arXiv subjects

Mohammad Hammoud

Publications and source records attributed to Mohammad Hammoud.

4 recordsLinked to original sources

arXiv2026

Avey-B

Compact pretrained bidirectional encoders remain the backbone of industrial NLP under tight compute and memory budgets. Their effectiveness stems from self-attention's ability to deliver high-quality bidirectional contextualization with sequence-level parallelism, as popularized by BERT-style architectures. Recently, Avey was introduced as an autoregressive, attention-free alternative that naturally admits an encoder-only adaptation. In this paper, we reformulate Avey for the encoder-only paradigm and propose several innovations to its architecture, including decoupled static and dynamic parameterizations, stability-oriented normalization, and neural compression. Results show that this reformulated architecture compares favorably to four widely used Transformer-based encoders, consistently outperforming them on standard token-classification and information-retrieval benchmarks while scaling more efficiently to long contexts.

cs.CL↗

arXiv2025

Don't Pay Attention

The Transformer has become the de facto standard for modern language models owing to its parallelizable training and effective autoregressive decoding. However, its fixed context window and the quadratic time and memory costs of its self-attention mechanism remain central bottlenecks. These constraints have revived interest in recurrent architectures that scale linearly with sequence length, but at the cost of reduced parallelism. In this paper, we introduce Avey, a new foundational architecture that breaks away from both attention and recurrence. Avey pairs a ranker with an autoregressive neural processor to select and contextualize only the most relevant tokens for any given token. Specifically, it decouples sequence length from context width, thus enabling effective and efficient processing of arbitrarily long sequences. Results show that Avey compares favorably to the Transformer across a variety of standard short-range NLP benchmarks, while significantly outperforming it on tasks requiring long-range dependency modeling.

cs.CL↗

arXiv2021

CoCoS: Fast and Accurate Distributed Triangle Counting in Graph Streams

Given a graph stream, how can we estimate the number of triangles in it using multiple machines with limited storage? Specifically, how should edges be processed and sampled across the machines for rapid and accurate estimation? The count of triangles (i.e., cliques of size three) has proven useful in numerous applications, including anomaly detection, community detection, and link recommendation. For triangle counting in large and dynamic graphs, recent work has focused largely on streaming algorithms and distributed algorithms but little on their combinations for "the best of both worlds". In this work, we propose CoCoS, a fast and accurate distributed streaming algorithm for estimating the counts of global triangles (i.e., all triangles) and local triangles incident to each node. Making one pass over the input stream, COCOS carefully processes and stores the edges across multiple machines so that the redundant use of computational and storage resources is minimized. Compared to baselines, CoCoS is (a) Accurate: giving up to 39X smaller estimation error, (b) Fast: up to 10.4X faster, scaling linearly with the size of the input stream, and (c) Theoretically sound: yielding unbiased estimates.

cs.DB↗

arXiv2019

Partitioning Graphs for the Cloud using Reinforcement Learning

In this paper, we propose Revolver, a parallel graph partitioning algorithm capable of partitioning large-scale graphs on a single shared-memory machine. Revolver employs an asynchronous processing framework, which leverages reinforcement learning and label propagation to adaptively partition a graph. In addition, it adopts a vertex-centric view of the graph where each vertex is assigned an autonomous agent responsible for selecting a suitable partition for it, distributing thereby the computation across all vertices. The intuition behind using a vertex-centric view is that it naturally fits the graph partitioning problem, which entails that a graph can be partitioned using local information provided by each vertex's neighborhood. We fully implemented and comprehensively tested Revolver using nine real-world graphs. Our results show that Revolver is scalable and can outperform three popular and state-of-the-art graph partitioners via producing comparable localized partitions, yet without sacrificing the load balance across partitions.

cs.DC↗