Neural Information Processing Systems http://nips.cc/

Convolutional Neural Networks (CNN) are being actively explored for safety-critical applications such as autonomous vehicles and aerospace, where it is essential to ensure the reliability of inference results in the presence of possible memory faults. Traditional methods such as error correction codes (ECC) and Triple Modular Redundancy (TMR) are CNN-oblivious and incur substantial memory overhead and energy cost. This paper introduces in-place zero-space ECC assisted with a new training scheme weight distribution-oriented training. The new method provides the first known zero space cost memory protection for CNNs without compromising the reliability offered by traditional ECC.

The massive growth in the utilization of edge AI has made the applications of machine learning models ubiquitous in different domains. Despite the computation and communication efficiency of these systems, due to limited computation resources on edge devices, relying on more computationally rich systems on the cloud side is inevitable in most cases. Cloud inference systems can achieve the best performance while the computation and communication cost is dramatically increasing by the expansion of a number of edge devices relying on these systems. Hence, there is a trade-off between the computation, communication, and performance of these systems. In this paper, we propose a novel framework, dubbed as Eccentric that learns models with different levels of trade-offs between these conflicting objectives. This framework, based on an adaptation of knowledge from the edge model to the cloud one, reduces the computation and communication costs of the system during inference while achieving the best performance possible. The Eccentric framework can be considered as a new form of compression method suited for edge-cloud inference systems to reduce both computation and communication costs. Empirical studies on classification and object detection tasks corroborate the efficacy of this framework.

Topological features capture global geometric structure in imaging data, but practical adoption in deep learning requires both computational efficiency and differentiability. We present optimized GPU kernels for the Euler Characteristic Curve (ECC) computation achieving 16-2000Ö speedups over prior GPU implementations on synthetic grids, and introduce a differentiable PyTorch layer enabling end-to-end learning. Our CUDA kernels, optimized for Ampere GPUs use 128B-coalesced access and hierarchical shared-memory accumulation. Our PyTorch layer learns thresholds in a single direction via a Differentiable Euler Characteristic Transform-style sigmoid relaxation. We discuss downstream relevance, including applications highlighted by prior ECC work, and outline batching/multi-GPU extensions to broaden adoption.

Here, we are motivated by both the Hopfield network and by strong error-correcting codes (ECCs).

This paper introduces in-place zero-space ECC assisted with a new training scheme weight distribution-oriented training .

Clustering is a fundamental task in both machine learning and data mining. Among various methods, edge-colored clustering (ECC) has emerged as a useful approach for handling categorical data. Given a hypergraph with (hyper)edges labeled by colors, ECC aims to assign vertex colors to minimize the number of edges where the vertex color differs from the edge's color. However, traditional ECC has inherent limitations, as it enforces a nonoverlapping and exhaustive clustering. To tackle these limitations, three versions of ECC have been studied: Local ECC and Global ECC, which allow overlapping clusters, and Robust ECC, which accounts for vertex outliers. For these problems, both linear programming (LP) rounding algorithms and greedy combinatorial algorithms have been proposed. While these LP-rounding algorithms provide high-quality solutions, they demand substantial computation time; the greedy algorithms, on the other hand, run very fast but often compromise solution quality. In this paper, we present an algorithmic framework that combines the strengths of LP with the computational efficiency of combinatorial algorithms. Both experimental and theoretical analyses show that our algorithms efficiently produce high-quality solutions for all three problems: Local, Global, and Robust ECC. We complement our algorithmic contributions with complexity-theoretic inapproximability results and integrality gap bounds, which suggest that significant theoretical improvements are unlikely. Our results also answer two open questions previously raised in the literature.

Large Language Models (LLMs) require robust confidence estimation, particularly in critical domains like healthcare and law where unreliable outputs can lead to significant consequences. Despite much recent work in confidence estimation, current evaluation frameworks rely on correctness functions -- various heuristics that are often noisy, expensive, and possibly introduce systematic biases. These methodological weaknesses tend to distort evaluation metrics and thus the comparative ranking of confidence measures. We introduce MCQA-Eval, an evaluation framework for assessing confidence measures in Natural Language Generation (NLG) that eliminates dependence on an explicit correctness function by leveraging gold-standard correctness labels from multiple-choice datasets. MCQA-Eval enables systematic comparison of both internal state-based white-box (e.g. logit-based) and consistency-based black-box confidence measures, providing a unified evaluation methodology across different approaches. Through extensive experiments on multiple LLMs and widely used QA datasets, we report that MCQA-Eval provides efficient and more reliable assessments of confidence estimation methods than existing approaches.

Edge-colored clustering (ECC) is an optimization framework for clustering datasets characterized by categorical relationships among data points. The problem is formally encoded as an edge-colored hypergraph (Figure 1), where each edge represents an interaction between data objects (the nodes) and the color of the edge indicates the type or category of that interaction. The goal is to assign colors to nodes in such a way that edges of a color tend to include nodes of that color, by minimizing or maximizing some objective function relating edge colors and node colors. ECC algorithms have been applied to various clustering tasks where cluster labels naturally match with interaction types. For example, if nodes are researchers, edges are author lists for publications, and colors indicate publication field (computer science, biology, etc.), then ECC provides a framework for inferring researchers' fields based on publications. ECC has also been used for temporal hypergraph clustering [Amburg et al., 2020], where edge colors encode time windows in which interactions occur. ECC then clusters nodes into time windows in which they are especially active. Variants of ECC have also been used for team formation [Amburg et al., 2022], in which case nodes are people, edges represent team tasks, and colors indicate task type. In this setting, ECC corresponds to assigning tasks based on prior team experiences.

This paper presents a novel form of associative content addressable (ACA) memory systems. The canonical model for ACA memory is the Hopfield network, which can only store approximately N patterns of N bits. The authors use developments from error-correcting codes (ECCs) to implement an ACA that can store e N, N bit patterns. This is accomplished by using a bipartite expander graph, which is essentially a restricted Boltzmann machine (RBM) wherein the hidden nodes are actually clusters of units that are mutually inhibitory. The authors demonstrate that these networks have dynamics that can engage in error correction similar to ECCs, enabling the storage of exponentially many patterns.