Related papers: AIF: Asynchronous Inference Framework for Cost-Eff…

The linear-chain Conditional Random Field (CRF) model is one of the most widely-used neural sequence labeling approaches. Exact probabilistic inference algorithms such as the forward-backward and Viterbi algorithms are typically applied in…

We propose a cooperative training framework for deep neural network architectures that enables the runtime network depths to change to satisfy dynamic computing resource requirements. In our framework, the number of layers participating in…

Modeling feature interactions plays a crucial role in accurately predicting click-through rates (CTR) in advertising systems. To capture the intricate patterns of interaction, many existing models employ matrix-factorization techniques to…

Neural architecture search has been shown to hold great promise towards the automation of deep learning. However in spite of its potential, neural architecture search remains quite costly. To this point, we propose a novel gradient-based…

Though action recognition in videos has achieved great success recently, it remains a challenging task due to the massive computational cost. Designing lightweight networks is a possible solution, but it may degrade the recognition…

Modern software systems are usually highly configurable, providing users with customized functionality through various configuration options. Understanding how system performance varies with different option combinations is important to…

Modern industrial recommendation systems improve recommendation performance by integrating multimodal representations from pre-trained models into ID-based Click-Through Rate (CTR) prediction frameworks. However, existing approaches…

As industrial recommender systems enter a scaling-driven regime, Transformer architectures have become increasingly attractive for scaling models towards larger capacity and longer sequence. However, existing Transformer-based…

Deep neural network models owe their representational power to the high number of learnable parameters. It is often infeasible to run these largely parametrized deep models in limited resource environments, like mobile phones. Network…

Many techniques have been developed, such as model compression, to make Deep Neural Networks (DNNs) inference more efficiently. Nevertheless, DNNs still lack excellent run-time dynamic inference capability to enable users trade-off accuracy…

In daily fantasy sports (DFS), match participation is highly time-sensitive. Users must act within a narrow window before a game begins, making match recommendation a time-critical task to prevent missed engagement and revenue loss.…

Accurate Quality of Service (QoS) prediction is fundamental to service computing, providing essential data-driven guidance for service selection and ensuring superior user experiences. However, prevalent approaches, particularly Graph…

Approximate nearest neighbor (ANN) search is a fundamental problem in areas such as data management,information retrieval and machine learning. Recently, Li et al. proposed a learned approach named AdaptNN to support adaptive ANN query…

The expansion of Artificial Intelligence-generated content service requires diffusion model serving to simultaneously achieve high throughput and low task end-to-end (E2E) latency. However, existing continuous batching methods suffer from…

We propose a novel interactive learning framework which we refer to as Interactive Attention Learning (IAL), in which the human supervisors interactively manipulate the allocated attentions, to correct the model's behavior by updating the…

Federated Learning (FL) on resource-constrained edge devices faces a critical challenge: The computational energy required for training Deep Neural Networks (DNNs) often dominates communication costs. However, most existing…

In most real-world large-scale online applications (e.g., e-commerce or finance), customer acquisition is usually a multi-step conversion process of audiences. For example, an impression->click->purchase process is usually performed of…

Many tool-based Retrieval Augmented Generation (RAG) systems lack precise mechanisms for tracing final responses back to specific tool components -- a critical gap as systems scale to complex multi-agent architectures. We present…

Recently, the artificial intelligence of things (AIoT) has been gaining increasing attention, with an intriguing vision of providing highly intelligent services through the network connection of things, leading to an advanced AI-driven…

Active feature acquisition (AFA) is an instance-adaptive paradigm in which, at inference time, a policy sequentially chooses which features to acquire (at a cost) before predicting. Existing approaches either train reinforcement learning…