Neural Information Processing Systems http://nips.cc/

Graph Neural Networks (GNNs) often suffer from weak-generalization due to sparsely labeled data despite their promising results on various graph-based tasks. Data augmentation is a prevalent remedy to improve the generalization ability of models in many domains. However, due to the non-Euclidean nature of data space and the dependencies between samples, designing effective augmentation on graphs is challenging. In this paper, we propose a novel framework Metropolis-Hastings Data Augmentation (MH-Aug) that draws augmented graphs from an explicit target distribution for semi-supervised learning. MH-Aug produces a sequence of augmented graphs from the target distribution enables flexible control of the strength and diversity of augmentation. Since the direct sampling from the complex target distribution is challenging, we adopt the Metropolis-Hastings algorithm to obtain the augmented samples. We also propose a simple and effective semi-supervised learning strategy with generated samples from MH-Aug. Our extensive experiments demonstrate that MH-Aug can generate a sequence of samples according to the target distribution to significantly improve the performance of GNNs.

We introduce ParK, a new large-scale solver for kernel ridge regression. Our approach combines partitioning with random projections and iterative optimization to reduce space and time complexity while provably maintaining the same statistical accuracy. In particular, constructing suitable partitions directly in the feature space rather than in the input space, we promote orthogonality between the local estimators, thus ensuring that key quantities such as local effective dimension and bias remain under control. We characterize the statistical-computational tradeoff of our model, and demonstrate the effectiveness of our method by numerical experiments on large-scale datasets.

Machine Learning (ML) can help solve combinatorial optimization (CO) problems better. A popular approach is to use a neural net to compute on the parameters of a given CO problem and extract useful information that guides the search for good solutions. Many CO problems of practical importance can be specified in a matrix form of parameters quantifying the relationship between two groups of items. There is currently no neural net model, however, that takes in such matrix-style relationship data as an input. Consequently, these types of CO problems have been out of reach for ML engineers. In this paper, we introduce Matrix Encoding Network (MatNet) and show how conveniently it takes in and processes parameters of such complex CO problems. Using an end-to-end model based on MatNet, we solve asymmetric traveling salesman (ATSP) and flexible flow shop (FFSP) problems as the earliest neural approach. In particular, for a class of FFSP we have tested MatNet on, we demonstrate a far superior empirical performance to any methods (neural or not) known to date.

It is great to see the kind of interest in applying machine learning, and specifically reinforcement learning, into real-world problems such as computer systems as presented in this paper. While the paper has no significant contributions on either a theoretical or algorithmic front, it does an important job at highlighting some of the issues in applying modern RL algorithms to real problems, and provides a necessary benchmarking environment for computer systems research specifically. The problem domains included have a wide variety of characteristics, from high-frequent real-time systems to very-long horizon problems, uniquely structured state and action spaces and both simulated and real environments (some other related work that could be added is [1]). Especially the latter is valuable to ground any research. Moreover, the authors provide an RL baseline result for each of the proposed tasks, and highlight some of the problematic characteristics of these tasks for RL specifically. There could be a more elaborate discussion of the results however.

The reviewers have each reviewed this paper carefully, and have taken the author response into account. There is clear consensus among them that this paper is a valuable contribution to the research community, both in helping to bring the application area of ML for systems environment more into the conversation and for providing a solid suite of benchmarks to foster further innovation within the community. I especially appreciate this aspect of helping to make the future research community more effective. In the author response, the authors describe several ways in which their paper will be revised to take reviewer feedback into account, and I expect this will be done for any final version of the paper.

We present a novel OCR-free document understanding framework based on pretrained Multimodal Large Language Models (MLLMs). Our approach employs multi-scale visual features to effectively handle various font sizes within document images.To address the increasing costs of considering the multi-scale visual inputs for MLLMs, we propose the Hierarchical Visual Feature Aggregation (HVFA) module, designed to reduce the number of input tokens to LLMs. Leveraging a feature pyramid with cross-attentive pooling, our approach effectively manages the trade-off between information loss and efficiency without being affected by varying document image sizes.Furthermore, we introduce a novel instruction tuning task, which facilitates the model's text-reading capability by learning to predict the relative positions of input text, eventually minimizing the risk of truncated text caused by the limited capacity of LLMs.Comprehensive experiments validate the effectiveness of our approach, demonstrating superior performance in various document understanding tasks.

Autonomous cars will now be allowed on all public Boston roads. The city has played host to nuTonomy for some time now, allowing the company to test its self-driving Renault Zoes at the Raymond L. Flynn Marine Park in January of last year, later expanding its testing zone to the Seaport District. And for the past few months, nuTonomy and Lyft have teamed up on a pilot program, transporting passengers in the autonomous vehicles within the Seaport area. Now, Boston will allow nuTonomy to test its vehicles city-wide. "Continuing to test autonomous vehicles in a careful and methodical manner represents another step forward in helping us to achieve the vision for improved mobility that was established by residents during the Go Boston 2030 Transportation Plan public process," Boston Mayor Martin Walsh said in a statement.

This article presents an innovative research project (sponsored by the National Science Foundation, the American Iron and Steel Institute, and the American Institute of Steel Construction) where computationally elegant algorithms based on the integration of a novel connectionist computing model, mathematical optimization, and a massively parallel computer architecture are used to automate the complex process of engineering design. Adeli and his associates have been working on creating novel design theories and computational models with two broad objectives: (1) automation and (2) optimization (Adeli and Hung 1995; Adeli and Kamal 1993; Adeli and Zhang 1993; Adeli and Yeh 1989; Adeli and Balasubramanyam 1988a, 1998b; Paek and Adeli 1988; Adeli and Alrijleh 1987). Civil-engineering structures are typically one of a kind as opposed to manufacturing designs that are often mass produced. To create computational models for structural design automation, we have been exploring new computing paradigms. Two such paradigms are neurocomputing and parallel processing.

With a simple swipe of the band across sensors located throughout the park, the giant system knows where you are, what you're doing and what you need. The goal of the tech team who developed the MagicBands was to "root out all the friction within the Disney World experience." The goal would be to potentially offer customized guest experiences at those points. The more data Disney collects it can improve operational efficiency such as in the scheduling of 240,00 shifts for 80,000 employees each week, the better it is able to target marketing because the preferences and behaviors of past guests are used to create future packages and offers specific to them and Disney is even dabbling at making robotic versions of Mickey and Minnie and all of its characters that would move around among the guests and interact with them.