We propose a new task of conversational recommendation over multi-type dialogs, where the bots can proactively and naturally lead a conversation from a non-recommendation dialog (e.g., QA) to a recommendation dialog, taking into account user's interests and feedback. To facilitate the study of this task, we create a human-to-human Chinese dialog dataset \emph{DuRecDial} (about 10k dialogs, 156k utterances), which contains multiple sequential dialogs for every pair of a recommendation seeker (user) and a recommender (bot). In each dialog, the recommender proactively leads a multi-type dialog to approach recommendation targets and then makes multiple recommendations with rich interaction behavior. This dataset allows us to systematically investigate different parts of the overall problem, e.g., how to naturally lead a dialog, how to interact with users for recommendation. Finally we establish baseline results on DuRecDial for future studies. Dataset and codes are publicly available at https://github.com/PaddlePaddle/models/tree/develop/PaddleNLP/Research/ACL2020-DuRecDial.

This paper presents a novel attention-based algorithm for achieving adaptive computation called DACT, which, unlike existing ones, is end-to-end differentiable. Our method can be used in conjunction with many networks; in particular, we study its application to the widely known MAC architecture, obtaining a significant reduction in the number of recurrent steps needed to achieve similar accuracies, therefore improving its performance to computation ratio. Furthermore, we show that by increasing the maximum number of steps used, we surpass the accuracy of even our best non-adaptive MAC in the CLEVR dataset, demonstrating that our approach is able to control the number of steps without significant loss of performance. Additional advantages provided by our approach include considerably improving interpretability by discarding useless steps and providing more insights into the underlying reasoning process. Finally, we present adaptive computation as an equivalent to an ensemble of models, similar to a mixture of expert formulation. Both the code and the configuration files for our experiments are made available to support further research in this area.

Designing DNA and protein sequences with improved or novel function has the potential to greatly accelerate synthetic biology. Machine learning models that accurately predict biological fitness from sequence are becoming a powerful tool for molecular design. Activation maximization offers a simple design strategy for differentiable models: one-hot coded sequences are first approximated by a continuous representation which is then iteratively optimized with respect to the predictor oracle by gradient ascent. While elegant, this method is limited by technical challenges, as it suffers from vanishing gradients and may cause predictor pathologies leading to poor convergence. Here, we build on a previously proposed straight-through approximation method to optimize through discrete sequence samples. By normalizing nucleotide logits across positions and introducing an adaptive entropy variable, we remove bottlenecks arising from overly large or skewed sampling parameters. This results in a markedly improved algorithm with up to 100-fold faster convergence. Moreover, our method finds improved fitness optima compared to existing methods, including the original algorithm without normalization and global optimization heuristics such as Simulated Annealing. We demonstrate our improved method by designing DNA and enzyme sequences for six deep learning predictors, including a protein structure predictor (trRosetta).

Domain adaptation (DA) offers a valuable means to reuse data and models for new problem domains. However, robust techniques have not yet been considered for time series data with varying amounts of data availability. In this paper, we make three main contributions to fill this gap. First, we propose a novel Convolutional deep Domain Adaptation model for Time Series data (CoDATS) that significantly improves accuracy and training time over state-of-the-art DA strategies on real-world sensor data benchmarks. By utilizing data from multiple source domains, we increase the usefulness of CoDATS to further improve accuracy over prior single-source methods, particularly on complex time series datasets that have high variability between domains. Second, we propose a novel Domain Adaptation with Weak Supervision (DA-WS) method by utilizing weak supervision in the form of target-domain label distributions, which may be easier to collect than additional data labels. Third, we perform comprehensive experiments on diverse real-world datasets to evaluate the effectiveness of our domain adaptation and weak supervision methods. Results show that CoDATS for single-source DA significantly improves over the state-of-the-art methods, and we achieve additional improvements in accuracy using data from multiple source domains and weakly supervised signals. Code is available at: https://github.com/floft/codats

Deep speaker embedding models have been commonly used as a building block for speaker diarization systems; however, the speaker embedding model is usually trained according to a global loss defined on the training data, which could be sub-optimal for distinguishing speakers locally in a specific meeting session. In this work we present the first use of graph neural networks (GNNs) for the speaker diarization problem, utilizing a GNN to refine speaker embeddings locally using the structural information between speech segments inside each session. The speaker embeddings extracted by a pre-trained model are remapped into a new embedding space, in which the different speakers within a single session are better separated. The model is trained for linkage prediction in a supervised manner by minimizing the difference between the affinity matrix constructed by the refined embeddings and the ground-truth adjacency matrix. Spectral clustering is then applied on top of the refined embeddings. We show that the clustering performance of the refined speaker embeddings outperforms the original embeddings significantly on both simulated and real meeting data, and our system achieves the state-of-the-art result on the NIST SRE 2000 CALLHOME database.

A Tree Architecture of LSTM Networks for Sequential Regression with Missing Data S. Onur Sahin and Suleyman S. Kozat, Senior Member, IEEE Abstract --We investigate regression for variable length sequential data containing missing samples and introduce a novel tree architecture based on the Long Short-T erm Memory (LSTM) networks. In our architecture, we employ a variable number of LSTM networks, which use only the existing inputs in the sequence, in a treelike architecture without any statistical assumptions or imputations on the missing data, unlike all the previous approaches. In particular, we incorporate the missingness information by selecting a subset of these LSTM networks based on "presence-pattern" of a certain number of previous inputs. From the mixture of experts perspective, we train different LSTM networks as our experts for various missingness patterns and then combine their outputs to generate the final prediction. We also provide the computational complexity analysis of the proposed architecture, which is in the same order of the complexity of the conventional LSTM architectures for the sequence length. Our method can be readily extended to similar structures such as GRUs, RNNs as remarked in the paper . In the experiments, we achieve significant performance improvements with respect to the state-of-the-art methods for the well-known financial and real life datasets. I NTRODUCTION A. Preliminaries We study regression of variable length sequential data containing missing samples. Here, we sequentially receive a data sequence suffering from missing input values and estimate an unknown desired signal related to this data sequence. In most regression tasks involving sequential data, one usually assumes that we have the complete data sequence [1]. However, nearly in every real life application, the data sequences usually contain missing input values due to various reasons such as inconvenience, anomalies and cost savings [2], [3]. Furthermore, in many real life problems such as medical imaging applications [4] and finance [5], we encounter nonuniformly sampled data, which can be modelled as a missing data case [6]. To mitigate these issues, the widely used approaches make certain statistical assumptions on the missing data [7], [8], however, these assumptions usually do not hold and the This works is in part supported by Turkish Academy of Sciences Outstanding Researcher Programme and TUBIT AK Project No: 117E153.

Channel pruning is one of the predominant approaches for accelerating deep neural networks. Most existing pruning methods either train from scratch with a sparsity inducing term such as group lasso, or prune redundant channels in a pretrained network and then fine tune the network. Both strategies suffer from some limitations: the use of group lasso is computationally expensive, difficult to converge and often suffers from worse behavior due to the regularization bias. The methods that start with a pretrained network either prune channels uniformly across the layers or prune channels based on the basic statistics of the network parameters. These approaches either ignore the fact that some CNN layers are more redundant than others or fail to adequately identify the level of redundancy in different layers. In this work, we investigate a simple-yet-effective method for pruning channels based on a computationally light-weight yet effective data driven optimization step that discovers the necessary width per layer. Experiments conducted on ILSVRC-$12$ confirm effectiveness of our approach. With non-uniform pruning across the layers on ResNet-$50$, we are able to match the FLOP reduction of state-of-the-art channel pruning results while achieving a $0.98\%$ higher accuracy. Further, we show that our pruned ResNet-$50$ network outperforms ResNet-$34$ and ResNet-$18$ networks, and that our pruned ResNet-$101$ outperforms ResNet-$50$.

De novo therapeutic design is challenged by a vast chemical repertoire and multiple constraints such as high broad-spectrum potency and low toxicity. We propose CLaSS (Controlled Latent attribute Space Sampling) - a novel and efficient computational method for attribute-controlled generation of molecules, which leverages guidance from classifiers trained on an informative latent space of molecules modeled using a deep generative autoencoder. We further screen the generated molecules by using a set of deep learning classifiers in conjunction with novel physicochemical features derived from high-throughput molecular simulations. The proposed approach is employed for designing non-toxic antimicrobial peptides (AMPs) with strong broad-spectrum potency, which are emerging drug candidates for tackling antibiotic resistance. Synthesis and wet lab testing of only twenty designed sequences identified two novel and minimalist AMPs with high potency against diverse Gram-positive and Gram-negative pathogens, including the hard-to-treat multidrug-resistant K. pneumoniae, as well as low in vitro and in vivo toxicity. The proposed approach thus presents a viable path for faster discovery of potent and selective broad-spectrum antimicrobials with a higher success rate than state-of-the-art methods.

Computer-aided diagnosis via deep learning relies on large-scale annotated data sets, which can be costly when involving expert knowledge. Semi-supervised learning (SSL) mitigates this challenge by leveraging unlabeled data. One effective SSL approach is to regularize the local smoothness of neural functions via perturbations around single data points. In this work, we argue that regularizing the global smoothness of neural functions by filling the void in between data points can further improve SSL. We present a novel SSL approach that trains the neural network on linear mixing of labeled and unlabeled data, at both the input and latent space in order to regularize different portions of the network. We evaluated the presented model on two distinct medical image data sets for semi-supervised classification of thoracic disease and skin lesion, demonstrating its improved performance over SSL with local perturbations and SSL with global mixing but at the input space only. Our code is available at https://github.com/Prasanna1991/LatentMixing.

Neural Architecture Search (NAS) is a research field concerned with utilizing optimization algorithms to design optimal neural network architectures. There are many approaches concerning the architectural search spaces, optimization algorithms, as well as candidate architecture evaluation methods. As the field is growing at a continuously increasing pace, it is difficult for a beginner to discern between major, as well as emerging directions the field has followed. In this work, we provide an introduction to the basic concepts of NAS for convolutional networks, along with the major advances in search spaces, algorithms and evaluation techniques.