Neural Architecture Search (NAS) is a promising and rapidly evolving research area. Training a large number of neural networks requires an exceptional amount of computational power, which makes NAS unreachable for those researchers who have limited or no access to high-performance clusters and supercomputers. A few benchmarks with precomputed neural architectures performances have been recently introduced to overcome this problem and ensure more reproducible experiments. However, these benchmarks are only for the computer vision domain and, thus, are built from the image datasets and convolution-derived architectures. In this work, we step outside the computer vision domain by leveraging the language modeling task, which is the core of natural language processing (NLP). Our main contribution is as follows: we have provided search space of recurrent neural networks on the text datasets and trained 14k architectures within it; we have conducted both intrinsic and extrinsic evaluation of the trained models using datasets for semantic relatedness and language understanding evaluation; finally, we have tested several NAS algorithms to demonstrate how the precomputed results can be utilized. We believe that our results have high potential of usage for both NAS and NLP communities.

With the rising number of machine learning competitions, the world has witnessed an exciting race for the best algorithms. However, the involved data selection process may fundamentally suffer from evidence ambiguity and concept drift issues, thereby possibly leading to deleterious effects on the performance of various models. This paper proposes a new Reinforced Data Sampling (RDS) method to learn how to sample data adequately on the search for useful models and insights. We formulate the optimisation problem of model diversification $\delta{-div}$ in data sampling to maximise learning potentials and optimum allocation by injecting model diversity. This work advocates the employment of diverse base learners as value functions such as neural networks, decision trees, or logistic regressions to reinforce the selection process of data subsets with multi-modal belief. We introduce different ensemble reward mechanisms, including soft voting and stochastic choice to approximate optimal sampling policy. The evaluation conducted on four datasets evidently highlights the benefits of using RDS method over traditional sampling approaches. Our experimental results suggest that the trainable sampling for model diversification is useful for competition organisers, researchers, or even starters to pursue full potentials of various machine learning tasks such as classification and regression. The source code is available at https://github.com/probeu/RDS.

Deep neural networks have successfully been trained in various application areas with stochastic gradient descent. However, there exists no rigorous mathematical explanation why this works so well. The training of neural networks with stochastic gradient descent has four different discretization parameters: (i) the network architecture; (ii) the size of the training data; (iii) the number of gradient steps; and (iv) the number of randomly initialized gradient trajectories. While it can be shown that the approximation error converges to zero if all four parameters are sent to infinity in the right order, we demonstrate in this paper that stochastic gradient descent fails to converge for rectified linear unit networks if their depth is much larger than their width and the number of random initializations does not increase to infinity fast enough.

End-to-end training of neural network solvers for combinatorial problems such as the Travelling Salesman Problem is intractable and inefficient beyond a few hundreds of nodes. While state-of-the-art Machine Learning approaches perform closely to classical solvers for trivially small sizes, they are unable to generalize the learnt policy to larger instances of practical scales. Towards leveraging transfer learning to solve large-scale TSPs, this paper identifies inductive biases, model architectures and learning algorithms that promote generalization to instances larger than those seen in training. Our controlled experiments provide the first principled investigation into such zero-shot generalization, revealing that extrapolating beyond training data requires rethinking the entire neural combinatorial optimization pipeline, from network layers and learning paradigms to evaluation protocols.

Disentanglement is an enjoyable property in representation learning which increases the interpretability of generative models such as Variational Auto-Encoders (VAE), Generative Adversarial Models and their many variants. In the context of latent space models, this work presents a representation learning framework that explicitly promotes disentanglement thanks to the combination of an auto-encoder with Principal Component Analysis (PCA) in latent space. The proposed objective is the sum of an auto-encoder error term along with a PCA reconstruction error in the feature space. This has an interpretation of a Restricted Kernel Machine with an interconnection matrix on the Stiefel manifold. The construction encourages a matching between the principal directions in latent space and the directions of orthogonal variation in data space. The training algorithm involves a stochastic optimization method on the Stiefel manifold, which increases only marginally the computing time compared to an analogous VAE. Our theoretical discussion and various experiments show that the proposed model improves over many VAE variants along with special emphasis on disentanglement learning.

Deep reinforcement learning (RL) algorithms have achieved great success on a wide variety of sequential decision-making tasks. However, many of these algorithms suffer from high sample complexity when learning from scratch using environmental rewards, due to issues such as credit-assignment and high-variance gradients, among others. Transfer learning, in which knowledge gained on a source task is applied to more efficiently learn a different but related target task, is a promising approach to improve the sample complexity in RL. Prior work has considered using pre-trained teacher policies to enhance the learning of the student policy, albeit with the constraint that the teacher and the student MDPs share the state-space or the action-space. In this paper, we propose a new framework for transfer learning where the teacher and the student can have arbitrarily different state- and action-spaces. To handle this mismatch, we produce embeddings which can systematically extract knowledge from the teacher policy and value networks, and blend it into the student networks. To train the embeddings, we use a task-aligned loss and show that the representations could be enriched further by adding a mutual information loss. Using a set of challenging simulated robotic locomotion tasks involving many-legged centipedes, we demonstrate successful transfer learning in situations when the teacher and student have different state- and action-spaces.

One fundamental problem in the learning treatment effect from observational data is confounder identification and balancing. Most of the previous methods realized confounder balancing by treating all observed variables as confounders, ignoring the identification of confounders and non-confounders. In general, not all the observed variables are confounders which are the common causes of both the treatment and the outcome, some variables only contribute to the treatment and some contribute to the outcome. Balancing those non-confounders would generate additional bias for treatment effect estimation. By modeling the different relations among variables, treatment and outcome, we propose a synergistic learning framework to 1) identify and balance confounders by learning decomposed representation of confounders and non-confounders, and simultaneously 2) estimate the treatment effect in observational studies via counterfactual inference. Our empirical results demonstrate that the proposed method can precisely identify and balance confounders, while the estimation of the treatment effect performs better than the state-of-the-art methods on both synthetic and real-world datasets.

Retrosynthesis prediction is a fundamental problem in organic synthesis, where the task is to identify precursor molecules that can be used to synthesize a target molecule. Despite recent advancements in neural retrosynthesis algorithms, they are unable to fully recapitulate the strategies employed by chemists and do not generalize well to infrequent reaction types. In this paper, we propose a graph-based approach that capitalizes on the idea that the graph topology of precursor molecules is largely unaltered during the reaction. The model first predicts the set of graph edits transforming the target into incomplete molecules called synthons. Next, the model learns to expand synthons into complete molecules by attaching relevant leaving groups. Since the model operates at the level of molecular fragments, it avoids full generation, greatly simplifying the underlying architecture and improving its ability to generalize. The model yields $11.7\%$ absolute improvement over state-of-the-art approaches on the USPTO-50k dataset, and a $4\%$ absolute improvement on a rare reaction subset of the same dataset.

A spectral mixture (SM) kernel is a flexible kernel used to model any stationary covariance function. Although it is useful in modeling data, the learning of the SM kernel is generally difficult because optimizing a large number of parameters for the SM kernel typically induces an over-fitting, particularly when a gradient-based optimization is used. Also, a longer training time is required. To improve the training, we propose an approximate Bayesian inference for the SM kernel. Specifically, we employ the variational distribution of the spectral points to approximate SM kernel with a random Fourier feature. We optimize the variational parameters by applying a sampling-based variational inference to the derived evidence lower bound (ELBO) estimator constructed from the approximate kernel. To improve the inference, we further propose two additional strategies: (1) a sampling strategy of spectral points to estimate the ELBO estimator reliably and thus its associated gradient, and (2) an approximate natural gradient to accelerate the convergence of the parameters. The proposed inference combined with two strategies accelerates the convergence of the parameters and leads to better optimal parameters.

Federated learning allows multiple users to collaboratively train a shared classification model while preserving data privacy. This approach, where model updates are aggregated by a central server, was shown to be vulnerable to backdoor attacks: a malicious user can alter the shared model to arbitrarily classify specific inputs from a given class. In this paper, we analyze the effects of backdoor attacks in federated meta-learning, where users train a model that can be adapted to different sets of output classes using only a few training examples. While the ability to adapt could, in principle, make federated learning more robust to backdoor attacks when new training examples are benign, we find that even 1-shot poisoning attacks can be very successful and persist after additional training. To address these vulnerabilities, we propose a defense mechanism inspired by matching networks, where the class of an input is predicted from the cosine similarity of its features with a support set of labeled examples. By removing the decision logic from the model shared with the federation, success and persistence of backdoor attacks are greatly reduced.