arXiv subjects

Bill Lin

Publications and source records attributed to Bill Lin.

At least 19 recordsLinked to original sources

arXiv2026

An Extended Study of Gear-Ratio-Aware Standard Cell Layout Generation for DTCO Exploration

Advanced nodes decouple contacted poly pitch (CPP) and lower-metal pitch to improve routability. We present CPCell, an efficient standard-cell layout generation framework, to support arbitrary gear ratio (GR) and offset parameters through a fine-grained layered grid graph and constraint-programming-based placement-routing co-optimization. Layout quality is improved via Middle-of-Line routing, M0 pin enablement, pin accessibility constraints and a weighted multi-objective formulation that jointly optimizes cell layouts. To scale to netlists with up to 48 transistors, we incorporate acceleration techniques including transistor clustering, identical transistor partitioning, routing lower bound tightening and early termination strategies. Comprehensive cell-level and block-level studies are conducted to evaluate GR and offset choices, quantify the benefits of the proposed objectives and assess their impact on power, performance, area and IR-drop outcomes.

cs.AR↗

arXiv2026

Scheduling Parallel Optical Circuit Switches for AI Training

The rapid growth of AI training has dramatically increased datacenter traffic demand and energy consumption, which has motivated renewed interest in optical circuit switches (OCSes) as a high-bandwidth, energy-efficient alternative for AI fabrics. Deploying multiple parallel OCSes is a leading alternative. However, efficiently scheduling time-varying traffic matrices across parallel optical switches with non-negligible reconfiguration delays remains an open challenge. We consider the problem of scheduling a single AI traffic demand matrix $D$ over $s$ parallel OCSes while minimizing the makespan under reconfiguration delay $\delta$. Our algorithm Spectra relies on a three-step approach: Decompose $D$ into a minimal set of weighted permutations; Schedule these permutations across parallel switches using load-aware assignment; then Equalize the imbalanced loads on the switches via controlled permutation splitting. Evaluated on realistic AI training workloads (GPT model and Qwen MoE expert routing) as well as standard benchmarks, Spectra vastly outperforms a baseline based on state-of-the-art algorithms, reducing schedule makespan by an average factor of $1.4\times$ on GPT AI workloads, $1.9\times$ on MoE AI workloads, and $2.4\times$ on standard benchmarks. Further, the makespans achieved by Spectra consistently approach newly derived lower bounds.

cs.NI↗

arXiv2026

Scaling Routers with In-Package Optics and High-Bandwidth Memories

This paper aims to apply two major scaling transformations from the computing packaging industry to internet routers: the heterogeneous integration of high-bandwidth memories (HBMs) and chiplets, as well as in-package optics. We propose a novel internet router architecture that employs these technologies to achieve a petabit/sec router within a single integrated package. At the top-level, we introduce a novel split-parallel switch architecture that spatially divides (without processing) the incoming fibers and distributes them across smaller independent switches without intermediate OEO conversions or fine-tuned per-packet load-balancing. This passive spatial division enables scaling at the cost of a coarser traffic load balancing. Yet, through extensive evaluations of backbone network traffic, we demonstrate that differences with fine-tuned approaches are small. In addition, we propose a novel HBM-based shared-memory architecture for the implementation of the smaller independent switches, and we introduce a novel parallel frame interleaving algorithm that packs traffic into frames so that HBM banks are accessed at peak HBM data rates in a cyclical interleaving manner. We further discuss why these new technologies represent a paradigm shift in the design of future internet routers. Finally, we emphasize that power consumption may constitute the primary bottleneck to scaling.

cs.NI↗

arXiv2025

Panel-Scale Reconfigurable Photonic Interconnects for Scalable AI Computation

Panel-scale reconfigurable photonic interconnects on a glass substrate up to 500-mm x 500-mm or larger are envisioned by proposing a novel photonic switch fabric that enables all directional panel-edge-to-panel-edge reach without the need for active repeaters while offering high communication bandwidth, planar-direction reconfigurability, low energy consumption, and compelling data bandwidth density for heterogeneous integration of an in-package AI computing system on a single glass-substrate photonic interposer exceeding thousands of centimeters square. The proposed approach focuses on reconfigurable photonic interconnects, which are integration-compatible with commercial processor chiplets and 3D high-bandwidth memory (HBM) stacks on a large-area glass substrate, to create a novel panel-scale heterogeneously integrated interposer or package enabling low-energy and high-capacity wavelength-division-multiplexing (WDM) optical data links using advanced high-speed optical modulators, broadband photodetectors, novel optical crossbar switches with multi-layer waveguides, and in-package frequency comb sources.

eess.SY↗

arXiv2024

Federated Learning Client Pruning for Noisy Labels

Federated Learning (FL) enables collaborative model training across decentralized edge devices while preserving data privacy. However, existing FL methods often assume clean annotated datasets, impractical for resource-constrained edge devices. In reality, noisy labels are prevalent, posing significant challenges to FL performance. Prior approaches attempt label correction and robust training techniques but exhibit limited efficacy, particularly under high noise levels. This paper introduces ClipFL (Federated Learning Client Pruning), a novel framework addressing noisy labels from a fresh perspective. ClipFL identifies and excludes noisy clients based on their performance on a clean validation dataset, tracked using a Noise Candidacy Score (NCS). The framework comprises three phases: pre-client pruning to identify potential noisy clients and calculate their NCS, client pruning to exclude a percentage of clients with the highest NCS, and post-client pruning for fine-tuning the global model with standard FL on clean clients. Empirical evaluation demonstrates ClipFL's efficacy across diverse datasets and noise levels, achieving accurate noisy client identification, superior performance, faster convergence, and reduced communication costs compared to state-of-the-art FL methods. Our code is available at https://github.com/MMorafah/ClipFL.

cs.LG↗

arXiv2024

Towards Diverse Device Heterogeneous Federated Learning via Task Arithmetic Knowledge Integration

Federated Learning has emerged as a promising paradigm for collaborative machine learning, while preserving user data privacy. Despite its potential, standard FL lacks support for diverse heterogeneous device prototypes, which vary significantly in model and dataset sizes -- from small IoT devices to large workstations. This limitation is only partially addressed by existing knowledge distillation techniques, which often fail to transfer knowledge effectively across a broad spectrum of device prototypes with varied capabilities. This failure primarily stems from two issues: the dilution of informative logits from more capable devices by those from less capable ones, and the use of a single integrated logits as the distillation target across all devices, which neglects their individual learning capacities and and the unique contributions of each. To address these challenges, we introduce TAKFL, a novel KD-based framework that treats the knowledge transfer from each device prototype's ensemble as a separate task, independently distilling each to preserve its unique contributions and avoid dilution. TAKFL also incorporates a KD-based self-regularization technique to mitigate the issues related to the noisy and unsupervised ensemble distillation process. To integrate the separately distilled knowledge, we introduce an adaptive task arithmetic knowledge integration process, allowing each student model to customize the knowledge integration for optimal performance. Additionally, we present theoretical results demonstrating the effectiveness of task arithmetic in transferring knowledge across heterogeneous devices with varying capacities. Comprehensive evaluations of our method across both CV and NLP tasks demonstrate that TAKFL achieves SOTA results in a variety of datasets and settings, significantly outperforming existing KD-based methods Code is released at https://github.com/MMorafah/TAKFL

cs.LG↗

arXiv2024

Micro-Ring Modulator Linearity Enhancement for Analog and Digital Optical Links

An energy/area-efficient low-cost broadband linearity enhancement technique for electro-optic micro-ring modulators (MRM) is proposed to achieve 6.1-dB dynamic linearity improvement in spurious-free-dynamic-range with intermodulation distortions (IMD) and 17.9-dB static linearity improvement in integral nonlinearity over a conventional notch-filter MRM within a 4.8-dB extinction-ratio (ER) full-scale range based on rapid silicon-photonics fabrication results for the emerging applications of various analog and digital optical communication systems.

eess.SY↗

arXiv2024

MAP-Neo: Highly Capable and Transparent Bilingual Large Language Model Series

Large Language Models (LLMs) have made great strides in recent years to achieve unprecedented performance across different tasks. However, due to commercial interest, the most competitive models like GPT, Gemini, and Claude have been gated behind proprietary interfaces without disclosing the training details. Recently, many institutions have open-sourced several strong LLMs like LLaMA-3, comparable to existing closed-source LLMs. However, only the model's weights are provided with most details (e.g., intermediate checkpoints, pre-training corpus, and training code, etc.) being undisclosed. To improve the transparency of LLMs, the research community has formed to open-source truly open LLMs (e.g., Pythia, Amber, OLMo), where more details (e.g., pre-training corpus and training code) are being provided. These models have greatly advanced the scientific study of these large models including their strengths, weaknesses, biases and risks. However, we observe that the existing truly open LLMs on reasoning, knowledge, and coding tasks are still inferior to existing state-of-the-art LLMs with similar model sizes. To this end, we open-source MAP-Neo, a highly capable and transparent bilingual language model with 7B parameters trained from scratch on 4.5T high-quality tokens. Our MAP-Neo is the first fully open-sourced bilingual LLM with comparable performance compared to existing state-of-the-art LLMs. Moreover, we open-source all details to reproduce our MAP-Neo, where the cleaned pre-training corpus, data cleaning pipeline, checkpoints, and well-optimized training/evaluation framework are provided. Finally, we hope our MAP-Neo will enhance and strengthen the open research community and inspire more innovations and creativities to facilitate the further improvements of LLMs.

cs.CL↗

arXiv2024

Stable Diffusion-based Data Augmentation for Federated Learning with Non-IID Data

The proliferation of edge devices has brought Federated Learning (FL) to the forefront as a promising paradigm for decentralized and collaborative model training while preserving the privacy of clients' data. However, FL struggles with a significant performance reduction and poor convergence when confronted with Non-Independent and Identically Distributed (Non-IID) data distributions among participating clients. While previous efforts, such as client drift mitigation and advanced server-side model fusion techniques, have shown some success in addressing this challenge, they often overlook the root cause of the performance reduction - the absence of identical data accurately mirroring the global data distribution among clients. In this paper, we introduce Gen-FedSD, a novel approach that harnesses the powerful capability of state-of-the-art text-to-image foundation models to bridge the significant Non-IID performance gaps in FL. In Gen-FedSD, each client constructs textual prompts for each class label and leverages an off-the-shelf state-of-the-art pre-trained Stable Diffusion model to synthesize high-quality data samples. The generated synthetic data is tailored to each client's unique local data gaps and distribution disparities, effectively making the final augmented local data IID. Through extensive experimentation, we demonstrate that Gen-FedSD achieves state-of-the-art performance and significant communication cost savings across various datasets and Non-IID settings.

cs.LG↗

arXiv2024

On Robustness and Generalization of ML-Based Congestion Predictors to Valid and Imperceptible Perturbations

There is substantial interest in the use of machine learning (ML)-based techniques throughout the electronic computer-aided design (CAD) flow, particularly methods based on deep learning. However, while deep learning methods have achieved state-of-the-art performance in several applications, recent work has demonstrated that neural networks are generally vulnerable to small, carefully chosen perturbations of their input (e.g. a single pixel change in an image). In this work, we investigate robustness in the context of ML-based EDA tools -- particularly for congestion prediction. As far as we are aware, we are the first to explore this concept in the context of ML-based EDA. We first describe a novel notion of imperceptibility designed specifically for VLSI layout problems defined on netlists and cell placements. Our definition of imperceptibility is characterized by a guarantee that a perturbation to a layout will not alter its global routing. We then demonstrate that state-of-the-art CNN and GNN-based congestion models exhibit brittleness to imperceptible perturbations. Namely, we show that when a small number of cells (e.g. 1%-5% of cells) have their positions shifted such that a measure of global congestion is guaranteed to remain unaffected (e.g. 1% of the design adversarially shifted by 0.001% of the layout space results in a predicted decrease in congestion of up to 90%, while no change in congestion is implied by the perturbation). In other words, the quality of a predictor can be made arbitrarily poor (i.e. can be made to predict that a design is "congestion-free") for an arbitrary input layout. Next, we describe a simple technique to train predictors that improves robustness to these perturbations. Our work indicates that CAD engineers should be cautious when integrating neural network-based mechanisms in EDA flows to ensure robust and high-quality results.

cs.LG↗

arXiv2024

Monolithic Silicon-Photonics Linear-Algebra Accelerators Enabling Next-Gen Massive MIMO

A system-on-chip (SoC) photonic-electronic linear-algebra accelerator with the features of wavelength-division-multiplexing (WDM) based broadband photodetections and high-dimensional matrix-inversion operations fabricated in advanced monolithic silicon-photonics (M-SiPh) semiconductor process technology is proposed to achieve substantial leaps in computation density and energy efficiency, including realistic considerations of energy/area overhead due to electronic/photonic on-chip conversions, integrations, and calibrations through holistic co-design methodologies to support linear-detection based massive multiple-input multiple-output (MIMO) decoding technology requiring the inversion of channel matrices and other emergent applications limited by linear-algebra computation capacities.

eess.SY↗

arXiv2023

ChatGPT at the Speed of Light: Optical Comb-Based Monolithic Photonic-Electronic Linear-Algebra Accelerators

This paper proposes to adopt advanced monolithic silicon-photonics integrated-circuits manufacturing capabilities to achieve a system-on-chip photonic-electronic linear-algebra accelerator with the features of optical comb-based broadband incoherent photo-detections and high-dimensional operations of consecutive matrix-matrix multiplications to enable substantial leaps in computation density and energy efficiency, with practical considerations of power/area overhead due to photonic-electronic on-chip conversions, integrations, and calibrations through holistic co-design approaches to support attention-head mechanism based deep-learning neural networks used in Large Language Models and other emergent applications.

eess.SY↗

arXiv2023

A Practical Recipe for Federated Learning Under Statistical Heterogeneity Experimental Design

Federated Learning (FL) has been an area of active research in recent years. There have been numerous studies in FL to make it more successful in the presence of data heterogeneity. However, despite the existence of many publications, the state of progress in the field is unknown. Many of the works use inconsistent experimental settings and there are no comprehensive studies on the effect of FL-specific experimental variables on the results and practical insights for a more comparable and consistent FL experimental setup. Furthermore, the existence of several benchmarks and confounding variables has further complicated the issue of inconsistency and ambiguity. In this work, we present the first comprehensive study on the effect of FL-specific experimental variables in relation to each other and performance results, bringing several insights and recommendations for designing a meaningful and well-incentivized FL experimental setup. We further aid the community by releasing FedZoo-Bench, an open-source library based on PyTorch with pre-implementation of 22 state-of-the-art methods, and a broad set of standardized and customizable features available at https://github.com/MMorafah/FedZoo-Bench. We also provide a comprehensive comparison of several state-of-the-art (SOTA) methods to better understand the current state of the field and existing limitations.

cs.LG↗

arXiv2022

When Do Curricula Work in Federated Learning?

An oft-cited open problem of federated learning is the existence of data heterogeneity at the clients. One pathway to understanding the drastic accuracy drop in federated learning is by scrutinizing the behavior of the clients' deep models on data with different levels of "difficulty", which has been left unaddressed. In this paper, we investigate a different and rarely studied dimension of FL: ordered learning. Specifically, we aim to investigate how ordered learning principles can contribute to alleviating the heterogeneity effects in FL. We present theoretical analysis and conduct extensive empirical studies on the efficacy of orderings spanning three kinds of learning: curriculum, anti-curriculum, and random curriculum. We find that curriculum learning largely alleviates non-IIDness. Interestingly, the more disparate the data distributions across clients the more they benefit from ordered learning. We provide analysis explaining this phenomenon, specifically indicating how curriculum training appears to make the objective landscape progressively less convex, suggesting fast converging iterations at the beginning of the training procedure. We derive quantitative results of convergence for both convex and nonconvex objectives by modeling the curriculum training on federated devices as local SGD with locally biased stochastic gradients. Also, inspired by ordered learning, we propose a novel client selection technique that benefits from the real-world disparity in the clients. Our proposed approach to client selection has a synergic effect when applied together with ordered learning in FL.

cs.LG↗

arXiv2022

Neural Routing in Meta Learning

Meta-learning often referred to as learning-to-learn is a promising notion raised to mimic human learning by exploiting the knowledge of prior tasks but being able to adapt quickly to novel tasks. A plethora of models has emerged in this context and improved the learning efficiency, robustness, etc. The question that arises here is can we emulate other aspects of human learning and incorporate them into the existing meta learning algorithms? Inspired by the widely recognized finding in neuroscience that distinct parts of the brain are highly specialized for different types of tasks, we aim to improve the model performance of the current meta learning algorithms by selectively using only parts of the model conditioned on the input tasks. In this work, we describe an approach that investigates task-dependent dynamic neuron selection in deep convolutional neural networks (CNNs) by leveraging the scaling factor in the batch normalization (BN) layer associated with each convolutional layer. The problem is intriguing because the idea of helping different parts of the model to learn from different types of tasks may help us train better filters in CNNs, and improve the model generalization performance. We find that the proposed approach, neural routing in meta learning (NRML), outperforms one of the well-known existing meta learning baselines on few-shot classification tasks on the most widely used benchmark datasets.

cs.LG↗

arXiv2022

Rethinking Data Heterogeneity in Federated Learning: Introducing a New Notion and Standard Benchmarks

Though successful, federated learning presents new challenges for machine learning, especially when the issue of data heterogeneity, also known as Non-IID data, arises. To cope with the statistical heterogeneity, previous works incorporated a proximal term in local optimization or modified the model aggregation scheme at the server side or advocated clustered federated learning approaches where the central server groups agent population into clusters with jointly trainable data distributions to take the advantage of a certain level of personalization. While effective, they lack a deep elaboration on what kind of data heterogeneity and how the data heterogeneity impacts the accuracy performance of the participating clients. In contrast to many of the prior federated learning approaches, we demonstrate not only the issue of data heterogeneity in current setups is not necessarily a problem but also in fact it can be beneficial for the FL participants. Our observations are intuitive: (1) Dissimilar labels of clients (label skew) are not necessarily considered data heterogeneity, and (2) the principal angle between the agents' data subspaces spanned by their corresponding principal vectors of data is a better estimate of the data heterogeneity. Our code is available at https://github.com/MMorafah/FL-SC-NIID.

cs.LG↗

arXiv2022

Efficient Distribution Similarity Identification in Clustered Federated Learning via Principal Angles Between Client Data Subspaces

Clustered federated learning (FL) has been shown to produce promising results by grouping clients into clusters. This is especially effective in scenarios where separate groups of clients have significant differences in the distributions of their local data. Existing clustered FL algorithms are essentially trying to group together clients with similar distributions so that clients in the same cluster can leverage each other's data to better perform federated learning. However, prior clustered FL algorithms attempt to learn these distribution similarities indirectly during training, which can be quite time consuming as many rounds of federated learning may be required until the formation of clusters is stabilized. In this paper, we propose a new approach to federated learning that directly aims to efficiently identify distribution similarities among clients by analyzing the principal angles between the client data subspaces. Each client applies a truncated singular value decomposition (SVD) step on its local data in a single-shot manner to derive a small set of principal vectors, which provides a signature that succinctly captures the main characteristics of the underlying distribution. This small set of principal vectors is provided to the server so that the server can directly identify distribution similarities among the clients to form clusters. This is achieved by comparing the similarities of the principal angles between the client data subspaces spanned by those principal vectors. The approach provides a simple, yet effective clustered FL framework that addresses a broad range of data heterogeneity issues beyond simpler forms of Non-IIDness like label skews. Our clustered FL approach also enables convergence guarantees for non-convex objectives. Our code is available at https://github.com/MMorafah/PACFL.

cs.LG↗

arXiv2022

FLIS: Clustered Federated Learning via Inference Similarity for Non-IID Data Distribution

Classical federated learning approaches yield significant performance degradation in the presence of Non-IID data distributions of participants. When the distribution of each local dataset is highly different from the global one, the local objective of each client will be inconsistent with the global optima which incur a drift in the local updates. This phenomenon highly impacts the performance of clients. This is while the primary incentive for clients to participate in federated learning is to obtain better personalized models. To address the above-mentioned issue, we present a new algorithm, FLIS, which groups the clients population in clusters with jointly trainable data distributions by leveraging the inference similarity of clients' models. This framework captures settings where different groups of users have their own objectives (learning tasks) but by aggregating their data with others in the same cluster (same learning task) to perform more efficient and personalized federated learning. We present experimental results to demonstrate the benefits of FLIS over the state-of-the-art benchmarks on CIFAR-100/10, SVHN, and FMNIST datasets. Our code is available at https://github.com/MMorafah/FLIS.

cs.LG↗