arXiv subjects

Yuchong Hu

Publications and source records attributed to Yuchong Hu.

At least 19 recordsLinked to original sources

arXiv2026

In-situ Indexing via Memristive Content-Addressable Memory

Processing-in-Memory (PIM) is a proven paradigm for overcoming the ``memory wall". However, while data indexing is severely bottlenecked by this same wall, it remains unclear how indexing can effectively benefit from PIM's unique capabilities. We present PATH, an in-situ indexing architecture that bridges this gap by leveraging the massive parallelism and inherent data-movement of PIMs. Specifically, we first reformulate the fundamental indexing operations, namely Insert, Search, Update, and Delete, into highly parallel in-situ content-addressable memory operations executed directly within memory arrays. Taking hash indexes as a typical case, we elaborate how PATH breaks the inherent trade-off among memory accesses, load factor, and process latency in conventional hashing schemes. By adopting ultra-large logical buckets and in-memory moving, PATH virtually eliminates the cost of hash collision resolution and significantly reduces resizing overhead. Compared with state-of-the-art schemes, PATH achieves $4.7-7.8\times$ higher throughput, $>14.5\times$ lower tail latency, and $>61.4\%$ fewer memory accesses under insertions, laying a scalable foundation for next-generation data-centric computing.

cs.AR↗

arXiv2025

Optimizing Frequent Checkpointing via Low-Cost Differential for Distributed Training Systems

Distributed training of large deep-learning models often leads to failures, so checkpointing is commonly employed for recovery. State-of-the-art studies focus on frequent checkpointing for fast recovery from failures. However, frequent checkpointing generates numerous checkpoints, incurring substantial costs and thus degrading training performance. Recently, differential checkpointing has been proposed to reduce costs, but it is limited to recommendation systems, so its application to general distributed training systems remains unexplored. In this paper, we find that gradients generated during distributed training can be reused to construct differential checkpoints, while the former's size is smaller than the latter's, motivating us to reuse gradients for low-cost differential checkpointing. Based on this main idea, we propose \sysname, a frequent checkpointing framework for compression-enabled training systems that reuses compressed gradients as differential checkpoints, eliminating redundant differential computation and reducing checkpoint transmission cost. Furthermore, we extend gradient reuse to scenarios without gradient compression and propose \sysnameplus, which employs layer-wise-reuse snapshotting and incremental-merging persistence to overlap checkpointing with training execution. Experiments on diverse workloads, including billion-parameter-scale models, demonstrate that \sysname and \sysnameplus significantly reduce checkpointing overhead and enable checkpointing at frequencies as high as once per iteration, reducing training time by up to 89.2\% and 81.2\%, respectively.

cs.DC↗

arXiv2022

Multi-Modal Cross-Domain Alignment Network for Video Moment Retrieval

As an increasingly popular task in multimedia information retrieval, video moment retrieval (VMR) aims to localize the target moment from an untrimmed video according to a given language query. Most previous methods depend heavily on numerous manual annotations (i.e., moment boundaries), which are extremely expensive to acquire in practice. In addition, due to the domain gap between different datasets, directly applying these pre-trained models to an unseen domain leads to a significant performance drop. In this paper, we focus on a novel task: cross-domain VMR, where fully-annotated datasets are available in one domain (``source domain''), but the domain of interest (``target domain'') only contains unannotated datasets. As far as we know, we present the first study on cross-domain VMR. To address this new task, we propose a novel Multi-Modal Cross-Domain Alignment (MMCDA) network to transfer the annotation knowledge from the source domain to the target domain. However, due to the domain discrepancy between the source and target domains and the semantic gap between videos and queries, directly applying trained models to the target domain generally leads to a performance drop. To solve this problem, we develop three novel modules: (i) a domain alignment module is designed to align the feature distributions between different domains of each modality; (ii) a cross-modal alignment module aims to map both video and query features into a joint embedding space and to align the feature distributions between different modalities in the target domain; (iii) a specific alignment module tries to obtain the fine-grained similarity between a specific frame and the given query for optimal localization. By jointly training these three modules, our MMCDA can learn domain-invariant and semantic-aligned cross-modal representations.

cs.CV↗

arXiv2021

Emotion-aware Chat Machine: Automatic Emotional Response Generation for Human-like Emotional Interaction

The consistency of a response to a given post at semantic-level and emotional-level is essential for a dialogue system to deliver human-like interactions. However, this challenge is not well addressed in the literature, since most of the approaches neglect the emotional information conveyed by a post while generating responses. This article addresses this problem by proposing a unifed end-to-end neural architecture, which is capable of simultaneously encoding the semantics and the emotions in a post for generating more intelligent responses with appropriately expressed emotions. Extensive experiments on real-world data demonstrate that the proposed method outperforms the state-of-the-art methods in terms of both content coherence and emotion appropriateness.

cs.CL↗

arXiv2021

Multi-level Forwarding and Scheduling Recovery Algorithm in Rapidly-changing Network for Erasure-coded Clusters

A key design goal of erasure-coded clusters is to reduce the repair time. The existing Erasure-coded data repair schemes are roughly classified into two categories: 1. Designing rapid data repair (e.g., PPR) in a homogeneous environment. 2. Constructing data repair (e.g., PPT) based on bandwidth in a heterogeneous environment. However, these solutions are difficult to cope with the heterogeneous and Rapidly-changing network in erasure-coded clusters. To address this problem, a bandwidth-aware multi-level forwarding repair algorithm, called BMFRepair, is proposed. BMFRepair monitors the network bandwidth in real time when data is forwarded, and selects idle nodes with high-bandwidth links to assist in forwarding. Thus, it can reduce the time bottleneck caused by low link transmission. At the same time, multi-node repair becomes very complicated when the bandwidth changes drastically. A multi-node scheduling repairing algorithm, called MSRepair, is proposed for multi-node repairing problems, which can repair multiple failed blocks in parallel by scheduling node resources. The two algorithms can flexibly adapt to the rapidly changing network environment and make full use of the bandwidth resources of idle nodes. Most importantly, algorithms can continuously adjust the repair plan according to the bandwidth change in fast and dynamic network. The algorithms have been evaluated by both simulations on Mininet and real experiments on Aliyun cloud platform ECS. Results show that compared with the state-of-the-art repair schemes PPR and PPT, the algorithms can significantly reduce the repair time in rapidly-changing network.

cs.NI↗

arXiv2021

Target Guided Emotion Aware Chat Machine

The consistency of a response to a given post at semantic-level and emotional-level is essential for a dialogue system to deliver human-like interactions. However, this challenge is not well addressed in the literature, since most of the approaches neglect the emotional information conveyed by a post while generating responses. This article addresses this problem by proposing a unifed end-to-end neural architecture, which is capable of simultaneously encoding the semantics and the emotions in a post and leverage target information for generating more intelligent responses with appropriately expressed emotions. Extensive experiments on real-world data demonstrate that the proposed method outperforms the state-of-the-art methods in terms of both content coherence and emotion appropriateness.

cs.CL↗

arXiv2020

V3H: View Variation and View Heredity for Incomplete Multi-view Clustering

Real data often appear in the form of multiple incomplete views. Incomplete multi-view clustering is an effective method to integrate these incomplete views. Previous methods only learn the consistent information between different views and ignore the unique information of each view, which limits their clustering performance and generalizations. To overcome this limitation, we propose a novel View Variation and View Heredity approach (V3H). Inspired by the variation and the heredity in genetics, V3H first decomposes each subspace into a variation matrix for the corresponding view and a heredity matrix for all the views to represent the unique information and the consistent information respectively. Then, by aligning different views based on their cluster indicator matrices, V3H integrates the unique information from different views to improve the clustering performance. Finally, with the help of the adjustable low-rank representation based on the heredity matrix, V3H recovers the underlying true data structure to reduce the influence of the large incompleteness. More importantly, V3H presents possibly the first work to introduce genetics to clustering algorithms for learning simultaneously the consistent information and the unique information from incomplete multi-view data. Extensive experimental results on fifteen benchmark datasets validate its superiority over other state-of-the-arts.

cs.LG↗

arXiv2020

Repair Pipelining for Erasure-Coded Storage: Algorithms and Evaluation

We propose repair pipelining, a technique that speeds up the repair performance in general erasure-coded storage. By carefully scheduling the repair of failed data in small-size units across storage nodes in a pipelined manner, repair pipelining reduces the single-block repair time to approximately the same as the normal read time for a single block in homogeneous environments. We further design different extensions of repair pipelining algorithms for heterogeneous environments and multi-block repair operations. We implement a repair pipelining prototype, called ECPipe, and integrate it as a middleware system into two versions of Hadoop Distributed File System (HDFS) (namely HDFS-RAID and HDFS-3) as well as Quantcast File System (QFS). Experiments on a local testbed and Amazon EC2 show that repair pipelining significantly improves the performance of degraded reads and full-node recovery over existing repair techniques.

cs.DC↗

arXiv2020

ANIMC: A Soft Framework for Auto-weighted Noisy and Incomplete Multi-view Clustering

Multi-view clustering has wide applications in many image processing scenarios. In these scenarios, original image data often contain missing instances and noises, which is ignored by most multi-view clustering methods. However, missing instances may make these methods difficult to use directly and noises will lead to unreliable clustering results. In this paper, we propose a novel Auto-weighted Noisy and Incomplete Multi-view Clustering framework (ANIMC) via a soft auto-weighted strategy and a doubly soft regular regression model. Firstly, by designing adaptive semi-regularized nonnegative matrix factorization (adaptive semi-RNMF), the soft auto-weighted strategy assigns a proper weight to each view and adds a soft boundary to balance the influence of noises and incompleteness. Secondly, by proposing{\theta}-norm, the doubly soft regularized regression model adjusts the sparsity of our model by choosing different{\theta}. Compared with existing methods, ANIMC has three unique advantages: 1) it is a soft algorithm to adjust our framework in different scenarios, thereby improving its generalization ability; 2) it automatically learns a proper weight for each view, thereby reducing the influence of noises; 3) it performs doubly soft regularized regression that aligns the same instances in different views, thereby decreasing the impact of missing instances. Extensive experimental results demonstrate its superior advantages over other state-of-the-art methods.

cs.CV↗

arXiv2020

Double Self-weighted Multi-view Clustering via Adaptive View Fusion

Multi-view clustering has been applied in many real-world applications where original data often contain noises. Some graph-based multi-view clustering methods have been proposed to try to reduce the negative influence of noises. However, previous graph-based multi-view clustering methods treat all features equally even if there are redundant features or noises, which is obviously unreasonable. In this paper, we propose a novel multi-view clustering framework Double Self-weighted Multi-view Clustering (DSMC) to overcome the aforementioned deficiency. DSMC performs double self-weighted operations to remove redundant features and noises from each graph, thereby obtaining robust graphs. For the first self-weighted operation, it assigns different weights to different features by introducing an adaptive weight matrix, which can reinforce the role of the important features in the joint representation and make each graph robust. For the second self-weighting operation, it weights different graphs by imposing an adaptive weight factor, which can assign larger weights to more robust graphs. Furthermore, by designing an adaptive multiple graphs fusion, we can fuse the features in the different graphs to integrate these graphs for clustering. Experiments on six real-world datasets demonstrate its advantages over other state-of-the-art multi-view clustering methods.

cs.LG↗

arXiv2020

Unbalanced Incomplete Multi-view Clustering via the Scheme of View Evolution: Weak Views are Meat; Strong Views do Eat

Incomplete multi-view clustering is an important technique to deal with real-world incomplete multi-view data. Previous works assume that all views have the same incompleteness, i.e., balanced incompleteness. However, different views often have distinct incompleteness, i.e., unbalanced incompleteness, which results in strong views (low-incompleteness views) and weak views (high-incompleteness views). The unbalanced incompleteness prevents us from directly using the previous methods for clustering. In this paper, inspired by the effective biological evolution theory, we design the novel scheme of view evolution to cluster strong and weak views. Moreover, we propose an Unbalanced Incomplete Multi-view Clustering method (UIMC), which is the first effective method based on view evolution for unbalanced incomplete multi-view clustering. Compared with previous methods, UIMC has two unique advantages: 1) it proposes weighted multi-view subspace clustering to integrate these unbalanced incomplete views, which effectively solves the unbalanced incomplete multi-view problem; 2) it designs the low-rank and robust representation to recover the data, which diminishes the impact of the incompleteness and noises. Extensive experimental results demonstrate that UIMC improves the clustering performance by up to 40% on three evaluation metrics over other state-of-the-art methods.

cs.LG↗

arXiv2019

A New Design of Binary MDS Array Codes with Asymptotically Weak-Optimal Repair

Binary maximum distance separable (MDS) array codes are a special class of erasure codes for distributed storage that not only provide fault tolerance with minimum storage redundancy but also achieve low computational complexity. They are constructed by encoding $k$ information columns into $r$ parity columns, in which each element in a column is a bit, such that any $k$ out of the $k+r$ columns suffice to recover all information bits. In addition to providing fault tolerance, it is critical to improve repair performance in practical applications. Specifically, if a single column fails, our goal is to minimize the repair bandwidth by downloading the least amount of bits from $d$ healthy columns, where $k\leq d\leq k+r-1$. If one column of an MDS code is failed, it is known that we need to download at least $1/(d-k+1)$ fraction of the data stored in each of $d$ healthy columns. If this lower bound is achieved for the repair of the failure column from accessing arbitrary $d$ healthy columns, we say that the MDS code has optimal repair. However, if such lower bound is only achieved by $d$ specific healthy columns, then we say the MDS code has weak-optimal repair. In this paper, we propose two explicit constructions of binary MDS array codes with more parity columns (i.e., $r\geq 3$) that achieve asymptotically weak-optimal repair, where $k+1\leq d\leq k+\lfloor(r-1)/2\rfloor$, and "asymptotic" means that the repair bandwidth achieves the minimum value asymptotically in $d$. Codes in the first construction have odd number of parity columns and asymptotically weak-optimal repair for any one information failure, while codes in the second construction have even number of parity columns and asymptotically weak-optimal repair for any one column failure.

cs.IT↗

arXiv2019

Rack-Aware Regenerating Codes for Data Centers

Erasure coding is widely used for massive storage in data centers to achieve high fault tolerance and low storage redundancy. Since the cross-rack communication cost is often high, it is critical to design erasure codes that minimize the cross-rack repair bandwidth during failure repair. In this paper, we analyze the optimal trade-off between storage redundancy and cross-rack repair bandwidth specifically for data centers, subject to the condition that the original data can be reconstructed from a sufficient number of any non-failed nodes. We characterize the optimal trade-off curve under functional repair, and propose a general family of erasure codes called rack-aware regenerating codes (RRC), which achieve the optimal trade-off. We further propose exact repair constructions of RRC that have minimum storage redundancy and minimum cross-rack repair bandwidth, respectively. We show that (i) the minimum storage redundancy constructions support a wide range of parameters and have cross-rack repair bandwidth that is strictly less than that of the classical minimum storage regenerating codes in most cases, and (ii) the minimum cross-rack repair bandwidth constructions support all the parameters and have less cross-rack repair bandwidth than that of the minimum bandwidth regenerating codes for almost all of the parameters.

cs.IT↗

arXiv2017

Optimal Repair Layering for Erasure-Coded Data Centers: From Theory to Practice

Repair performance in hierarchical data centers is often bottlenecked by cross-rack network transfer. Recent theoretical results show that the cross-rack repair traffic can be minimized through repair layering, whose idea is to partition a repair operation into inner-rack and cross-rack layers. However, how repair layering should be implemented and deployed in practice remains an open issue. In this paper, we address this issue by proposing a practical repair layering framework called DoubleR. We design two families of practical double regenerating codes (DRC), which not only minimize the cross-rack repair traffic, but also have several practical properties that improve state-of-the-art regenerating codes. We implement and deploy DoubleR atop Hadoop Distributed File System (HDFS), and show that DoubleR maintains the theoretical guarantees of DRC and improves the repair performance of regenerating codes in both node recovery and degraded read operations.

cs.DC↗

arXiv2016

Private and Truthful Aggregative Game for Large-Scale Spectrum Sharing

Thanks to the rapid development of information technology, the size of the wireless network becomes larger and larger, which makes spectrum resources more precious than ever before. To improve the efficiency of spectrum utilization, game theory has been applied to study the spectrum sharing in wireless networks for a long time. However, the scale of wireless network in existing studies is relatively small. In this paper, we introduce a novel game and model the spectrum sharing problem as an aggregative game for large-scale, heterogeneous, and dynamic networks. The massive usage of spectrum also leads to easier privacy divulgence of spectrum users' actions, which calls for privacy and truthfulness guarantees in wireless network. In a large decentralized scenario, each user has no priori about other users' decisions, which forms an incomplete information game. A "weak mediator", e.g., the base station or licensed spectrum regulator, is introduced and turns this game into a complete one, which is essential to reach a Nash equilibrium (NE). By utilizing past experience on the channel access, we propose an online learning algorithm to improve the utility of each user, achieving NE over time. Our learning algorithm also provides no regret guarantee to each user. Our mechanism admits an approximate ex-post NE. We also prove that it satisfies the joint differential privacy and is incentive-compatible. Efficiency of the approximate NE is evaluated, and the innovative scaling law results are disclosed. Finally, we provide simulation results to verify our analysis.

cs.GT↗

arXiv2016

Context-Aware Online Learning for Course Recommendation of MOOC Big Data

The Massive Open Online Course (MOOC) has expanded significantly in recent years. With the widespread of MOOC, the opportunity to study the fascinating courses for free has attracted numerous people of diverse educational backgrounds all over the world. In the big data era, a key research topic for MOOC is how to mine the needed courses in the massive course databases in cloud for each individual student accurately and rapidly as the number of courses is increasing fleetly. In this respect, the key challenge is how to realize personalized course recommendation as well as to reduce the computing and storage costs for the tremendous course data. In this paper, we propose a big data-supported, context-aware online learning-based course recommender system that could handle the dynamic and infinitely massive datasets, which recommends courses by using personalized context information and historical statistics. The context-awareness takes the personal preferences into consideration, making the recommendation suitable for people with different backgrounds. Besides, the algorithm achieves the sublinear regret performance, which means it can gradually recommend the mostly preferred and matched courses to students. In addition, our storage module is expanded to the distributed-connected storage nodes, where the devised algorithm can handle massive course storage problems from heterogeneous sources of course datasets. Comparing to existing algorithms, our proposed algorithms achieve the linear time complexity and space complexity. Experiment results verify the superiority of our algorithms when comparing with existing ones in the MOOC big data setting.

cs.LG↗

arXiv2013

Cooperative Regenerating Codes

One of the design objectives in distributed storage system is the minimization of the data traffic during the repair of failed storage nodes. By repairing multiple failures simultaneously and cooperatively, further reduction of repair traffic is made possible. A closed-form expression of the optimal tradeoff between the repair traffic and the amount of storage in each node for cooperative repair is given. We show that the points on the tradeoff curve can be achieved by linear cooperative regenerating codes, with an explicit bound on the required finite field size. The proof relies on a max-flow-min-cut-type theorem for submodular flow from combinatorial optimization. Two families of explicit constructions are given.

cs.IT↗

arXiv2013

Analysis and Construction of Functional Regenerating Codes with Uncoded Repair for Distributed Storage Systems

Modern distributed storage systems apply redundancy coding techniques to stored data. One form of redundancy is based on regenerating codes, which can minimize the repair bandwidth, i.e., the amount of data transferred when repairing a failed storage node. Existing regenerating codes mainly require surviving storage nodes encode data during repair. In this paper, we study functional minimum storage regenerating (FMSR) codes, which enable uncoded repair without the encoding requirement in surviving nodes, while preserving the minimum repair bandwidth guarantees and also minimizing disk reads. Under double-fault tolerance settings, we formally prove the existence of FMSR codes, and provide a deterministic FMSR code construction that can significantly speed up the repair process. We further implement and evaluate our deterministic FMSR codes to show the benefits. Our work is built atop a practical cloud storage system that implements FMSR codes, and we provide theoretical validation to justify the practicality of FMSR codes.

cs.IT↗