A critical challenge in contemporary recommendation systems lies in effectively leveraging multimodal content to enhance recommendation personalization. Although various solutions have been proposed, most fail to account for discrepancies between knowledge extracted through isolated feature extraction and its application in recommendation tasks. Specifically, multimodal feature extraction does not incorporate task-specific prior knowledge, while downstream recommendation tasks typically use these features as auxiliary information. This misalignment often introduces biases in model fitting and degrades performance, a phenomenon we refer to as the curse of knowledge. To address this challenge, we propose a knowledge soft integration framework designed to balance the utilization of multimodal features with the biases they may introduce. The framework, namedKnowledgeSoftIntegration (KSI), comprises two key components: the Structure Efficient Injection (SEI) module and the Semantic Soft Integration (SSI) module. The SEI module employs a Refined Graph Neural Network (RGNN) to model inter-modal correlations among items while introducing a regularization term to minimize redundancy in user and item representations. In parallel, the SSI module utilizes a self-supervised retrieval task to implicitly integrate multimodal semantic knowledge, thereby enhancing the semantic distinctiveness of item representations. We conduct comprehensive experiments on three benchmark datasets, demonstrating KSI's effectiveness. Furthermore, these results underscore the ability of the SEI and SSI modules to reduce representation redundancy and mitigate the curse of knowledge in multimodal recommendation systems.

Noise is a pervasive issue in recommendation systems, which can stem from user behaviors that do not align with their intentions. As a result, noise reduction has become a prominent area of research in the field of recommendation systems. However, existing noise reduction techniques in recommendation tend to compromise the performance of certain task objectives. Moreover, they require modifying the structure of the model, which introduces inference latency and additional space cost. In this paper, we propose a straightforward yet powerful approach, Multi-layer Tensor trace Norm (MTN), to address noise-related challenges. Our method achieves this by promoting information sharing across different tasks using tensor trace norms. By leveraging norms, MTN effectively reduces noise without modifying the model’s structure or incurring substantial time and space complexities. Extensive experiments on public datasets and generated noisy datasets demonstrate the effectiveness of MTN on several of the most popular multi-task models.

Data augmentation with Mixup has been proven an effective method to regularize the current deep neural networks. Mixup generates virtual samples and corresponding labels simultaneously by linear interpolation. However, the one-stage generation paradigm and the use of linear interpolation have two defects: (1) The label of the generated sample is simply combined from the labels of the original sample pairs without reasonable judgment, resulting in ambiguous labels. (2) Linear combination significantly restricts the sampling space for generating samples. To address these issues, we propose a novel and effective augmentation method, Global Mixup, based on global clustering relationships. Specifically, we transform the previous one-stage augmentation process into two-stage by decoupling the process of generating virtual samples from the labeling. And for the labels of the generated samples, relabeling is performed based on clustering by calculating the global relationships of the generated samples. Furthermore, we are no longer restricted to linear relationships, which allows us to generate more reliable virtual samples in a larger sampling space. Extensive experiments for CNN, LSTM, and BERT on five tasks show that Global Mixup outperforms previous baselines. Further experiments also demonstrate the advantage of Global Mixup in low-resource scenarios.

Session-based Recommendation (SBR) aims to predict the next item for a session, which consists of several clicked items in a transaction. Most SBR approaches follow an underlying assumption that all sequential information should be strictly utilized. Thus, they model temporal information for items using implicit, explicit, or ensemble methods. In fact, users may recall previously clicked items but might not remember the exact order in which they were clicked. Therefore, focusing on representing item temporal information in various ways could make learning session intents challenging. In this paper, we rethink the necessity of temporal information for items in SBR. We propose Aggregating the Contextual intents of the session with Attentive networks, namely ACARec. Specifically, we avoid explicitly modeling positional embeddings and learn contextual intents through aggregation methods (convolutions or poolings). We also demonstrate that even an entirely position-agnostic aggregation approach can yield promising results. Extensive experiments on real-world datasets validate our arguments. We hope our study can provide insights into SBR and inspire future research in the community.

Search result diversification aims to balance the relevance and diversity of retrieved documents to satisfy the different information needs of users. Three types of approaches have proliferated: explicit models that are based on explicit features (e.g., subtopic coverage), implicit models that are based on implicit features (e.g., the novelty of documents), and ensemble models that utilize both implicit and explicit features. However, the subtopics used by most explicit and ensemble models are usu-ally mined from queries (e.g., using Google Search Suggestions), which may not match the subtopics covered by the candidate documents. Besides, the implicit features used by most implicit models are formulated as either the similarity of documents or the intent of documents. The former cannot directly reflect the relationships of documents at the subtopic level, while the latter cannot capture non-pairwise relationships among documents. To tackle these issues, we propose a novel model that dynamically mines subtopics from the candidate documents and leverages thehypergraph structure to model the diversity of candidate documents, named HGDIV. Specifically, we dynamically mine subtopics from the candidate documents, rather than mining subtopics from queries or using static subtopics as existing methods do. More importantly, we introduce the hypergraph structure to model the diversity of candidate documents for search result diversification, which can capture the non-pairwise relationships among documents. Furthermore, we innovatively model the global and local subtopic distributions to extract the diversity of candidate documents. Experimental results on the public diversity benchmark TREC datasets demonstrate the superiority of our model over state-of-the-art models.

Mixed-precision quantization (MPQ) suffers from the time-consuming process of searching the optimal bit-width allocation (i.e., the policy) for each layer, especially when using large-scale datasets such as ISLVRC-2012. This limits the practicality of MPQ in real-world deployment scenarios. To address this issue, this paper proposes a novel method for efficiently searching for effective MPQ policies using a small proxy dataset instead of the large-scale dataset used for training the model. Deviating from the established norm of employing a consistent dataset for both model training and MPQ policy search stages, our approach, therefore, yields a substantial enhancement in the efficiency of MPQ exploration. Nonetheless, using discrepant datasets poses challenges in searching for a transferable MPQ policy. Driven by the observation that quantization noise of sub-optimal policy exerts a detrimental influence on the discriminability of feature representations---manifesting as diminished class margins and ambiguous decision boundaries---our method aims to identify policies that uphold the discriminative nature of feature representations, i.e., intra-class compactness and inter-class separation. This general and dataset-independent property makes us search for the MPQ policy over a rather small-scale proxy dataset and then the policy can be directly used to quantize the model trained on a large-scale dataset. Our method offers several advantages, including high proxy data utilization, no excessive hyper-parameter tuning, and high searching efficiency. We search high-quality MPQ policies with the proxy dataset that has only 4% of the data scale compared to the large-scale target dataset, achieving the same accuracy as searching directly on the latter, improving MPQ searching efficiency by up to 300×.

Pre-trained language models (PLMs) with external knowledge have demonstrated their remarkable performance on a variety of downstream natural language processing tasks.The typical methods of integrating knowledge into PLMs are designing different pre-training tasks and training from scratch, which requires high-end hardware, massive storage resources, and computing time.Prompt learning is an effective approach to tune PLMs for specific tasks, and it can also be used to infuse knowledge.However, most prompt learning methods accept one token as the answer instead of multiple tokens.To tackle this problem, we propose the long-answer prompt learning method (KLAPrompt) to incorporate semantic knowledge in Xinhua Dictionary into pre-trained language models.The proposed method splits the whole answer space into several answer subspaces according to the token's position in the long answer.Extensive experimental results on five datasets demonstrate the effectiveness of our approach.

Session-based Recommendation (SR) aims to predict users' next click based on their behavior within a short period, which is crucial for online platforms. However, most existing SR methods somewhat ignore the fact that user preference is not necessarily strongly related to the order of interactions. Moreover, they ignore the differences in importance between different samples, which limits the model-fitting performance. To tackle these issues, we put forward the method, Mining Interest Trends and Adaptively Assigning Sample Weight, abbreviated as MTAW. Specifically, we model users' instant interest based on their present behavior and all their previous behaviors. Meanwhile, we discriminatively integrate instant interests to capture the changing trend of user interest to make more personalized recommendations. Furthermore, we devise a novel loss function that dynamically weights the samples according to their prediction difficulty in the current epoch. Extensive experimental results on two benchmark datasets demonstrate the effectiveness and superiority of our method.

Session-based Recommendation (SBR) aims to predict the next item for the current session, which consists of several clicked items in a short period by an anonymous user. Most of the sequential modeling approaches to SBR are focusing on adopting advanced Deep Neural Networks (DNNs), and these methods require increasingly longer training times. Existing studies have shown that some traditional SBR methods can outperform some DNN-based sequential models, however, few studies have attempted to investigate the effectiveness of traditional methods in recent years. In this paper, we propose a novel and concise SBR model inspired by the basic concept of autocorrelation in the Stochastic Process. Autocorrelation measures the correlation of a process at different moments. Therefore, it is natural to use it to model the correlation of clicked item sequences at different time shifts. Specifically, we use Fast Fourier Transforms (FFT) to compute the autocorrelation and combine it with several linear transformations to enhance the session representation. By this means, our proposed method can learn better session preferences and is more efficient than most DNN-based models. Extensive experiments on two public datasets show that the proposed method outperforms state-of-the-art models in both effectiveness and efficiency.

For task-oriented dialogue systems, Natural Language Generation (NLG) is the last and vital step which aims at generating an appropriate response according to the dialogue act (DA). While end-to-end neural networks have achieved promising performances on this task, the existing models still struggle to avoid slot mistakes. To address this challenge, we propose a novel segmented generation approach in this paper. The proposed method operates by progressively generating text for the span between two adjacent keywords (act type and slots) in semantically ordered DA. This procedure is recursively applied from left to right until a response is completed. Besides, a retrieval mechanism is utilized to better match the diversity and fluency in human language. Experimental results on four datasets demonstrate that our model achieves state-of-the-art slot error rate and also gets competitive performance on BLEU score with all strong baselines.

The task of Session-based Social Recommendation (SSR) aims to utilize the social networks to make recommendations in session-based scenarios. Existing SSR methods mainly focused on using graph networks to capture complex item transition patterns, ignoring the sequential information. Few studies combined two aspects of features to enhance session preferences, resulting in information loss. Besides, modeling the entire session that some items are invalid or repeatedly clicked will interfere with the results. In this paper, to address the information loss issue in SSR, we propose a novel Dual-Channel Attentive Network (DCAN) to leverage both sequential infor-mation and complex item transitions. Specifically, we construct one channel by a light graph attention layer to capture item transitions, and we elaborate a concise attention-based layer to build the other channel to learn sequential information. To solve the invalid or repeatedly clicked problem in the session, we introduce new self-supervised learning (SSL) learning method, which allows model learning to distinguish and discard these items. However, the effect of SSL in SSR has not been investigated yet. Besides, these studies require negative sampling, which makes its performance depend on negative sampling strategies. Then, we investigate the effect of adding existing SSL frameworks in DCAN, but it has not achieved good results. Besides, we propose a novel SSL framework that does not require negative sampling for SSR, denoted as Positive sampling SSL (PSSL). Furthermore, we combined DCAN and PSSL to make more accurate recommendations, denoted as DCAN - PSSL. Extensive experiments on three public benchmark datasets demonstrate that both DCAN and DCAN - PSSL consistently outperform the state-of-the-art models.

Graph neural networks have been widely used in recent recommender systems, where negative sampling plays an important role. Existing negative sampling methods restrict the relationship between nodes as either hard positive pairs or hard negative pairs. This leads to the loss of structural information, and lacks the mechanism to generate positive pairs for nodes with few neighbors. To overcome limitations, we propose a novel soft link-based sampling method, namely MixDec Sampling, which consists of Mixup Sampling module and Decay Sampling module. The Mixup Sampling augments node features by synthesizing new nodes and soft links, which provides sufficient number of samples for nodes with few neighbors. The Decay Sampling strengthens the digestion of graph structure information by generating soft links for node embedding learning. To the best of our knowledge, we are the first to model sampling relationships between nodes by soft links in GNN-based recommender systems. Extensive experiments demonstrate that the proposed MixDec Sampling can significantly and consistently improve the recommendation performance of several representative GNN-based models on various recommendation benchmarks.

Conventional model quantization methods use a fixed quantization scheme to different data samples, which ignores the inherent"recognition difficulty" differences between various samples. We propose to feed different data samples with varying quantization schemes to achieve a data-dependent dynamic inference, at a fine-grained layer level. However, enabling this adaptive inference with changeable layer-wise quantization schemes is challenging because the combination of bit-widths and layers is growing exponentially, making it extremely difficult to train a single model in such a vast searching space and use it in practice. To solve this problem, we present the Arbitrary Bit-width Network (ABN), where the bit-widths of a single deep network can change at runtime for different data samples, with a layer-wise granularity. Specifically, first we build a weight-shared layer-wise quantizable "super-network" in which each layer can be allocated with multiple bit-widths and thus quantized differently on demand. The super-network provides a considerably large number of combinations of bit-widths and layers, each of which can be used during inference without retraining or storing myriad models. Second, based on the well-trained super-network, each layer's runtime bit-width selection decision is modeled as a Markov Decision Process (MDP) and solved by an adaptive inference strategy accordingly. Experiments show that the super-network can be built without accuracy degradation, and the bit-widths allocation of each layer can be adjusted to deal with various inputs on the fly. On ImageNet classification, we achieve 1.1% top1 accuracy improvement while saving 36.2% BitOps.

Abstract—In recent years, erasure coding has been adopted by large-scale cloud storage systems to replace data replication. With the increase of disk I/O throughput and network bandwidth, the speed of erasure coding becomes one of the key system bot-tlenecks. In this paper, we propose to offload the task of erasure coding to Graphics Processing Units (GPUs). Specifically, we have designed and implemented PErasure, a parallel Cauchy Reed-Solomon (CRS) coding library. We compare the performance of PErasure with that of two state-of-the-art libraries: Jerasure (for CPUs) and Gibraltar (for GPUs). Our experiments show that the raw coding speed of PErasure on a $500 Nvidia GTX780 card is about 10 times faster than that of multithreaded Jerasure on a quad-core modern CPU, and 2-4 times faster than Gibraltar on the same GPU. PErasure can achieve up to 10GB/s of overall encoding speed using just a single GPU for a large storage system that can withstand up to 8 disk failures. I.

The low-level disk characteristics play a vital role for the I/O performance optimization in disk storage systems. This paper presents FAXtrac, a tool for automatically and efficiently extracting the exact disk layout, i.e., the number of sectors of each disk track. FAXtrac includes three algorithms, namely SptExplore, TrackExplore, and RemoveNoise, to ensure the correctness and speediness of the extraction of disk layout. We tested FAXtrac on a number of different disk models. It took only 75 minutes to extract the detailed disk layout for a 250 GB SATA disk, which shortened the time by two orders of magnitude as compared with an existing solution. We believe that FAXtrac is a valuable tool for the hard disk storage research community.

Current peer-to-peer (P2P) swarming systems have been immensely successful for large scale media content distribution with fewer server resources and lower protocol overhead. In order to improve media delivery quality and provide high service availability, network coding techniques have been proposed to help resource propagating through P2P network. Applying network coding over small time-window of video reduces the risks of uploading duplicate content and minimizes the variance in the performance of each node, thus, improving the overall efficiency of the system. However, by combining network coding in video delivery, the bitrates of media stream is usually nonscalable. Since the channel bandwidth between peers may fluctuate in a wide range in P2P swarming system, nonscalable network coding video stream cannot adapt P2P communication channel effectively. In this work, we propose a novel network coding scheme to address the issues. Considering that MPEG-4 video sequences can be presented by multiple layers of bitstreams, including baselayer and enhanced layer, network coding can be applied on base layer for availability, and enhanced layers can be truncated to adapt channel bandwidth. Compared with existing network coding approaches, our simulation experimental results clearly show that the proposed scheme brings higher efficiency and more flexibility to video streaming over P2P swarming system.

Abstract The access control model is a core aspect of trusted information systems. Based on the role based access control (RBAC) model, we put forward the concept of thehomonymous role, which extends the role control categories in RBAC, balances the control granularity and the storage space requirements, and executes the fine‐grained access control. Instead of the traditional global access control policies (GACP), we propose thehomonymous control domain(HCD) mechanism to enable the coexistence of multiple types of access control policies in a single system, thereby improving the control granularity and flexibility. The HCD mechanism facilitates the discretionary supporting of independent access control policies for its homonymous user. The HCD mechanism and the traditional access control mechanism can be linked to construct a two‐layer access control policy mechanism for a system. Notably, we also consider the temporal characteristic in HCD, which is a critical feature of modern access control models. Furthermore, we analyze the conflicts between the HCD and GACP mechanisms. Finally, we design and implement our HCD on FreeBSD to demonstrate the advantages of the two‐layer access control mechanism. Copyright © 2008 John Wiley & Sons, Ltd.

Many emerging applications show the need for a fine-grained context based access control requirements. The generalized temporal RBAC model has been proposed to capture fine-grained time-based access control requirements using periodic time expression to capture recurring intervals of time. In this paper, we present conditional temporal RBAC (CT-RBAC) model that extends GTRBAC model by extending the periodic time expression. In particular, the extension allows fine-grained extension to capture other logical conditions that restricts the validity of the temporal constraints. CT-RBAC uses a symbolic representation of conditional periodic time that can be used to define a set of conditions to qualify the components of a periodic time expression, using the concurrent transaction logic. Because of the conditional set introduced, CT-RBAC extends the time control dimension to the (condition, time) control plane and the (time, constraint) plane of the GTRBAC framework to the (condition, time, constraint) three-dimensional control space, thus providing more flexibility in the access control model. We analyze conflicts introduced by the constraint set and the complexity of evaluating the conditional set.