arXiv subjects

Yujia Li

Publications and source records attributed to Yujia Li.

At least 55 records · Page 3Linked to original sources

arXiv2020

Strong Generalization and Efficiency in Neural Programs

We study the problem of learning efficient algorithms that strongly generalize in the framework of neural program induction. By carefully designing the input / output interfaces of the neural model and through imitation, we are able to learn models that produce correct results for arbitrary input sizes, achieving strong generalization. Moreover, by using reinforcement learning, we optimize for program efficiency metrics, and discover new algorithms that surpass the teacher used in imitation. With this, our approach can learn to outperform custom-written solutions for a variety of problems, as we tested it on sorting, searching in ordered lists and the NP-complete 0/1 knapsack problem, which sets a notable milestone in the field of Neural Program Induction. As highlights, our learned model can perform sorting perfectly on any input data size we tested on, with $O(n log n)$ complexity, whilst outperforming hand-coded algorithms, including quick sort, in number of operations even for list sizes far beyond those seen during training.

cs.LG↗

arXiv2020

Scalable Deep Generative Modeling for Sparse Graphs

Learning graph generative models is a challenging task for deep learning and has wide applicability to a range of domains like chemistry, biology and social science. However current deep neural methods suffer from limited scalability: for a graph with $n$ nodes and $m$ edges, existing deep neural methods require $Ω(n^2)$ complexity by building up the adjacency matrix. On the other hand, many real world graphs are actually sparse in the sense that $m\ll n^2$. Based on this, we develop a novel autoregressive model, named BiGG, that utilizes this sparsity to avoid generating the full adjacency matrix, and importantly reduces the graph generation time complexity to $O((n + m)\log n)$. Furthermore, during training this autoregressive model can be parallelized with $O(\log n)$ synchronization stages, which makes it much more efficient than other autoregressive models that require $Ω(n)$. Experiments on several benchmarks show that the proposed approach not only scales to orders of magnitude larger graphs than previously possible with deep autoregressive graph generative models, but also yields better graph generation quality.

cs.LG↗

arXiv2020

A sparse negative binomial mixture model for clustering RNA-seq count data

Clustering with variable selection is a challenging yet critical task for modern small-n-large-p data. Existing methods based on sparse Gaussian mixture models or sparse K-means provide solutions to continuous data. With the prevalence of RNA-seq technology and lack of count data modeling for clustering, the current practice is to normalize count expression data into continuous measures and apply existing models with Gaussian assumption. In this paper, we develop a negative binomial mixture model with lasso or fused lasso gene regularization to cluster samples (small n) with high-dimensional gene features (large p). EM algorithm and Bayesian information criterion are used for inference and determining tuning parameters. The method is compared with existing methods using extensive simulations and two real transcriptomic applications in rat brain and breast cancer studies. The result shows superior performance of the proposed count data model in clustering accuracy, feature selection and biological interpretation in pathways.

stat.ML↗

arXiv2020

Reinforced Genetic Algorithm Learning for Optimizing Computation Graphs

We present a deep reinforcement learning approach to minimizing the execution cost of neural network computation graphs in an optimizing compiler. Unlike earlier learning-based works that require training the optimizer on the same graph to be optimized, we propose a learning approach that trains an optimizer offline and then generalizes to previously unseen graphs without further training. This allows our approach to produce high-quality execution decisions on real-world TensorFlow graphs in seconds instead of hours. We consider two optimization tasks for computation graphs: minimizing running time and peak memory usage. In comparison to an extensive set of baselines, our approach achieves significant improvements over classical and other learning-based methods on these two tasks.

cs.LG↗

arXiv2020

Learning the Graphical Structure of Electronic Health Records with Graph Convolutional Transformer

Effective modeling of electronic health records (EHR) is rapidly becoming an important topic in both academia and industry. A recent study showed that using the graphical structure underlying EHR data (e.g. relationship between diagnoses and treatments) improves the performance of prediction tasks such as heart failure prediction. However, EHR data do not always contain complete structure information. Moreover, when it comes to claims data, structure information is completely unavailable to begin with. Under such circumstances, can we still do better than just treating EHR data as a flat-structured bag-of-features? In this paper, we study the possibility of jointly learning the hidden structure of EHR while performing supervised prediction tasks on EHR data. Specifically, we discuss that Transformer is a suitable basis model to learn the hidden EHR structure, and propose Graph Convolutional Transformer, which uses data statistics to guide the structure learning process. The proposed model consistently outperformed previous approaches empirically, on both synthetic data and publicly available EHR data, for various prediction tasks such as graph reconstruction and readmission prediction, indicating that it can serve as an effective general-purpose representation learning algorithm for EHR data.

cs.LG↗

arXiv2019

Prioritized Unit Propagation with Periodic Resetting is (Almost) All You Need for Random SAT Solving

We propose prioritized unit propagation with periodic resetting, which is a simple but surprisingly effective algorithm for solving random SAT instances that are meant to be hard. In particular, an evaluation on the Random Track of the 2017 and 2018 SAT competitions shows that a basic prototype of this simple idea already ranks at second place in both years. We share this observation in the hope that it helps the SAT community better understand the hardness of random instances used in competitions and inspire other interesting ideas on SAT solving.

cs.AI↗

arXiv2019

Learning Transferable Graph Exploration

This paper considers the problem of efficient exploration of unseen environments, a key challenge in AI. We propose a `learning to explore' framework where we learn a policy from a distribution of environments. At test time, presented with an unseen environment from the same distribution, the policy aims to generalize the exploration strategy to visit the maximum number of unique states in a limited number of steps. We particularly focus on environments with graph-structured state-spaces that are encountered in many important real-world applications like software testing and map building. We formulate this task as a reinforcement learning problem where the `exploration' agent is rewarded for transitioning to previously unseen environment states and employ a graph-structured memory to encode the agent's past trajectory. Experimental results demonstrate that our approach is extremely effective for exploration of spatial maps; and when applied on the challenging problems of coverage-guided software-testing of domain-specific programs and real-world mobile applications, it outperforms methods that have been hand-engineered by human experts.

cs.LG↗

arXiv2019

Simultaneous Estimation of Number of Clusters and Feature Sparsity in Clustering High-Dimensional Data

Estimating the number of clusters (K) is a critical and often difficult task in cluster analysis. Many methods have been proposed to estimate K, including some top performers using resampling approach. When performing cluster analysis in high-dimensional data, simultaneous clustering and feature selection is needed for improved interpretation and performance. To our knowledge, none has investigated simultaneous estimation of K and feature selection in an exploratory cluster analysis. In this paper, we propose a resampling method to meet this gap and evaluate its performance under the sparse K-means clustering framework. The proposed target function balances between sensitivity and specificity of clustering evaluation of pairwise subjects from clustering of full and subsampled data. Through extensive simulations, the method performs among the best over classical methods in estimating K in low-dimensional data. For high-dimensional simulation data, it also shows superior performance to simultaneously estimate K and feature sparsity parameter. Finally, we evaluated the methods in four microarray, two RNA-seq, one SNP and two non-omics datasets. The proposed method achieves better clustering accuracy with fewer selected predictive genes in almost all real applications.

stat.ME↗

arXiv2019

Fast Training of Sparse Graph Neural Networks on Dense Hardware

Graph neural networks have become increasingly popular in recent years due to their ability to naturally encode relational input data and their ability to scale to large graphs by operating on a sparse representation of graph adjacency matrices. As we look to scale up these models using custom hardware, a natural assumption would be that we need hardware tailored to sparse operations and/or dynamic control flow. In this work, we question this assumption by scaling up sparse graph neural networks using a platform targeted at dense computation on fixed-size data. Drawing inspiration from optimization of numerical algorithms on sparse matrices, we develop techniques that enable training the sparse graph neural network model from Allamanis et al. [2018] in 13 minutes using a 512-core TPUv2 Pod, whereas the original training takes almost a day.

stat.ML↗

arXiv2019

CompILE: Compositional Imitation Learning and Execution

We introduce Compositional Imitation Learning and Execution (CompILE): a framework for learning reusable, variable-length segments of hierarchically-structured behavior from demonstration data. CompILE uses a novel unsupervised, fully-differentiable sequence segmentation module to learn latent encodings of sequential data that can be re-composed and executed to perform new tasks. Once trained, our model generalizes to sequences of longer length and from environment instances not seen during training. We evaluate CompILE in a challenging 2D multi-task environment and a continuous control task, and show that it can find correct task boundaries and event encodings in an unsupervised manner. Latent codes and associated behavior policies discovered by CompILE can be used by a hierarchical agent, where the high-level policy selects actions in the latent code space, and the low-level, task-specific policies are simply the learned decoders. We found that our CompILE-based agent could learn given only sparse rewards, where agents without task-specific policies struggle.

stat.ML↗

arXiv2019

Graph Matching Networks for Learning the Similarity of Graph Structured Objects

This paper addresses the challenging problem of retrieval and matching of graph structured objects, and makes two key contributions. First, we demonstrate how Graph Neural Networks (GNN), which have emerged as an effective model for various supervised prediction problems defined on structured data, can be trained to produce embedding of graphs in vector spaces that enables efficient similarity reasoning. Second, we propose a novel Graph Matching Network model that, given a pair of graphs as input, computes a similarity score between them by jointly reasoning on the pair through a new cross-graph attention-based matching mechanism. We demonstrate the effectiveness of our models on different domains including the challenging problem of control-flow-graph based function similarity search that plays an important role in the detection of vulnerabilities in software systems. The experimental analysis demonstrates that our models are not only able to exploit structure in the context of similarity learning but they can also outperform domain-specific baseline systems that have been carefully hand-engineered for these problems.

cs.LG↗

arXiv2019

Coherent optical modulation of partially mode-locked fiber laser based on coherent population oscillation in reduced oxide graphene

Optical control of graphene-based photonic devices and systems has been under extensive explorations, nevertheless, the requirement of high power pump laser due to incoherent modulation makes those schemes low efficient. Here, we demonstrate coherent manipulation of the operating states of partially mode-locked fiber laser based on coherent population oscillation in reduced graphene oxide for the first time. We couple a much weaker continuous wave laser into the resonator operating with parametric instability state, and observe significant depression/enhancement of the sidebands when the coherent population oscillation conditions are satisfied. Besides, significant depression of partially mode-locked fiber laser is achieved. The experimental results reveal that the coherent population oscillation in reduced graphene oxide is highly effective in manipulating mode-locked fiber laser system, and the induced phase variation is highly asymmetrical. The discovery of coherent population oscillation in reduced graphene oxide facilitates coherent optical modulation of reduced graphene oxide-based photonic devices and systems with a much weaker controlling laser.

physics.optics↗

arXiv2018

Polarization evolution dynamics of dissipative soliton fiber laser

Dissipative solitons are localized solutions in non-integrable and non-conservative nonlinear system, due to a balance of nonlinearity, dispersion, filtering, and loss/gain. Different from conventional soliton, they exhibit extremely complex and striking dynamics, and are more universal in the far-from-equilibrium natural system. Taking advantage of dispersive Fourier transform and time lens, the spatio-temporal transient dynamics of dissipative solitons have been characterized with both amplitude and phase. Yet, a full avenue of the buildup process of dissipative soliton is full of debris for the lack of the polarization evolution information. Here, we characterize the probabilistic polarization distributions in the buildup of dissipative soliton in a net-normal dispersion fiber laser system mode-locked by single-wall carbon nanotubes. The lasing system operates from random amplified spontaneous emission to stable dissipative soliton when the cavity gain is increasing, and state of polarization of each wavelength convergence exponentially towards a fixed point. To reveal the invariant polarization relationship among various wavelengths, the phase diagram of the ellipticity angle and spherical orientation angle is introduced. We find that the polarization of each filtered wavelength in the central region of the dissipative soliton is linearly spaced, while those in the two fronts are spatially varying. Increasing cavity gain leads to spectrum broadening, meanwhile, the polarizations of the new generated frequencies are extending to scatter. Further increasing pump power results into dissipative soliton explosion, during which a kind of polarization optical rogue waves is identified. Those experimental results provide more information for deeper insights into the transient dynamics of dissipative soliton fiber laser.

physics.optics↗

arXiv2018

Relational inductive biases, deep learning, and graph networks

Artificial intelligence (AI) has undergone a renaissance recently, making major progress in key domains such as vision, language, control, and decision-making. This has been due, in part, to cheap data and cheap compute resources, which have fit the natural strengths of deep learning. However, many defining characteristics of human intelligence, which developed under much different pressures, remain out of reach for current approaches. In particular, generalizing beyond one's experiences--a hallmark of human intelligence from infancy--remains a formidable challenge for modern AI. The following is part position paper, part review, and part unification. We argue that combinatorial generalization must be a top priority for AI to achieve human-like abilities, and that structured representations and computations are key to realizing this objective. Just as biology uses nature and nurture cooperatively, we reject the false choice between "hand-engineering" and "end-to-end" learning, and instead advocate for an approach which benefits from their complementary strengths. We explore how using relational inductive biases within deep learning architectures can facilitate learning about entities, relations, and rules for composing them. We present a new building block for the AI toolkit with a strong relational inductive bias--the graph network--which generalizes and extends various approaches for neural networks that operate on graphs, and provides a straightforward interface for manipulating structured knowledge and producing structured behaviors. We discuss how graph networks can support relational reasoning and combinatorial generalization, laying the foundation for more sophisticated, interpretable, and flexible patterns of reasoning. As a companion to this paper, we have released an open-source software library for building graph networks, with demonstrations of how to use them in practice.

cs.LG↗

arXiv2018

Proximal Policy Optimization and its Dynamic Version for Sequence Generation

In sequence generation task, many works use policy gradient for model optimization to tackle the intractable backpropagation issue when maximizing the non-differentiable evaluation metrics or fooling the discriminator in adversarial learning. In this paper, we replace policy gradient with proximal policy optimization (PPO), which is a proved more efficient reinforcement learning algorithm, and propose a dynamic approach for PPO (PPO-dynamic). We demonstrate the efficacy of PPO and PPO-dynamic on conditional sequence generation tasks including synthetic experiment and chit-chat chatbot. The results show that PPO and PPO-dynamic can beat policy gradient by stability and performance.

cs.CL↗

arXiv2018

Relational Deep Reinforcement Learning

We introduce an approach for deep reinforcement learning (RL) that improves upon the efficiency, generalization capacity, and interpretability of conventional approaches through structured perception and relational reasoning. It uses self-attention to iteratively reason about the relations between entities in a scene and to guide a model-free policy. Our results show that in a novel navigation and planning task called Box-World, our agent finds interpretable solutions that improve upon baselines in terms of sample complexity, ability to generalize to more complex scenes than experienced during training, and overall performance. In the StarCraft II Learning Environment, our agent achieves state-of-the-art performance on six mini-games -- surpassing human grandmaster performance on four. By considering architectural inductive biases, our work opens new directions for overcoming important, but stubborn, challenges in deep RL.

cs.LG↗

arXiv2018

Learning Deep Generative Models of Graphs

Graphs are fundamental data structures which concisely capture the relational structure in many important real-world domains, such as knowledge graphs, physical and social interactions, language, and chemistry. Here we introduce a powerful new approach for learning generative models over graphs, which can capture both their structure and attributes. Our approach uses graph neural networks to express probabilistic dependencies among a graph's nodes and edges, and can, in principle, learn distributions over any arbitrary graph. In a series of experiments our results show that once trained, our models can generate good quality samples of both synthetic graphs as well as real molecular graphs, both unconditionally and conditioned on data. Compared to baselines that do not use graph-structured representations, our models often perform far better. We also explore key challenges of learning generative models of graphs, such as how to handle symmetries and ordering of elements during the graph generation process, and offer possible solutions. Our work is the first and most general approach for learning generative models over arbitrary graphs, and opens new directions for moving away from restrictions of vector- and sequence-like knowledge representations, toward more expressive and flexible relational data structures.

cs.LG↗

arXiv2018

Imagination-Augmented Agents for Deep Reinforcement Learning

We introduce Imagination-Augmented Agents (I2As), a novel architecture for deep reinforcement learning combining model-free and model-based aspects. In contrast to most existing model-based reinforcement learning and planning methods, which prescribe how a model should be used to arrive at a policy, I2As learn to interpret predictions from a learned environment model to construct implicit plans in arbitrary ways, by using the predictions as additional context in deep policy networks. I2As show improved data efficiency, performance, and robustness to model misspecification compared to several baselines.

cs.LG↗