In recommender systems, reinforcement learning solutions have effectively boosted recommendation performance because of their ability to capture long-term user-system interaction. However, the action space of the recommendation policy is a list of items, which could be extremely large with a dynamic candidate item pool. To overcome this challenge, we propose a hyper-actor and critic learning framework where the policy decomposes the item list generation process into a hyper-action inference step and an effect-action selection step. The first step maps the given state space into a vectorized hyper-action space, and the second step selects the item list based on the hyper-action. In order to regulate the discrepancy between the two action spaces, we design an alignment module along with a kernel mapping function for items to ensure inference accuracy and include a supervision module to stabilize the learning process. We build simulated environments on public datasets and empirically show that our framework is superior in recommendation compared to standard RL baselines.
Multi-task learning (MTL) aims at learning related tasks in a unified model to achieve mutual improvement among tasks considering their shared knowledge. It is an important topic in recommendation due to the demand for multi-task prediction considering performance and efficiency. Although MTL has been well studied and developed, there is still a lack of systematic review in the recommendation community. To fill the gap, we provide a comprehensive review of existing multi-task deep recommender systems (MTDRS) in this survey. To be specific, the problem definition of MTDRS is first given, and it is compared with other related areas. Next, the development of MTDRS is depicted and the taxonomy is introduced from the task relation and methodology aspects. Specifically, the task relation is categorized into parallel, cascaded, and auxiliary with main, while the methodology is grouped into parameter sharing, optimization, and training mechanism. The survey concludes by summarizing the application and public datasets of MTDRS and highlighting the challenges and future directions of the field.
To facilitate research on text generation, this paper presents a comprehensive and unified library, TextBox 2.0, focusing on the use of pre-trained language models (PLMs). To be comprehensive, our library covers $13$ common text generation tasks and their corresponding $83$ datasets and further incorporates $45$ PLMs covering general, translation, Chinese, dialogue, controllable, distilled, prompting, and lightweight PLMs. We also implement $4$ efficient training strategies and provide $4$ generation objectives for pre-training new PLMs from scratch. To be unified, we design the interfaces to support the entire research pipeline (from data loading to training and evaluation), ensuring that each step can be fulfilled in a unified way. Despite the rich functionality, it is easy to use our library, either through the friendly Python API or command line. To validate the effectiveness of our library, we conduct extensive experiments and exemplify four types of research scenarios. The project is released at the link: https://github.com/RUCAIBox/TextBox.
The radiation dose in computed tomography (CT) examinations is harmful for patients but can be significantly reduced by intuitively decreasing the number of projection views. Reducing projection views usually leads to severe aliasing artifacts in reconstructed images. Previous deep learning (DL) techniques with sparse-view data require sparse-view/full-view CT image pairs to train the network with supervised manners. When the number of projection view changes, the DL network should be retrained with updated sparse-view/full-view CT image pairs. To relieve this limitation, we present a fully unsupervised score-based generative model in sinogram domain for sparse-view CT reconstruction. Specifically, we first train a score-based generative model on full-view sinogram data and use multi-channel strategy to form highdimensional tensor as the network input to capture their prior distribution. Then, at the inference stage, the stochastic differential equation (SDE) solver and data-consistency step were performed iteratively to achieve fullview projection. Filtered back-projection (FBP) algorithm was used to achieve the final image reconstruction. Qualitative and quantitative studies were implemented to evaluate the presented method with several CT data. Experimental results demonstrated that our method achieved comparable or better performance than the supervised learning counterparts.
In recent years, some researchers focused on using a single image to obtain a large number of samples through multi-scale features. This study intends to a brand-new idea that requires only ten or even fewer samples to construct the low-rank structural-Hankel matrices-assisted score-based generative model (SHGM) for color image inpainting task. During the prior learning process, a certain amount of internal-middle patches are firstly extracted from several images and then the structural-Hankel matrices are constructed from these patches. To better apply the score-based generative model to learn the internal statistical distribution within patches, the large-scale Hankel matrices are finally folded into the higher dimensional tensors for prior learning. During the iterative inpainting process, SHGM views the inpainting problem as a conditional generation procedure in low-rank environment. As a result, the intermediate restored image is acquired by alternatively performing the stochastic differential equation solver, alternating direction method of multipliers, and data consistency steps. Experimental results demonstrated the remarkable performance and diversity of SHGM.
Automated radiology report generation aims at automatically generating a detailed description of medical images, which can greatly alleviate the workload of radiologists and provide better medical services to remote areas. Most existing works pay attention to the holistic impression of medical images, failing to utilize important anatomy information. However, in actual clinical practice, radiologists usually locate important anatomical structures, and then look for signs of abnormalities in certain structures and reason the underlying disease. In this paper, we propose a novel framework AGFNet to dynamically fuse the global and anatomy region feature to generate multi-grained radiology report. Firstly, we extract important anatomy region features and global features of input Chest X-ray (CXR). Then, with the region features and the global features as input, our proposed self-adaptive fusion gate module could dynamically fuse multi-granularity information. Finally, the captioning generator generates the radiology reports through multi-granularity features. Experiment results illustrate that our model achieved the state-of-the-art performance on two benchmark datasets including the IU X-Ray and MIMIC-CXR. Further analyses also prove that our model is able to leverage the multi-grained information from radiology images and texts so as to help generate more accurate reports.
We show how factoring the RNN-T's output distribution can significantly reduce the computation cost and power consumption for on-device ASR inference with no loss in accuracy. With the rise in popularity of neural-transducer type models like the RNN-T for on-device ASR, optimizing RNN-T's runtime efficiency is of great interest. While previous work has primarily focused on the optimization of RNN-T's acoustic encoder and predictor, this paper focuses the attention on the joiner. We show that despite being only a small part of RNN-T, the joiner has a large impact on the overall model's runtime efficiency. We propose to factorize the joiner into blank and non-blank portions for the purpose of skipping the more expensive non-blank computation when the blank probability exceeds a certain threshold. Since the blank probability can be computed very efficiently and the RNN-T output is dominated by blanks, our proposed method leads to a 26-30% decoding speed-up and 43-53% reduction in on-device power consumption, all the while incurring no accuracy degradation and being relatively simple to implement.
In this paper we consider the contextual multi-armed bandit problem for linear payoffs under a risk-averse criterion. At each round, contexts are revealed for each arm, and the decision maker chooses one arm to pull and receives the corresponding reward. In particular, we consider mean-variance as the risk criterion, and the best arm is the one with the largest mean-variance reward. We apply the Thompson Sampling algorithm for the disjoint model, and provide a comprehensive regret analysis for a variant of the proposed algorithm. For $T$ rounds, $K$ actions, and $d$-dimensional feature vectors, we prove a regret bound of $O((1+\rho+\frac{1}{\rho}) d\ln T \ln \frac{K}{\delta}\sqrt{d K T^{1+2\epsilon} \ln \frac{K}{\delta} \frac{1}{\epsilon}})$ that holds with probability $1-\delta$ under the mean-variance criterion with risk tolerance $\rho$, for any $0<\epsilon<\frac{1}{2}$, $0<\delta<1$. The empirical performance of our proposed algorithms is demonstrated via a portfolio selection problem.
We study the identification and estimation of long-term treatment effects when both experimental and observational data are available. Since the long-term outcome is observed only after a long delay, it is not measured in the experimental data, but only recorded in the observational data. However, both types of data include observations of some short-term outcomes. In this paper, we uniquely tackle the challenge of persistent unmeasured confounders, i.e., some unmeasured confounders that can simultaneously affect the treatment, short-term outcomes and the long-term outcome, noting that they invalidate identification strategies in previous literature. To address this challenge, we exploit the sequential structure of multiple short-term outcomes, and develop three novel identification strategies for the average long-term treatment effect. We further propose three corresponding estimators and prove their asymptotic consistency and asymptotic normality. We finally apply our methods to estimate the effect of a job training program on long-term employment using semi-synthetic data. We numerically show that our proposals outperform existing methods that fail to handle persistent confounders.
Magnetic resonance imaging (MRI) is a widely used medical imaging modality. However, due to the limitations in hardware, scan time, and throughput, it is often clinically challenging to obtain high-quality MR images. In this article, we propose a method of using artificial intelligence to expand the channel to achieve the effect of increasing the virtual coil. The main feature of our work is utilizing dummy variable technology to expand the channel in both the image and k-space domains. The high-dimensional information formed by channel expansion is used as the prior information of parallel imaging to improve the reconstruction effect of parallel imaging. Two features are introduced, namely variable enhancement and sum of squares (SOS) objective function. Variable argumentation provides the network with more high-dimensional prior information, which is helpful for the network to extract the deep feature in-formation of the image. The SOS objective function is employed to solve the problem that k-space data is difficult to train while speeding up the convergence speed. Ablation studies and experimental results demonstrate that our method achieves significantly higher image reconstruction performance than current state-of-the-art techniques.