In recent years, neural architecture search (NAS) has received intensive scientific and industrial interest due to its capability of finding a neural architecture with high accuracy for various artificial intelligence tasks such as image classification or object detection. In particular, gradient-based NAS approaches have become one of the more popular approaches thanks to their computational efficiency during the search. However, these methods often experience a mode collapse, where the quality of the found architectures is poor due to the algorithm resorting to choosing a single operation type for the entire network, or stagnating at a local minima for various datasets or search spaces. To address these defects, we present a differentiable variational inference-based NAS method for searching sparse convolutional neural networks. Our approach finds the optimal neural architecture by dropping out candidate operations in an over-parameterised supergraph using variational dropout with automatic relevance determination prior, which makes the algorithm gradually remove unnecessary operations and connections without risking mode collapse. The evaluation is conducted through searching two types of convolutional cells that shape the neural network for classifying different image datasets. Our method finds diverse network cells, while showing state-of-the-art accuracy with up to almost 2 times fewer non-zero parameters.

Overparameterised deep neural networks (DNNs) are highly expressive and so can, in principle, generate almost any function that fits a training dataset with zero error. The vast majority of these functions will perform poorly on unseen data, and yet in practice DNNs often generalise remarkably well. This success suggests that a trained DNN must have a strong inductive bias towards functions with low generalisation error. Here we empirically investigate this inductive bias by calculating, for a range of architectures and datasets, the probability $P_{SGD}(f\mid S)$ that an overparameterised DNN, trained with stochastic gradient descent (SGD) or one of its variants, converges on a function $f$ consistent with a training set $S$. We also use Gaussian processes to estimate the Bayesian posterior probability $P_B(f\mid S)$ that the DNN expresses $f$ upon random sampling of its parameters, conditioned on $S$. Our main findings are that $P_{SGD}(f\mid S)$ correlates remarkably well with $P_B(f\mid S)$ and that $P_B(f\mid S)$ is strongly biased towards low-error and low complexity functions. These results imply that strong inductive bias in the parameter-function map (which determines $P_B(f\mid S)$), rather than a special property of SGD, is the primary explanation for why DNNs generalise so well in the overparameterised regime. While our results suggest that the Bayesian posterior $P_B(f\mid S)$ is the first order determinant of $P_{SGD}(f\mid S)$, there remain second order differences that are sensitive to hyperparameter tuning. A function probability picture, based on $P_{SGD}(f\mid S)$ and/or $P_B(f\mid S)$, can shed new light on the way that variations in architecture or hyperparameter settings such as batch size, learning rate, and optimiser choice, affect DNN performance.

Previous literature offers limited clues on how to learn a periodic function using modern neural networks. We start with a study of the extrapolation properties of neural networks; we prove and demonstrate experimentally that the standard activations functions, such as ReLU, tanh, sigmoid, along with their variants, all fail to learn to extrapolate simple periodic functions. We hypothesize that this is due to their lack of a "periodic" inductive bias. As a fix of this problem, we propose a new activation, namely, $x + \sin^2(x)$, which achieves the desired periodic inductive bias to learn a periodic function while maintaining a favorable optimization property of the ReLU-based activations. Experimentally, we apply the proposed method to temperature and financial data prediction.

Negative sampling, which samples negative triplets from non-observed ones in knowledge graph (KG), is an essential step in KG embedding. Recently, generative adversarial network (GAN), has been introduced in negative sampling. By sampling negative triplets with large gradients, these methods avoid the problem of vanishing gradient and thus obtain better performance. However, they make the original model more complex and harder to train. In this paper, motivated by the observation that negative triplets with large gradients are important but rare, we propose to directly keep track of them with the cache. In this way, our method acts as a "distilled" version of previous GAN-based methods, which does not waste training time on additional parameters to fit the full distribution of negative triplets. However, how to sample from and update the cache are two critical questions. We propose to solve these issues by automated machine learning techniques. The automated version also covers GAN-based methods as special cases. Theoretical explanation of NSCaching is also provided, justifying the superior over fixed sampling scheme. Besides, we further extend NSCaching with skip-gram model for graph embedding. Finally, extensive experiments show that our method can gain significant improvements on various KG embedding models and the skip-gram model, and outperforms the state-of-the-art negative sampling methods.

Journal of Scheduling manuscript No. (will be inserted by the editor) Abstract The personnel rostering problem is the problem on which branch to choose next and to prune the search of finding an optimal way to assign employees to tree. The problem has received significant attention in the literature and is addressed by a large number of exact and 1 Introduction metaheuristic methods. In order to make the complex and costly design of heuristics for the personnel rostering In various occupations and work scenarios, arranging problem automatic, we propose a new method employees to different shifts is a difficult job. The difficulty combined Deep Neural Network and Tree Search. By is that different employees have different requirements treating schedules as matrices, the neural network can for life and work, which leads to preference of predict the distance between the current solution and each employee. And there are also requirements of the the optimal solution. It can select solution strategies by law that must be followed or diverse properties of different analyzing existing (near-)optimal solutions to personnel occupations. These regulations are what we call soft rostering problem instances.

We investigate the problem of multi-domain Dialogue State Tracking (DST) with open vocabulary. Existing approaches exploit BERT encoder and copy-based RNN decoder, where the encoder first predicts the state operation, and then the decoder generates new slot values. However, in this stacked encoder-decoder structure, the operation prediction objective only affects the BERT encoder and the value generation objective mainly affects the RNN decoder. In this paper, we propose a purely Transformer-based framework that uses BERT as both encoder and decoder. In so doing, the operation prediction objective and the value generation objective can jointly optimize our model for DST. At the decoding step, we re-use the hidden states of the encoder in the self-attention mechanism of the corresponding decoder layer to construct a flat model structure for effective parameter updating. Experimental results show that our approach substantially outperforms the existing state-of-the-art framework, and it also achieves very competitive performance to the best ontology-based approaches.

Code retrieval is to find the code snippet from a large corpus of source code repositories that highly matches the query of natural language description. Recent work mainly uses natural language processing techniques to process both query texts (i.e., human natural language) and code snippets (i.e., machine programming language), however neglecting the deep structured features of natural language query texts and source codes, both of which contain rich semantic information. In this paper, we propose an end-to-end deep graph matching and searching (DGMS) model based on graph neural networks for semantic code retrieval. To this end, we first represent both natural language query texts and programming language codes with the unified graph-structured data, and then use the proposed graph matching and searching model to retrieve the best matching code snippet. In particular, DGMS not only captures more structural information for individual query texts or code snippets but also learns the fine-grained similarity between them by a cross-attention based semantic matching operation. We evaluate the proposed DGMS model on two public code retrieval datasets from two representative programming languages (i.e., Java and Python). The experiment results demonstrate that DGMS significantly outperforms state-of-the-art baseline models by a large margin on both datasets. Moreover, our extensive ablation studies systematically investigate and illustrate the impact of each part of DGMS.

In this work we propose Pathfinder Discovery Networks (PDNs), a method for jointly learning a message passing graph over a multiplex network with a downstream semi-supervised model. PDNs inductively learn an aggregated weight for each edge, optimized to produce the best outcome for the downstream learning task. PDNs are a generalization of attention mechanisms on graphs which allow flexible construction of similarity functions between nodes, edge convolutions, and cheap multiscale mixing layers. We show that PDNs overcome weaknesses of existing methods for graph attention (e.g. Graph Attention Networks), such as the diminishing weight problem. Our experimental results demonstrate competitive predictive performance on academic node classification tasks. Additional results from a challenging suite of node classification experiments show how PDNs can learn a wider class of functions than existing baselines. We analyze the relative computational complexity of PDNs, and show that PDN runtime is not considerably higher than static-graph models. Finally, we discuss how PDNs can be used to construct an easily interpretable attention mechanism that allows users to understand information propagation in the graph.

Large multi-label text classification is a challenging Natural Language Processing (NLP) problem that is concerned with text classification for datasets with thousands of labels. We tackle this problem in the legal domain, where datasets, such as JRC-Acquis and EURLEX57K labeled with the EuroVoc vocabulary were created within the legal information systems of the European Union. The EuroVoc taxonomy includes around 7000 concepts. In this work, we study the performance of various recent transformer-based models in combination with strategies such as generative pretraining, gradual unfreezing and discriminative learning rates in order to reach competitive classification performance, and present new state-of-the-art results of 0.661 (F1) for JRC-Acquis and 0.754 for EURLEX57K. Furthermore, we quantify the impact of individual steps, such as language model fine-tuning or gradual unfreezing in an ablation study, and provide reference dataset splits created with an iterative stratification algorithm.

AI assistants have started carrying out tasks on a user's behalf by interacting directly with the web. However, training an interface that maps natural language (NL) commands to web actions is challenging for existing semantic parsing approaches due to the variable and unknown set of actions that characterize websites. We propose FLIN, a natural language interface for web navigation that maps NL commands to concept-level actions rather than low-level UI interactions, thus being able to flexibly adapt to different websites and handle their transient nature. We frame this as a ranking problem where, given a user command and a webpage, FLIN learns to score the most appropriate navigation instruction (involving action and parameter values). To train and evaluate FLIN, we collect a dataset using nine popular websites from three different domains. Quantitative results show that FLIN is capable of adapting to new websites in a given domain.