Neighborhood-based recommenders are a major class of Collaborative Filtering (CF) models. The intuition is to exploit neighbors with similar preferences for bridging unseen user-item pairs and alleviating data sparseness. Many existing works propose neural attention networks to aggregate neighbors and place higher weights on specific subsets of users for recommendation. However, the neighborhood information is not necessarily always informative, and the noises in the neighborhood can negatively affect the model performance. To address this issue, we propose a novel neighborhood-based recommender, where a hybrid gated network is designed to automatically separate similar neighbors from dissimilar (noisy) ones, and aggregate those similar neighbors to comprise neighborhood representations. The confidence in the neighborhood is also addressed by putting higher weights on the neighborhood representations if we are confident with the neighborhood information, and vice versa. In addition, a user-neighbor component is proposed to explicitly regularize user-neighbor proximity in the latent space. These two components are combined into a unified model to complement each other for the recommendation task. Extensive experiments on three publicly available datasets show that the proposed model consistently outperforms state-of-the-art neighborhood-based recommenders. We also study different variants of the proposed model to justify the underlying intuition of the proposed hybrid gated network and user-neighbor modeling components.

Link prediction based on knowledge graph embedding (KGE) aims to predict new triples to complete knowledge graphs (KGs) automatically. However, recent KGE models tend to improve performance by excessively increasing vector dimensions, which would cause enormous training costs and save storage in practical applications. To address this problem, we first theoretically analyze the capacity of low-dimensional space for KG embeddings based on the principle of minimum entropy. Then, we propose a novel knowledge distillation framework for knowledge graph embedding, utilizing multiple low-dimensional KGE models as teachers. Under a novel iterative distillation strategy, the MulDE model produces soft labels according to training epochs and student performance adaptively. The experimental results show that MulDE can effectively improve the performance and training speed of low-dimensional KGE models. The distilled 32-dimensional models are very competitive compared to some of state-or-the-art (SotA) high-dimensional methods on several commonly-used datasets.

It is thought-provoking to read the pair of articles on 10 challenges in data science by Xuming He and Xihong Lin from a statistics perspective and Jeannette Wing from a computer science perspective. Unsurprisingly, there is a good overlap of important topics including multimodal and heterogenous data, data privacy, fairness and interpretability, and causal inference or reasoning. This overlap reflects and confirms the foundational and shared roles of statistics and computer science in data science, which is the merging of statistical and computing thinking in the context of solving domain problems. The challenges in both articles are presented as separate, not integrated, topics, and mostly decoupled from domain problems, possibly because of the mandate of "10 challenges." In my mind, the most exciting 10 challenges in data science are to solve 10 pressing real-world data problems with positive impacts. For example, how is data science going to help control covid-19 spread while allowing a healthy economy?

A main challenge for tasks on panorama lies in the distortion of objects among images. In this work, we propose a Distortion-Aware Monocular Omnidirectional (DAMO) dense depth estimation network to address this challenge on indoor panoramas with two steps. First, we introduce a distortion-aware module to extract calibrated semantic features from omnidirectional images. Specifically, we exploit deformable convolution to adjust its sampling grids to geometric variations of distorted objects on panoramas and then utilize a strip pooling module to sample against horizontal distortion introduced by inverse gnomonic projection. Second, we further introduce a plug-and-play spherical-aware weight matrix for our objective function to handle the uneven distribution of areas projected from a sphere. Experiments on the 360D dataset show that the proposed method can effectively extract semantic features from distorted panoramas and alleviate the supervision bias caused by distortion. It achieves state-of-the-art performance on the 360D dataset with high efficiency.

Model-free reinforcement learning (RL) has been an active area of research and provides a fundamental framework for agent-based learning and decision-making in artificial intelligence. In this paper, we review a specific subset of this literature, namely work that utilizes optimization criteria based on average rewards, in the infinite horizon setting. Average reward RL has the advantage of being the most selective criterion in recurrent (ergodic) Markov decision processes. In comparison to widely-used discounted reward criterion, it also requires no discount factor, which is a critical hyperparameter, and properly aligns the optimization and performance metrics. Motivated by the solo survey by Mahadevan (1996a), we provide an updated review of work in this area and extend it to cover policy-iteration and function approximation methods (in addition to the value-iteration and tabular counterparts). We also identify and discuss opportunities for future work.

While AI is poised to disrupt our work and lives, these technologies can be harnessed through wise regulation. So rather than replacing individuals, much AI should assist them in completing tasks that are more fulfilling, or by augmenting work that is often classified as professional. "Artificial intelligence (AI) has a proper substitutive role – it can ensure that difficult, dirty and dangerous work is done more and more by machines and less and less by human beings," says Professor Frank Pasquale from Brooklyn Law School."But Should people be taking more courses like computer science or technical fields that will help them understand AI better? "Yes, but I don't think they should replace existing courses.

Unsupervised disentangled representation learning from the unlabelled audio data, and high fidelity audio generation have become two linchpins in the machine learning research fields. However, the representation learned from an unsupervised setting does not guarantee its' usability for any downstream task at hand, which can be a wastage of the resources, if the training was conducted for that particular posterior job. Also, during the representation learning, if the model is highly biased towards the downstream task, it losses its generalisation capability which directly benefits the downstream job but the ability to scale it to other related task is lost. Therefore, to fill this gap, we propose a new autoencoder based model named "Guided Adversarial Autoencoder (GAAE)", which can learn both post-task-specific representations and the general representation capturing the factors of variation in the training data leveraging a small percentage of labelled samples; thus, makes it suitable for future related tasks. Furthermore, our proposed model can generate audio with superior quality, which is indistinguishable from the real audio samples. Hence, with the extensive experimental results, we have demonstrated that by harnessing the power of the high-fidelity audio generation, the proposed GAAE model can learn powerful representation from unlabelled dataset leveraging a fewer percentage of labelled data as supervision/guidance.

Disentanglement is a highly desirable property of representation due to its similarity with human's understanding and reasoning. This improves interpretability, enables the performance of down-stream tasks, and enables controllable generative models. However, this domain is challenged by the abstract notion and incomplete theories to support unsupervised disentanglement learning. We demonstrate the data itself, such as the orientation of images, plays a crucial role in disentanglement and instead of the factors, and the disentangled representations align the latent variables with the action sequences. We further introduce the concept of disentangling action sequences which facilitates the description of the behaviours of the existing disentangling approaches. An analogy for this process is to discover the commonality between the things and categorizing them. Furthermore, we analyze the inductive biases on the data and find that the latent information thresholds are correlated with the significance of the actions. For the supervised and unsupervised settings, we respectively introduce two methods to measure the thresholds. We further propose a novel framework, fractional variational autoencoder (FVAE), to disentangle the action sequences with different significance step-by-step. Experimental results on dSprites and 3D Chairs show that FVAE improves the stability of disentanglement.

Noname manuscript No. (will be inserted by the editor) Abstract Video Question Answering (Video QA) challenges show consistent improvements over state-of-the-art methods modelers in multiple fronts. Modeling video necessitates on well-studied benchmarks including large-scale real-world building not only spatiotemporal models for the dynamic datasets such as TGIF-QA and TVQA, demonstrating the visual channel but also multimodal structures for associated strong capabilities of our CRN unit and the HCRN for complex information channels such as subtitles or audio. To the best of our knowledge, adds at least two more layers of complexity - selecting relevant the HCRN is the very first method attempting to handle content for each channel in the context of the linguistic long and short-form multimodal Video QA at the same time. To address these modules · Hierarchy requirements, we start with two insights: (a) content selection and relation construction can be jointly encapsulated into a conditional computational structure, and (b) video-length 1 Introduction structures can be composed hierarchically. For (a) this paper introduces a general-reusable reusable neural unit dubbed Answering natural questions about a video is a powerful Conditional Relation Network (CRN) taking as input a set of demonstration of cognitive capability. The task involves acquisition tensorial objects and translating into a new set of objects that and manipulation of spatiotemporal visual, acoustic encode relations of the inputs. The generic design of CRN and linguistic representations from the video guided by helps ease the common complex model building process the compositional semantics of linguistic cues [1, 2, 3, 4, 5, of Video QA by simple block stacking and rearrangements 6]. As questions are potentially unconstrained, Video QA with flexibility in accommodating diverse input modalities requires deep modeling capacity to encode and represent crucial and conditioning features across both visual and linguistic multimodal video properties such as linguistic content, domains. As a result, we realize insight (b) by introducing object permanence, motion profiles, prolonged actions, and Hierarchical Conditional Relation Networks (HCRN) for varying-length temporal relations in a hierarchical manner. The HCRN primarily aims at exploiting intrinsic For Video QA, the visual and textual representations should properties of the visual content of a video as well as its accompanying ideally be question-specific and answer-ready.

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.