Decoupled Prune-and-Reconstruct (DPR) introduces a double‑layer sparsification strategy for graph neural networks that first prunes nodes to reduce memory usage and then reconstructs the full graph during inference. By training on a compact core of 30% of the nodes, DPR achieves 96.9% of the accuracy of a dense model while using only 1,450 MiB of peak memory on a single 6 GB GPU, outperforming edge‑sparsification baselines and reducing training memory by 50.1%. The method scales to millions of nodes, enabling all‑node inference on VRAM‑limited hardware without incurring a permanent accuracy loss.
arXiv:2606. 02608v1 Announce Type: new Abstract: We study a Marchenko--Pastur (MP) random-matrix approach to pruning deep neural networks with very small post-pruning fine-tuning budgets.
arXiv:2606. 09080v1 Announce Type: new Abstract: Pruning has emerged as a dominant paradigm for accelerating large language model (LLM) inference, spanning a broad spectrum of methods that remove computation across tokens, layers, heads, dimensions, and attention patterns.
arXiv:2607. 28418v1 Announce Type: cross Abstract: Pruning is a promising approach for improving the efficiency of LLMs.
arXiv:2607. 17374v1 Announce Type: cross Abstract: Graph Neural Network (GNN) inference on billion-scale graphs is challenging due to the large memory footprint of features and embeddings and high disk I/O costs in out-of-core settings.
arXiv:2606. 12278v1 Announce Type: cross Abstract: Neural network pruning reduces model size by removing less important parameters while aiming to preserve predictive performance.
Scaffold is a new unsupervised graph sparsification framework for graph neural networks that uses support graph theory preconditioners to jointly control dilation and congestion, thereby preserving short communication paths while avoiding bottlenecks. It achieves superior aggregate ranking across 19 homophilic and heterophilic benchmarks, recovering or closely approaching full‑graph GNN performance with only 10%–50% of the original edges. The method reduces memory usage to less than half and cuts end‑to‑end training time, including sparsification overhead.
Task-Aware Spectral Pruning (TASP) is a post‑training framework that tailors sparse masks to specific tasks by calibrating module‑level spectral descriptors against task‑specific ablation effects. It constructs masks that close grouped‑query‑attention and SwiGLU dependencies, routing each user turn to a single compiled mask that remains fixed during prefill and decoding. In experiments, TASP achieves a 43% active‑FLOP reduction while preserving 97.7% of the dense BF16 performance on Llama‑3‑70B, and delivers a 1.44× speedup on an A100 80GB with INT8‑weight/BF16‑compute, reducing decode latency from 45.2 to 31.3 ms/token.
Neural network pruning reduces model size by removing less important parameters while aiming to preserve predictive performance. Although the Lottery Ticket Hypothesis (LTH) shows that sparse subnetworks can match dense networks when trained from suitable initializations, its iterative pruning procedure requires multiple complete training cycles.
The paper presents a method for reliably scheduling operator execution in real‑time inference on small devices, achieving exact peak‑memory predictions and certified optimality. By profiling the generated program and modeling its memory usage, the authors can permute statements to match the modeled peak, guaranteeing bitwise‑identical results on CPUs and characterizing GPU limitations. They also provide efficient lower‑bound traps and analyze selective recomputation, showing it is NP‑hard in general but can reduce peak memory on certain architectures.
The paper introduces EDiS, an Edge‑Disjoint Subgraph sparsification framework that separates a one‑time structural extraction of a graph into cacheable edge‑disjoint subgraphs from the per‑epoch graph composition. By recombining these cached subgraphs under edge‑budget constraints, EDiS avoids repeated sampling or recomputation while allowing varying training graphs across epochs. Experiments on 19 node‑classification benchmarks show that EDiS outperforms 17 baselines in accuracy/ROC‑AUC, achieving the lowest average rank and gap‑to‑best, especially at tight edge budgets.
arXiv:2607. 21985v1 Announce Type: cross Abstract: The increasing deployment of large language models (LLMs) has magnified the computational and memory bottlenecks of autoregressive decoding, where low compute intensity and bandwidth-bound kernels dominate inference cost.
arXiv:2608. 16309v1 Announce Type: cross Abstract: Static pruning is widely used to accelerate sparse neural retrieval, yet existing studies each validate their conclusions within a single custom pipeline, leaving it unclear which findings transfer to modern engines with different index organizations and dynamic pruning mechanisms.