Fault diagnosis in distributed device clusters (DDCs) is essential for ensuring safe and reliable operation of modern automated systems. However, practical deployments face two fundamental challenges: severe class imbalance from scarce device-level fault data and strict resource constraints on edge nodes. This paper proposes a Lightweight Diffusion-Enhanced Multi-Domain Fusion (LDEMF) framework that addresses both challenges through integrated data balancing, representation learning, and efficient deployment. A dual-attention conditional diffusion model synthesizes class-balanced vibration samples preserving temporal, spectral, and non-stationary fault characteristics. A multi-domain feature fusion network then integrates time-, frequency-, and time-frequency-domain representations via cross-attention for robust fault characterization. Finally, structured channel pruning, knowledge distillation, and FP16 post-training quantization enable resource-efficient edge deployment. Experimental results on the CWRU bearing dataset and a self-collected industrial robot dataset demonstrate that LDEMF achieves superior diagnostic accuracy under moderate-to-severe class imbalance. The framework reduces model size, computational cost, and inference latency by up to an order of magnitude with negligible performance loss, validating its effectiveness for edge-level fault diagnosis in DDCs.

Satya Krishna Gorti, Ilan Gofman, Zhaoyan Liu, Jiapeng Wu, Noël Vouitsis, Guangwei Yu, Jesse C. Cresswell, Rasa Hosseinzadeh. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

Anomaly detection task is an open-set challenge, aiming to identify unseen faulty signals using only healthy signals for training. While data reconstruction frameworks are inherently suited for this task, they often struggle with complex signals due to limited feature extraction capabilities. Contrastive learning offers powerful representation learning, but faces challenges in one-class scenarios and requires effective augmentation techniques. To address these limitations, a novel fault detector is proposed, integrating a redesigned one-class contrastive loss into a data reconstruction framework to endow clustering capability. Learnable feature augmentation is incorporated to ensure effective and generalizable contrastive learning while reducing computational costs by performing augmentation in the feature space. A dilated inception network structure is employed to capture long-distance dependencies in complex input signals. A one-class similarity distance-based threshold is introduced to filter outliers in the healthy signal distribution, and an optimal model selection strategy is proposed based on the minimal threshold during training. The approach is evaluated using two case studies: single-fault and multifault scenarios in a reciprocating compressor. Our method achieves balanced accuracies of 98.44% and 97.81%, respectively, outperforming other methods. These results confirm our detector's capacity to balance false alarms and missed detections effectively, even in challenging multifault conditions.

Data scarcity in prognostic and health management research presents a significant challenge, often hindering the performance of supervised models due to the difficulty of acquiring diverse fault mode data during prolonged faultless operation. Conversely, nominal operating condition (NOC) data, including both healthy and varied faulty data, are more readily available due to predelivery inspection. Subsequently, we study this novel and unresolved NOC premise that leverages NOC data along with healthy data from other conditions to construct a fault diagnoser called Res-1D-bootstrap your own latent (BYOL) with the proposed probability distribution generalization strategy. The initial step involves a novel approach to the contrastive transformation optimization with the criteria based solely on similarity loss obtained in the training stage. We then pretrain the fault detector based on our NOC premise, followed by finetuning the network exclusively with NOC data. Given the novelty of our premise, there are few models for direct comparison. Thus, we contrast our approach with a supervised baseline, MoCo, an unoptimized equivalent algorithm, and an equivalent algorithm that solely employs NOC data for pretraining the feature extractor. Empirical results demonstrate our model's superior distribution generalization capabilities through the improved classification accuracy across different operating conditions.

Computing Power Networking (CPN) represents a transformative paradigm in distributed computing, harnessing the collective capabilities of edge servers dispersed across diverse geographical locations. CPN’s core strengths lie in its ability to accelerate data processing, diminish latency, and scale efficiently, rendering it particularly apt for real-time applications and the Internet of Things. When coupled with blockchain technology, CPN extends its potential by facilitating secure and transparent allocation and trading of computing resources, bolstering data integrity and reliability. However, current research at the intersection of CPN and blockchain primarily focuses on framework development and technology integration, often overlooking the challenge of delivering dependable computing services, especially in the presence of potentially unreliable nodes. To tackle this issue, we introduce a reputation-enhanced resource trading framework, designed to ensure equitable and trustworthy computing power transactions. We establish a decentralized reputation model, capable of accurately assessing node behavior over extended periods. Additionally, we present three optimization mechanisms for reputation updates, accounting for transaction history, quality of service, and transaction amount. Furthermore, our work introduces a reputation-enhanced consensus mechanism within the trading system, strategically employing incentives to motivate participants to deliver high-quality services, thereby increasing their rewards. Simultaneously, it effectively mitigates wealth inequality among resource providers of varying sizes. To validate our approach, we develop a prototype system and conduct performance evaluations, which affirm the superiority of our system in enhancing reputation and delivering robust economic features.

Many existing multiobject tracking (MOT) methods tend to model each object’s feature individually. However, under acute viewpoint variation and occlusion, there may exist significant differences between the current and historical features of objects, which easily leads to object loss. To alleviate these issues, the topological relationships (i.e., geometric shapes formed by objects) should be modeled as a supplement to individual object features to maintain stability. In this article, we propose a novel MOT framework, which consists of a frame graph and association graph, to leverage the topological relationships both spatially and temporally. Technically, the frame graph models distance and angle among objects to resist viewpoint change, while the association graph utilizes the interframe temporal consistency of topological features to recover occluded objects. Extensive experiments on mainstream datasets demonstrate the effectiveness.

Enhancing the endurance, performance, and energy efficiency of encrypted Non-Volatile Main Memory (NVMM) can be achieved by minimizing written data through inline deduplication. However, existing approaches applying inline deduplication to encrypted NVMM suffer from substantial performance degradation due to high computing, memory footprint, and index-lookup overhead to generate, store, and query the cryptographic hash (fingerprint). In the preliminary ESD [ 14 ], we proposed the Error Correcting Code (ECC) assisted selective deduplication scheme, utilizing the ECC information as a fingerprint to identify similar data effectively and then leveraging the selective deduplication technique to eliminate a large amount of redundant data with high reference counts. In this article, we proposed FSDedup. Compared with ESD, FSDedup could leverage the prefetch cache to reduce the read overhead during similarity comparison and utilize the cache refresh mechanism to identify further and eliminate more redundant data. Extensive experimental evaluations demonstrate that FSDedup can enhance the performance of the NVMM system further than the ESD. Experimental results show that FSDedup can improve both write and read speed by up to 1.8×, enhance Instructions Per Cycle by up to 1.5×, and reduce energy consumption by up to 2.0×, compared to ESD.

Reducing write data to encrypted Non-Volatile Main Memory (NVMM) can directly improve NVMM’s endurance, performance, and energy efficiency. However, existing works that straightforwardly apply inline deduplication on encrypted NVMM can significantly lead to system performance degradation due to high computing, memory footprint, and index-lookup overhead to generate, store, and query the cryptographic hash (fingerprint). This paper proposes ESD, an ECC-assisted and Selective Deduplication for encrypted NVMM by exploiting both the device characteristics (ECC mechanism) and the workload characteristics (content locality). First, ESD utilizes the ECC information associated with each cache line evicted from the Last-Level Cache (LLC) as the fingerprint to identify data similarity and avoids the costly hash calculating overhead on the non-duplicate cache lines. Second, ESD leverages selective deduplication to exploit the content locality within cache lines by only storing the fingerprints with high reference counts in the memory cache to reduce the memory space overhead and avoid fingerprints NVMM_lookup operations. The experimental results show that ESD can significantly speed up the writes by up to 3.4x, 4.3x, and 2.6x, speed up the reads by up to 5.3x, 5.0x, and 2.0x, and reduce the energy consumption by up to 96.3%, 96.2%, and 56.6% than Baseline, Dedup SHA1, and DeWrite, respectively. Meanwhile, ESD also can significantly outperform other schemes in tail latency.

Large-scale recommender systems are integral parts of many services. With the recent rapid growth of accessible data, the need for efficient training methods has arisen. Given the high computational cost of training state-of-the-art graph neural network (GNN) based models, it is infeasible to train them from scratch with every new set of interactions. In this work, we present a novel framework for incrementally training GNN-based models. Our framework takes advantage of an experience reply technique built on top of a structurally aware reservoir sampling method tailored for this setting. This framework addresses catastrophic forgetting, allowing the model to preserve its understanding of users' long-term behavioral patterns while adapting to new trends. Our experiments demonstrate the superior performance of our framework on numerous datasets when combined with state-of-the-art GNN-based models.

Non-Volatile Memories (NVMs) have shown tremendous potential to be the next generation of main memory, yet they are still seriously hampered by the high write latency and limited endurance. In this paper, we first unveil via realworld benchmark analysis that the words within the same cache line showcase a high degree of similarity. We therefore present SimiEncode, a low-overhead and effective Similarity-based Encoding approach. SimiEncode relieves writes to NVMs by (1) generating a mask word with minimized differences to the words within a cache line, (2) encoding each word with the associated mask word by simple XOR operations, and (3) writing a single tag bit to indicate the resulting zero word after encoding. Our prototype implementation of SimiEncode and extensive evaluations driven by 15 state-of-the-art benchmarks demonstrate that, compared with existing approaches, SimiEncode significantly prolongs the lifetime and improves the performance. Importantly, SimiEncode is orthogonal to and can be easily incorporated into existing bit flipping optimizations.

Reasoning in a temporal knowledge graph (TKG) is a critical task for information retrieval and semantic search. It is particularly challenging when the TKG is updated frequently. The model has to adapt to changes in the TKG for efficient training and inference while preserving its performance on historical knowledge. Recent work approaches TKG completion (TKGC) by augmenting the encoder-decoder framework with a time-aware encoding function. However, naively fine-tuning the model at every time step using these methods does not address the problems of 1) catastrophic forgetting, 2) the model's inability to identify the change of facts (e.g., the change of the political affiliation and end of a marriage), and 3) the lack of training efficiency. To address these challenges, we present the Time-aware Incremental Embedding (TIE) framework, which combines TKG representation learning, experience replay, and temporal regularization. We introduce a set of metrics that characterizes the intransigence of the model and propose a constraint that associates the deleted facts with negative labels.

Neural abstractive summarization systems have achieved promising progress, thanks to the availability of large-scale datasets and models pre-trained with self-supervised methods.However, ensuring the factual consistency of the generated summaries for abstractive summarization systems is a challenge.We propose a post-editing corrector module to address this issue by identifying and correcting factual errors in generated summaries.The neural corrector model is pre-trained on artificial examples that are created by applying a series of heuristic transformations on reference summaries.These transformations are inspired by an error analysis of state-of-the-art summarization model outputs.Experimental results show that our model is able to correct factual errors in summaries generated by other neural summarization models and outperforms previous models on factual consistency evaluation on the CNN/DailyMail dataset.We also find that transferring from artificial error correction to downstream settings is still very challenging 1 .Article: Jerusalem (CNN)The flame of remembrance burns in Jerusalem, and a song of memory haunts Valerie Braham as it never has before.(...) "Now I truly understand everyone who has lost a loved one," Braham said.Her husband, Philippe Braham, was one of 17 people killed in January's terror attacks in Paris.He was in a kosher supermarket when a gunman stormed in, killing four people, all of them Jewish.(...) Original: Valerie braham was one of 17 people killed in january's terror attacks in paris.(inconsistent) Corrected: Philippe braham was one of 17 people killed in january's terror attacks in paris.(consistent) Article: (...) Thursday's attack by al-Shabaab militants killed 147 people, including 142 students, three security officers and two university security personnel.The attack left 104 people injured, including 19 who are in critical condition, Nkaissery said.(...) Original: 147 people, including 142 students, are in critical condition.(inconsistent) Corrected: 19 people, including 142 students, are in critical condition.(inconsistent) Article: (CNN) Officer Michael Slager's five-year career with the North Charleston Police Department in South Carolina ended after he resorted to deadly force following a routine traffic stop.(...) His back is to Slager, who, from a few yards away, raises his gun and fires.Slager is now charged with murder.The FBI is involved in the investigation of the slaying of the father of four.(...) Original: Slager is now charged with murder.(consistent) Corrected: Michael Slager is now charged with murder.(consistent) Article: (CNN)The announcement this year of a new, original Dr. Seuss book sent a wave of nostalgic giddiness across Twitter, and months before publication, the number of pre-orders for "What Pet Should I Get?" continues to climb.(...) It features the spirited siblings from the beloved classic "One Fish Two Fish Red Fish Blue Fish" and is believed to have been written between 1958 and 1962.(...) Original: Seuss book sent a wave of nostalgic giddiness across twitter.(consistent) Corrected: "One Fish Two Fish Red Fish Blue Fish" book sent a wave of nostalgic giddiness across twitter.(inconsistent)

Inferring missing facts in temporal knowledge graphs (TKGs) is a fundamental and challenging task.Previous works have approached this problem by augmenting methods for static knowledge graphs to leverage time-dependent representations.However, these methods do not explicitly leverage multi-hop structural information and temporal facts from recent time steps to enhance their predictions.Additionally, prior work does not explicitly address the temporal sparsity and variability of entity distributions in TKGs.We propose the Temporal Message Passing (TeMP) framework to address these challenges by combining graph neural networks, temporal dynamics models, data imputation and frequency-based gating techniques.Experiments 1 on standard TKG tasks show that our approach provides substantial gains compared to the previous state of the art, achieving a 10.7% average relative improvement in Hits@10 across three standard benchmarks.Our analysis also reveals important sources of variability both within and across TKG datasets, and we introduce several simple but strong baselines that outperform the prior state of the art in certain settings.