduling and cache management system. HybriMoE introduces (i) a dynamic intra-layer scheduling strategy to balance workloads across CPU and GPU, (ii) an impact-driven inter-layer prefetching algorithm, and (iii) a score-based caching algorithm to mitigate expert activation instability. We implement HybriMoE on top of the kTransformers framework and evaluate it on three widely used MoE-based LLMs. Experimental results demonstrate that HybriMoE achieves an average speedup of 1.33$\times$ in the prefill stage and 1.70$\times$ in the decode stage compared to state-of-the-art hybrid MoE inference framework. Our code is available at: https://github.com/PKU-SEC-Lab/HybriMoE.

Zebin Yang, Renze Chen, Taiqiang Wu et al.

In this paper, we propose MCUBERT to enable language models like BERT on tiny microcontroller units (MCUs) through network and scheduling co-optimization. We observe the embedding table contributes to the major storage bottleneck for tiny BERT models. Hence, at the network level, we propose an MCU-aware two-stage neural architecture search algorithm based on clustered low-rank approximation for embedding compression. To reduce the inference memory requirements, we further propose a novel fine-grained MCU-friendly scheduling strategy. Through careful computation tiling and re-ordering as well as kernel design, we drastically increase the input sequence lengths supported on MCUs without any latency or accuracy penalty. MCUBERT reduces the parameter size of BERT-tiny and BERT-mini by 5.7$\times$ and 3.0$\times$ and the execution memory by 3.5$\times$ and 4.3$\times$, respectively. MCUBERT also achieves 1.5$\times$ latency reduction. For the first time, MCUBERT enables lightweight BERT models on commodity MCUs and processing more than 512 tokens with less than 256KB of memory.

Tianshi Xu, Shuzhang Zhong, Wenxuan Zeng et al.

Private deep neural network (DNN) inference based on secure two-party computation (2PC) enables secure privacy protection for both the server and the client. However, existing secure 2PC frameworks suffer from a high inference latency due to enormous communication. As the communication of both linear and non-linear DNN layers reduces with the bit widths of weight and activation, in this paper, we propose PrivQuant, a framework that jointly optimizes the 2PC-based quantized inference protocols and the network quantization algorithm, enabling communication-efficient private inference. PrivQuant proposes DNN architecture-aware optimizations for the 2PC protocols for communication-intensive quantized operators and conducts graph-level operator fusion for communication reduction. Moreover, PrivQuant also develops a communication-aware mixed precision quantization algorithm to improve inference efficiency while maintaining high accuracy. The network/protocol co-optimization enables PrivQuant to outperform prior-art 2PC frameworks. With extensive experiments, we demonstrate PrivQuant reduces communication by $11\times, 2.5\times \mathrm{and}~ 2.8\times$, which results in $8.7\times, 1.8\times ~ \mathrm{and}~ 2.4\times$ latency reduction compared with SiRNN, COINN, and CoPriv, respectively.

Meng Li, Michael Vrazitulis, David Schlangen

Rational speakers are supposed to know what they know and what they do not know, and to generate expressions matching the strength of evidence. In contrast, it is still a challenge for current large language models to generate corresponding utterances based on the assessment of facts and confidence in an uncertain real-world environment. While it has recently become popular to estimate and calibrate confidence of LLMs with verbalized uncertainty, what is lacking is a careful examination of the linguistic knowledge of uncertainty encoded in the latent space of LLMs. In this paper, we draw on typological frameworks of epistemic expressions to evaluate LLMs' knowledge of epistemic modality, using controlled stories. Our experiments show that the performance of LLMs in generating epistemic expressions is limited and not robust, and hence the expressions of uncertainty generated by LLMs are not always reliable. To build uncertainty-aware LLMs, it is necessary to enrich semantic knowledge of epistemic modality in LLMs.

Haichuan Yang, Yuan Shangguan, Dilin Wang et al.

From wearables to powerful smart devices, modern automatic speech recognition (ASR) models run on a variety of edge devices with different computational budgets. To navigate the Pareto front of model accuracy vs model size, researchers are trapped in a dilemma of optimizing model accuracy by training and fine-tuning models for each individual edge device while keeping the training GPU-hours tractable. In this paper, we propose Omni-sparsity DNN, where a single neural network can be pruned to generate optimized model for a large range of model sizes. We develop training strategies for Omni-sparsity DNN that allows it to find models along the Pareto front of word-error-rate (WER) vs model size while keeping the training GPU-hours to no more than that of training one singular model. We demonstrate the Omni-sparsity DNN with streaming E2E ASR models. Our results show great saving on training time and resources with similar or better accuracy on LibriSpeech compared to individually pruned sparse models: 2%-6.6% better WER on Test-other.

Grace Li Zhang, Bing Li, Meng Li et al.

With recent advances in reverse engineering, attackers can reconstruct a netlist to counterfeit chips by opening the die and scanning all layers of authentic chips. This relatively easy counterfeiting is made possible by the use of the standard simple clocking scheme, where all combinational blocks function within one clock period, so that a netlist of combinational logic gates and flip-flops is sufficient to duplicate a design. In this paper, we propose to invalidate the assumption that a netlist completely represents the function of a circuit with unconventional timing. With the introduced wave-pipelining paths, attackers have to capture gate and interconnect delays during reverse engineering, or to test a huge number of combinational paths to identify the wave-pipelining paths. To hinder the test-based attack, we construct false paths with wave-pipelining to increase the counterfeiting challenge. Experimental results confirm that wave-pipelining true paths and false paths can be constructed in benchmark circuits successfully with only a negligible cost, thus thwarting the potential attack techniques.

Yibo Lin, Meng Li, Yuki Watanabe et al.

Lithography simulation is one of the key steps in physical verification, enabled by the substantial optical and resist models. A resist model bridges the aerial image simulation to printed patterns. While the effectiveness of learning-based solutions for resist modeling has been demonstrated, they are considerably data-demanding. Meanwhile, a set of manufactured data for a specific lithography configuration is only valid for the training of one single model, indicating low data efficiency. Due to the complexity of the manufacturing process, obtaining enough data for acceptable accuracy becomes very expensive in terms of both time and cost, especially during the evolution of technology generations when the design space is intensively explored. In this work, we propose a new resist modeling framework for contact layers, utilizing existing data from old technology nodes and active selection of data in a target technology node, to reduce the amount of data required from the target lithography configuration. Our framework based on transfer learning and active learning techniques is effective within a competitive range of accuracy, i.e., 3-10X reduction on the amount of training data with comparable accuracy to the state-of-the-art learning approach.