Imperative session types provide an imperative interface to session-typed communication. In such an interface, channel references are first-class objects with operations that change the typestate of the channel. Compared to functional session type APIs, the program structure is simpler at the surface, but typestate is required to model the current state of communication throughout. Following an early work that explored the imperative approach, a significant body of work on session types has neglected the imperative approach and opts for a functional approach that uses linear types to manage channel references soundly. We demonstrate that the functional approach subsumes the early work on imperative session types by exhibiting a typing and semantics preserving translation into a system of linear functional session types. We further show that the untyped backwards translation from the functional to the imperative calculus is semantics preserving. We restrict the type system of the functional calculus such that the backwards translation becomes type preserving. Thus, we precisely capture the difference in expressiveness of the two calculi and conclude that the lack of expressiveness in the imperative calculus is largely due to restrictions imposed by its type system.
相關內容
Neural language models encode rich knowledge about entities and their relationships which can be extracted from their representations using probing. Common properties of nouns (e.g., red strawberries, small ant) are, however, more challenging to extract compared to other types of knowledge because they are rarely explicitly stated in texts. We hypothesize this to mainly be the case for perceptual properties which are obvious to the participants in the communication. We propose to extract these properties from images and use them in an ensemble model, in order to complement the information that is extracted from language models. We consider perceptual properties to be more concrete than abstract properties (e.g., interesting, flawless). We propose to use the adjectives' concreteness score as a lever to calibrate the contribution of each source (text vs. images). We evaluate our ensemble model in a ranking task where the actual properties of a noun need to be ranked higher than other non-relevant properties. Our results show that the proposed combination of text and images greatly improves noun property prediction compared to powerful text-based language models.
Modern applications often manage time-varying data. Despite decades of research on temporal databases, which culminated in the addition of temporal data operations into the SQL:2011 standard, temporal data query and manipulation operations are unavailable in most mainstream database management systems, leaving developers with the unenviable task of implementing such functionality from scratch. In this paper, we extend \emph{language-integrated query} to support writing temporal queries and updates in a uniform host language, with the language performing the required rewriting to emulate temporal capabilities automatically on any standard relational database. We introduce two core languages, $\lambda_{\mathsf{TLINQ}}$ and $\lambda_{\mathsf{VLINQ}}$, for manipulating transaction time and valid time data respectively, and formalise existing implementation strategies by giving provably correct semantics-preserving translations into a non-temporal core language, $\lambda_{\mathsf{LINQ}}$. We show how existing work on query normalisation supports a surprisingly simple implementation strategy for \emph{sequenced joins}. We implement our approach in the Links programming language, and describe a non-trivial case study based on curating COVID-19 statistics.
Recent years have witnessed remarkable progress in artificial intelligence (AI) thanks to refined deep network structures, powerful computing devices, and large-scale labeled datasets. However, researchers have mainly invested in the optimization of models and computational devices, leading to the fact that good models and powerful computing devices are currently readily available, while datasets are still stuck at the initial stage of large-scale but low quality. Data becomes a major obstacle to AI development. Taking note of this, we dig deeper and find that there has been some but unstructured work on data optimization. They focus on various problems in datasets and attempt to improve dataset quality by optimizing its structure to facilitate AI development. In this paper, we present the first review of recent advances in this area. First, we summarize and analyze various problems that exist in large-scale computer vision datasets. We then define data optimization and classify data optimization algorithms into three directions according to the optimization form: data sampling, data subset selection, and active learning. Next, we organize these data optimization works according to data problems addressed, and provide a systematic and comparative description. Finally, we summarize the existing literature and propose some potential future research topics.
We consider inverse problems in Hilbert spaces under correlated Gaussian noise and use a Bayesian approach to find their regularised solution. We focus on mildly ill-posed inverse problems with the noise being generalised derivative of fractional Brownian motion, using a novel wavelet - based approach we call vaguelette-vaguelette. It allows us to apply sequence space methods without assuming that all operators are simultaneously diagonalisable. The results are proved for more general bases and covariance operators. Our primary aim is to study the posterior contraction rate in such inverse problems over Sobolev classes of true functions, comparing it to the derived minimax rate. Secondly, we study the effect of plugging in a consistent estimator of variances in sequence space on the posterior contraction rate, for instance where there are repeated observations. This result is also applied to the problem where the forward operator is observed with error. Thirdly, we show that an adaptive empirical Bayes posterior distribution contracts at the optimal rate, in the minimax sense, under a condition on prior smoothness, with a plugged in maximum marginal likelihood estimator of the prior scale. These theoretical results are illustrated on simulated data.
Open Source Software (OSS) is forming the spines of technology infrastructures, attracting millions of talents to contribute. Notably, it is challenging and critical to consider both the developers' interests and the semantic features of the project code to recommend appropriate development tasks to OSS developers. In this paper, we formulate the novel problem of code recommendation, whose purpose is to predict the future contribution behaviors of developers given their interaction history, the semantic features of source code, and the hierarchical file structures of projects. Considering the complex interactions among multiple parties within the system, we propose CODER, a novel graph-based code recommendation framework for open source software developers. CODER jointly models microscopic user-code interactions and macroscopic user-project interactions via a heterogeneous graph and further bridges the two levels of information through aggregation on file-structure graphs that reflect the project hierarchy. Moreover, due to the lack of reliable benchmarks, we construct three large-scale datasets to facilitate future research in this direction. Extensive experiments show that our CODER framework achieves superior performance under various experimental settings, including intra-project, cross-project, and cold-start recommendation. We will release all the datasets, code, and utilities for data retrieval upon the acceptance of this work.
Generative data-free quantization emerges as a practical compression approach that quantizes deep neural networks to low bit-width without accessing the real data. This approach generates data utilizing batch normalization (BN) statistics of the full-precision networks to quantize the networks. However, it always faces the serious challenges of accuracy degradation in practice. We first give a theoretical analysis that the diversity of synthetic samples is crucial for the data-free quantization, while in existing approaches, the synthetic data completely constrained by BN statistics experimentally exhibit severe homogenization at distribution and sample levels. This paper presents a generic Diverse Sample Generation (DSG) scheme for the generative data-free quantization, to mitigate detrimental homogenization. We first slack the statistics alignment for features in the BN layer to relax the distribution constraint. Then, we strengthen the loss impact of the specific BN layers for different samples and inhibit the correlation among samples in the generation process, to diversify samples from the statistical and spatial perspectives, respectively. Comprehensive experiments show that for large-scale image classification tasks, our DSG can consistently quantization performance on different neural architectures, especially under ultra-low bit-width. And data diversification caused by our DSG brings a general gain to various quantization-aware training and post-training quantization approaches, demonstrating its generality and effectiveness.
Human-in-the-loop aims to train an accurate prediction model with minimum cost by integrating human knowledge and experience. Humans can provide training data for machine learning applications and directly accomplish some tasks that are hard for computers in the pipeline with the help of machine-based approaches. In this paper, we survey existing works on human-in-the-loop from a data perspective and classify them into three categories with a progressive relationship: (1) the work of improving model performance from data processing, (2) the work of improving model performance through interventional model training, and (3) the design of the system independent human-in-the-loop. Using the above categorization, we summarize major approaches in the field, along with their technical strengths/ weaknesses, we have simple classification and discussion in natural language processing, computer vision, and others. Besides, we provide some open challenges and opportunities. This survey intends to provide a high-level summarization for human-in-the-loop and motivates interested readers to consider approaches for designing effective human-in-the-loop solutions.
Graph Neural Networks (GNNs) have been studied from the lens of expressive power and generalization. However, their optimization properties are less well understood. We take the first step towards analyzing GNN training by studying the gradient dynamics of GNNs. First, we analyze linearized GNNs and prove that despite the non-convexity of training, convergence to a global minimum at a linear rate is guaranteed under mild assumptions that we validate on real-world graphs. Second, we study what may affect the GNNs' training speed. Our results show that the training of GNNs is implicitly accelerated by skip connections, more depth, and/or a good label distribution. Empirical results confirm that our theoretical results for linearized GNNs align with the training behavior of nonlinear GNNs. Our results provide the first theoretical support for the success of GNNs with skip connections in terms of optimization, and suggest that deep GNNs with skip connections would be promising in practice.
This paper focuses on two fundamental tasks of graph analysis: community detection and node representation learning, which capture the global and local structures of graphs, respectively. In the current literature, these two tasks are usually independently studied while they are actually highly correlated. We propose a probabilistic generative model called vGraph to learn community membership and node representation collaboratively. Specifically, we assume that each node can be represented as a mixture of communities, and each community is defined as a multinomial distribution over nodes. Both the mixing coefficients and the community distribution are parameterized by the low-dimensional representations of the nodes and communities. We designed an effective variational inference algorithm which regularizes the community membership of neighboring nodes to be similar in the latent space. Experimental results on multiple real-world graphs show that vGraph is very effective in both community detection and node representation learning, outperforming many competitive baselines in both tasks. We show that the framework of vGraph is quite flexible and can be easily extended to detect hierarchical communities.
To address the sparsity and cold start problem of collaborative filtering, researchers usually make use of side information, such as social networks or item attributes, to improve recommendation performance. This paper considers the knowledge graph as the source of side information. To address the limitations of existing embedding-based and path-based methods for knowledge-graph-aware recommendation, we propose Ripple Network, an end-to-end framework that naturally incorporates the knowledge graph into recommender systems. Similar to actual ripples propagating on the surface of water, Ripple Network stimulates the propagation of user preferences over the set of knowledge entities by automatically and iteratively extending a user's potential interests along links in the knowledge graph. The multiple "ripples" activated by a user's historically clicked items are thus superposed to form the preference distribution of the user with respect to a candidate item, which could be used for predicting the final clicking probability. Through extensive experiments on real-world datasets, we demonstrate that Ripple Network achieves substantial gains in a variety of scenarios, including movie, book and news recommendation, over several state-of-the-art baselines.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191