arXiv subjects

Hesham Mostafa

Publications and source records attributed to Hesham Mostafa.

At least 19 recordsLinked to original sources

arXiv2026

DiRotQ: Rotation-Aware Quantization for 4-bit Diffusion Transformers

Diffusion Transformers (DiTs) achieve state-of-the-art image generation quality but incur substantial memory and computational costs at inference. While aggressive Post-Training Quantization (PTQ) to 4-bit precision offers significant efficiency gains, it typically results in severe quality degradation. Existing approaches, including smoothing-based methods, mixed-precision schemes, rotation techniques, and low-rank residual methods, partially mitigate this issue but still leave a noticeable gap to FP16/BF16 performance. In this work, we introduce DiRotQ, a W4A4 PTQ framework that mitigates this degradation through rotation-aware activation quantization. DiRotQ identifies a low-rank subspace capturing dominant activation variance via Principal Component Analysis (PCA), preserving coefficients in this subspace at higher precision while quantizing the remaining components to 4-bit. Activations are rotated into the PCA basis at inference time using calibration-derived orthogonal transformations, while the inverse rotation is fused into the layer weights offline. Combined with GPTQ-based weight quantization, DiRotQ achieves an FID (lower is better) of 15.9 and PSNR (higher is better) of 19.1 dB on PixArt-{\Sigma} over the MJHQ-30K dataset, outperforming the prior state-of-the-art SVDQuant (FID 18.9, PSNR 17.6) under the same INT W4A4 setting. Beyond standard metrics, we introduce a VLM-as-a-Judge evaluation protocol for diffusion model quantization, the first such evaluation in this setting, providing a more holistic assessment of perceptual quality and prompt alignment under aggressive compression. On the systems side, we implement a Triton-based custom kernel to enable efficient end-to-end inference, reducing memory usage of the 12B FLUX.1-dev model by 2.1x and delivering 2.3x speedup over the BF16 baseline, on a 24 GB RTX 4090 GPU.

cs.CV↗

arXiv2026

MF-QAT: Multi-Format Quantization-Aware Training for Elastic Inference

Quantization-aware training (QAT) is typically performed for a single target numeric format, while practical deployments often need to choose numerical precision at inference time based on hardware support or runtime constraints. We study multi-format QAT, where a single model is trained to be robust across multiple quantization formats. We find that multi-format QAT can match single-format QAT at each target precision, yielding one model that performs well overall across different formats, even formats that were not seen during training. To enable practical deployment, we propose the Slice-and-Scale conversion procedure for both MXINT and MXFP that converts a high-precision representation into lower-precision formats without re-training. Building on this, we introduce a pipeline that (i) trains a model with multi-format QAT, (ii) stores a single anchor format checkpoint (MXINT8/MXFP8), and (iii) allows on-the-fly conversion to lower MXINT or MXFP formats at runtime with negligible-or no-additional accuracy degradation. Together, these components provide a practical path to elastic precision scaling and allow selecting the runtime format at inference time across diverse deployment targets.

cs.LG↗

arXiv2025

Early Attentive Sparsification Accelerates Neural Speech Transcription

Transformer-based neural speech processing has achieved state-of-the-art performance. Since speech audio signals are known to be highly compressible, here we seek to accelerate neural speech transcription by time-domain signal sparsification early in the neural encoding stage, taking advantage of the interpretability of the self-attention mechanism in transformer audio encoders. With the Whisper family of models, we perform a systematic architecture search over the joint space of sparsification stage (a certain encoder layer) and compression ratio (sparsity). We found that the best resulting solutions under 1% accuracy degradation choose to sparsify the hidden state to 40-60% sparsity at an early encoding stage, and thereby achieve up to 1.6x runtime acceleration in English speech transcription tasks on Nvidia GPUs without any fine-tuning.

cs.LG↗

arXiv2024

Distributed Training of Large Graph Neural Networks with Variable Communication Rates

Training Graph Neural Networks (GNNs) on large graphs presents unique challenges due to the large memory and computing requirements. Distributed GNN training, where the graph is partitioned across multiple machines, is a common approach to training GNNs on large graphs. However, as the graph cannot generally be decomposed into small non-interacting components, data communication between the training machines quickly limits training speeds. Compressing the communicated node activations by a fixed amount improves the training speeds, but lowers the accuracy of the trained GNN. In this paper, we introduce a variable compression scheme for reducing the communication volume in distributed GNN training without compromising the accuracy of the learned model. Based on our theoretical analysis, we derive a variable compression method that converges to a solution equivalent to the full communication case, for all graph partitioning schemes. Our empirical results show that our method attains a comparable performance to the one obtained with full communication. We outperform full communication at any fixed compression ratio for any communication budget.

cs.LG↗

arXiv2024

Fully-inductive Node Classification on Arbitrary Graphs

One fundamental challenge in graph machine learning is generalizing to new graphs. Many existing methods following the inductive setup can generalize to test graphs with new structures, but assuming the feature and label spaces remain the same as the training ones. This paper introduces a fully-inductive setup, where models should perform inference on arbitrary test graphs with new structures, feature and label spaces. We propose GraphAny as the first attempt at this challenging setup. GraphAny models inference on a new graph as an analytical solution to a LinearGNN, which can be naturally applied to graphs with any feature and label spaces. To further build a stronger model with learning capacity, we fuse multiple LinearGNN predictions with learned inductive attention scores. Specifically, the attention module is carefully parameterized as a function of the entropy-normalized distance features between pairs of LinearGNN predictions to ensure generalization to new graphs. Empirically, GraphAny trained on a single Wisconsin dataset with only 120 labeled nodes can generalize to 30 new graphs with an average accuracy of 67.26%, surpassing not only all inductive baselines, but also strong transductive methods trained separately on each of the 30 test graphs.

cs.LG↗

arXiv2024

FloorSet -- a VLSI Floorplanning Dataset with Design Constraints of Real-World SoCs

Floorplanning for systems-on-a-chip (SoCs) and its sub-systems is a crucial and non-trivial step of the physical design flow. It represents a difficult combinatorial optimization problem. A typical large scale SoC with 120 partitions generates a search-space of nearly 10E250. As novel machine learning (ML) approaches emerge to tackle such problems, there is a growing need for a modern benchmark that comprises a large training dataset and performance metrics that better reflect real-world constraints and objectives compared to existing benchmarks. To address this need, we present FloorSet -- two comprehensive datasets of synthetic fixed-outline floorplan layouts that reflect the distribution of real SoCs. Each dataset has 1M training samples and 100 test samples where each sample is a synthetic floor-plan. FloorSet-Prime comprises fully-abutted rectilinear partitions and near-optimal wire-length. A simplified dataset that reflects early design phases, FloorSet-Lite comprises rectangular partitions, with under 5 percent white-space and near-optimal wire-length. Both datasets define hard constraints seen in modern design flows such as shape constraints, edge-affinity, grouping constraints, and pre-placement constraints. FloorSet is intended to spur fundamental research on large-scale constrained optimization problems. Crucially, FloorSet alleviates the core issue of reproducibility in modern ML driven solutions to such problems. FloorSet is available as an open-source repository for the research community.

cs.AR↗

arXiv2024

PARSAC: Fast, Human-quality Floorplanning for Modern SoCs with Complex Design Constraints

The floorplanning of Systems-on-a-Chip (SoCs) and of chip sub-systems is a crucial step in the physical design flow as it determines the optimal shapes and locations of the blocks that make up the system. Simulated Annealing (SA) has been the method of choice for tackling classical floorplanning problems where the objective is to minimize wire-length and the total placement area. The goal in industry-relevant floorplanning problems, however, is not only to minimize area and wire-length, but to do that while respecting hard placement constraints that specify the general area and/or the specific locations for the placement of some blocks. We show that simply incorporating these constraints into the SA objective function leads to sub-optimal, and often illegal, solutions. We propose the Constraints-Aware Simulated Annealing (CA-SA) method and show that it strongly outperforms vanilla SA in floorplanning problems with hard placement constraints. We developed a new floorplanning tool on top of CA-SA: PARSAC (Parallel Simulated Annealing with Constraints). PARSAC is an efficient, easy-to-use, and massively parallel floorplanner. Unlike current SA-based or learning-based floorplanning tools that cannot effectively incorporate hard placement-constraints, PARSAC can quickly construct the Pareto-optimal legal solutions front for constrained floorplanning problems. PARSAC also outperforms traditional SA on legacy floorplanning benchmarks. PARSAC is available as an open-source repository for researchers to replicate and build on our result.

cs.OH↗

arXiv2023

FastSample: Accelerating Distributed Graph Neural Network Training for Billion-Scale Graphs

Training Graph Neural Networks(GNNs) on a large monolithic graph presents unique challenges as the graph cannot fit within a single machine and it cannot be decomposed into smaller disconnected components. Distributed sampling-based training distributes the graph across multiple machines and trains the GNN on small parts of the graph that are randomly sampled every training iteration. We show that in a distributed environment, the sampling overhead is a significant component of the training time for large-scale graphs. We propose FastSample which is composed of two synergistic techniques that greatly reduce the distributed sampling time: 1)a new graph partitioning method that eliminates most of the communication rounds in distributed sampling , 2)a novel highly optimized sampling kernel that reduces memory movement during sampling. We test FastSample on large-scale graph benchmarks and show that FastSample speeds up distributed sampling-based GNN training by up to 2x with no loss in accuracy.

cs.DC↗

arXiv2023

Towards Foundation Models for Knowledge Graph Reasoning

Foundation models in language and vision have the ability to run inference on any textual and visual inputs thanks to the transferable representations such as a vocabulary of tokens in language. Knowledge graphs (KGs) have different entity and relation vocabularies that generally do not overlap. The key challenge of designing foundation models on KGs is to learn such transferable representations that enable inference on any graph with arbitrary entity and relation vocabularies. In this work, we make a step towards such foundation models and present ULTRA, an approach for learning universal and transferable graph representations. ULTRA builds relational representations as a function conditioned on their interactions. Such a conditioning strategy allows a pre-trained ULTRA model to inductively generalize to any unseen KG with any relation vocabulary and to be fine-tuned on any graph. Conducting link prediction experiments on 57 different KGs, we find that the zero-shot inductive inference performance of a single pre-trained ULTRA model on unseen graphs of various sizes is often on par or better than strong baselines trained on specific graphs. Fine-tuning further boosts the performance.

cs.CL↗

arXiv2021

Exploiting Long-Term Dependencies for Generating Dynamic Scene Graphs

Dynamic scene graph generation from a video is challenging due to the temporal dynamics of the scene and the inherent temporal fluctuations of predictions. We hypothesize that capturing long-term temporal dependencies is the key to effective generation of dynamic scene graphs. We propose to learn the long-term dependencies in a video by capturing the object-level consistency and inter-object relationship dynamics over object-level long-term tracklets using transformers. Experimental results demonstrate that our Dynamic Scene Graph Detection Transformer (DSG-DETR) outperforms state-of-the-art methods by a significant margin on the benchmark dataset Action Genome. Our ablation studies validate the effectiveness of each component of the proposed approach. The source code is available at https://github.com/Shengyu-Feng/DSG-DETR.

cs.CV↗

arXiv2021

Implicit SVD for Graph Representation Learning

Recent improvements in the performance of state-of-the-art (SOTA) methods for Graph Representational Learning (GRL) have come at the cost of significant computational resource requirements for training, e.g., for calculating gradients via backprop over many data epochs. Meanwhile, Singular Value Decomposition (SVD) can find closed-form solutions to convex problems, using merely a handful of epochs. In this paper, we make GRL more computationally tractable for those with modest hardware. We design a framework that computes SVD of \textit{implicitly} defined matrices, and apply this framework to several GRL tasks. For each task, we derive linear approximation of a SOTA model, where we design (expensive-to-store) matrix $\mathbf{M}$ and train the model, in closed-form, via SVD of $\mathbf{M}$, without calculating entries of $\mathbf{M}$. By converging to a unique point in one step, and without calculating gradients, our models show competitive empirical test performance over various graphs such as article citation and biological interaction networks. More importantly, SVD can initialize a deeper model, that is architected to be non-linear almost everywhere, though behaves linearly when its parameters reside on a hyperplane, onto which SVD initializes. The deeper model can then be fine-tuned within only a few epochs. Overall, our procedure trains hundreds of times faster than state-of-the-art methods, while competing on empirical test performance. We open-source our implementation at: https://github.com/samihaija/isvd

cs.LG↗

arXiv2021

Sequential Aggregation and Rematerialization: Distributed Full-batch Training of Graph Neural Networks on Large Graphs

We present the Sequential Aggregation and Rematerialization (SAR) scheme for distributed full-batch training of Graph Neural Networks (GNNs) on large graphs. Large-scale training of GNNs has recently been dominated by sampling-based methods and methods based on non-learnable message passing. SAR on the other hand is a distributed technique that can train any GNN type directly on an entire large graph. The key innovation in SAR is the distributed sequential rematerialization scheme which sequentially re-constructs then frees pieces of the prohibitively large GNN computational graph during the backward pass. This results in excellent memory scaling behavior where the memory consumption per worker goes down linearly with the number of workers, even for densely connected graphs. Using SAR, we report the largest applications of full-batch GNN training to-date, and demonstrate large memory savings as the number of workers increases. We also present a general technique based on kernel fusion and attention-matrix rematerialization to optimize both the runtime and memory efficiency of attention-based models. We show that, coupled with SAR, our optimized attention kernels lead to significant speedups and memory savings in attention-based GNNs.We made the SAR GNN training library publicy available: \url{https://github.com/IntelLabs/SAR}.

cs.LG↗

arXiv2021

On Local Aggregation in Heterophilic Graphs

Many recent works have studied the performance of Graph Neural Networks (GNNs) in the context of graph homophily - a label-dependent measure of connectivity. Traditional GNNs generate node embeddings by aggregating information from a node's neighbors in the graph. Recent results in node classification tasks show that this local aggregation approach performs poorly in graphs with low homophily (heterophilic graphs). Several mechanisms have been proposed to improve the accuracy of GNNs on such graphs by increasing the aggregation range of a GNN layer, either through multi-hop aggregation, or through long-range aggregation from distant nodes. In this paper, we show that properly tuned classical GNNs and multi-layer perceptrons match or exceed the accuracy of recent long-range aggregation methods on heterophilic graphs. Thus, our results highlight the need for alternative datasets to benchmark long-range GNN aggregation mechanisms. We also show that homophily is a poor measure of the information in a node's local neighborhood and propose the Neighborhood Information Content(NIC) metric, which is a novel information-theoretic graph metric. We argue that NIC is more relevant for local aggregation methods as used by GNNs. We show that, empirically, it correlates better with GNN accuracy in node classification tasks than homophily.

cs.LG↗

arXiv2020

Attention-based Image Upsampling

Convolutional layers are an integral part of many deep neural network solutions in computer vision. Recent work shows that replacing the standard convolution operation with mechanisms based on self-attention leads to improved performance on image classification and object detection tasks. In this work, we show how attention mechanisms can be used to replace another canonical operation: strided transposed convolution. We term our novel attention-based operation attention-based upsampling since it increases/upsamples the spatial dimensions of the feature maps. Through experiments on single image super-resolution and joint-image upsampling tasks, we show that attention-based upsampling consistently outperforms traditional upsampling methods based on strided transposed convolution or based on adaptive filters while using fewer parameters. We show that the inherent flexibility of the attention mechanism, which allows it to use separate sources for calculating the attention coefficients and the attention targets, makes attention-based upsampling a natural choice when fusing information from multiple image modalities.

cs.CV↗

arXiv2020

Permutohedral-GCN: Graph Convolutional Networks with Global Attention

Graph convolutional networks (GCNs) update a node's feature vector by aggregating features from its neighbors in the graph. This ignores potentially useful contributions from distant nodes. Identifying such useful distant contributions is challenging due to scalability issues (too many nodes can potentially contribute) and oversmoothing (aggregating features from too many nodes risks swamping out relevant information and may result in nodes having different labels but indistinguishable features). We introduce a global attention mechanism where a node can selectively attend to, and aggregate features from, any other node in the graph. The attention coefficients depend on the Euclidean distance between learnable node embeddings, and we show that the resulting attention-based global aggregation scheme is analogous to high-dimensional Gaussian filtering. This makes it possible to use efficient approximate Gaussian filtering techniques to implement our attention-based global aggregation scheme. By employing an approximate filtering method based on the permutohedral lattice, the time complexity of our proposed global aggregation scheme only grows linearly with the number of nodes. The resulting GCNs, which we term permutohedral-GCNs, are differentiable and trained end-to-end, and they achieve state of the art performance on several node classification benchmarks.

cs.AI↗

arXiv2019

Robust Federated Learning Through Representation Matching and Adaptive Hyper-parameters

Federated learning is a distributed, privacy-aware learning scenario which trains a single model on data belonging to several clients. Each client trains a local model on its data and the local models are then aggregated by a central party. Current federated learning methods struggle in cases with heterogeneous client-side data distributions which can quickly lead to divergent local models and a collapse in performance. Careful hyper-parameter tuning is particularly important in these cases but traditional automated hyper-parameter tuning methods would require several training trials which is often impractical in a federated learning setting. We describe a two-pronged solution to the issues of robustness and hyper-parameter tuning in federated learning settings. We propose a novel representation matching scheme that reduces the divergence of local models by ensuring the feature representations in the global (aggregate) model can be derived from the locally learned representations. We also propose an online hyper-parameter tuning scheme which uses an online version of the REINFORCE algorithm to find a hyper-parameter distribution that maximizes the expected improvements in training loss. We show on several benchmarks that our two-part scheme of local representation matching and global adaptive hyper-parameters significantly improves performance and training robustness.

cs.LG↗

arXiv2019

Single-bit-per-weight deep convolutional neural networks without batch-normalization layers for embedded systems

Batch-normalization (BN) layers are thought to be an integrally important layer type in today's state-of-the-art deep convolutional neural networks for computer vision tasks such as classification and detection. However, BN layers introduce complexity and computational overheads that are highly undesirable for training and/or inference on low-power custom hardware implementations of real-time embedded vision systems such as UAVs, robots and Internet of Things (IoT) devices. They are also problematic when batch sizes need to be very small during training, and innovations such as residual connections introduced more recently than BN layers could potentially have lessened their impact. In this paper we aim to quantify the benefits BN layers offer in image classification networks, in comparison with alternative choices. In particular, we study networks that use shifted-ReLU layers instead of BN layers. We found, following experiments with wide residual networks applied to the ImageNet, CIFAR 10 and CIFAR 100 image classification datasets, that BN layers do not consistently offer a significant advantage. We found that the accuracy margin offered by BN layers depends on the data set, the network size, and the bit-depth of weights. We conclude that in situations where BN layers are undesirable due to speed, memory or complexity costs, that using shifted-ReLU layers instead should be considered; we found they can offer advantages in all these areas, and often do not impose a significant accuracy cost.

cs.LG↗

arXiv2019

Parameter Efficient Training of Deep Convolutional Neural Networks by Dynamic Sparse Reparameterization

Modern deep neural networks are typically highly overparameterized. Pruning techniques are able to remove a significant fraction of network parameters with little loss in accuracy. Recently, techniques based on dynamic reallocation of non-zero parameters have emerged, allowing direct training of sparse networks without having to pre-train a large dense model. Here we present a novel dynamic sparse reparameterization method that addresses the limitations of previous techniques such as high computational cost and the need for manual configuration of the number of free parameters allocated to each layer. We evaluate the performance of dynamic reallocation methods in training deep convolutional networks and show that our method outperforms previous static and dynamic reparameterization methods, yielding the best accuracy for a fixed parameter budget, on par with accuracies obtained by iteratively pruning a pre-trained dense model. We further investigated the mechanisms underlying the superior generalization performance of the resultant sparse networks. We found that neither the structure, nor the initialization of the non-zero parameters were sufficient to explain the superior performance. Rather, effective learning crucially depended on the continuous exploration of the sparse network structure space during training. Our work suggests that exploring structural degrees of freedom during training is more effective than adding extra parameters to the network.

cs.LG↗