Search Results for author:
Found 576 papers, 295 papers with code
Practical recommendations for gradient-based training of deep architectures
Learning algorithms related to artificial neural networks and in particular for Deep Learning may seem to involve many bells and whistles, called hyper-parameters.
Graph Attention Networks
We present graph attention networks (GATs), novel neural network architectures that operate on graph-structured data, leveraging masked self-attentional layers to address the shortcomings of prior methods based on graph convolutions or their approximations.
Ranked #1 on
Node Classification
on Pubmed
(Validation metric)
Generative Adversarial Networks
We propose a new framework for estimating generative models via an adversarial process, in which we simultaneously train two models: a generative model G that captures the data distribution, and a discriminative model D that estimates the probability that a sample came from the training data rather than G. The training procedure for G is to maximize the probability of D making a mistake.
Super-Resolution
Time-Series Few-Shot Learning with Heterogeneous Channels
Hyperbolic Discounting and Learning over Multiple Horizons
Reinforcement learning (RL) typically defines a discount factor as part of the Markov Decision Process.
On Catastrophic Interference in Atari 2600 Games
Our study provides a clear empirical link between catastrophic interference and sample efficiency in reinforcement learning.
Revisiting Fundamentals of Experience Replay
Experience replay is central to off-policy algorithms in deep reinforcement learning (RL), but there remain significant gaps in our understanding.
MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis
In this paper, we show that it is possible to train GANs reliably to generate high quality coherent waveforms by introducing a set of architectural changes and simple training techniques.
Boundary-Seeking Generative Adversarial Networks
We introduce a method for training GANs with discrete data that uses the estimated difference measure from the discriminator to compute importance weights for generated samples, thus providing a policy gradient for training the generator.
Neural Machine Translation by Jointly Learning to Align and Translate
Neural machine translation is a recently proposed approach to machine translation.
Ranked #4 on
Dialogue Generation
on Persona-Chat
(using extra training data)
Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
In this paper, we propose a novel neural network model called RNN Encoder-Decoder that consists of two recurrent neural networks (RNN).
Ranked #47 on
Machine Translation
on WMT2014 English-French
Deep Graph Infomax
We present Deep Graph Infomax (DGI), a general approach for learning node representations within graph-structured data in an unsupervised manner.
Ranked #49 on
Node Classification
on Citeseer
Theano: A Python framework for fast computation of mathematical expressions
Since its introduction, it has been one of the most used CPU and GPU mathematical compilers - especially in the machine learning community - and has shown steady performance improvements.
A Structured Self-attentive Sentence Embedding
This paper proposes a new model for extracting an interpretable sentence embedding by introducing self-attention.
SpeechBrain: A General-Purpose Speech Toolkit
SpeechBrain is an open-source and all-in-one speech toolkit.
Compositional Attention: Disentangling Search and Retrieval
Through our qualitative analysis, we demonstrate that Compositional Attention leads to dynamic specialization based on the type of retrieval needed.
N-BEATS: Neural basis expansion analysis for interpretable time series forecasting
We focus on solving the univariate times series point forecasting problem using deep learning.
Time Series
Time-Series Few-Shot Learning with Heterogeneous Channels
+1
BinaryConnect: Training Deep Neural Networks with binary weights during propagations
We introduce BinaryConnect, a method which consists in training a DNN with binary weights during the forward and backward propagations, while retaining precision of the stored weights in which gradients are accumulated.
Ranked #30 on
Image Classification
on SVHN
Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1
We introduce a method to train Binarized Neural Networks (BNNs) - neural networks with binary weights and activations at run-time.
Predicting COVID-19 Pneumonia Severity on Chest X-ray with Deep Learning
In this study, we present a severity score prediction model for COVID-19 pneumonia for frontal chest X-ray images.
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
Inspired by recent work in machine translation and object detection, we introduce an attention based model that automatically learns to describe the content of images.
Temporal Latent Bottleneck: Synthesis of Fast and Slow Processing Mechanisms in Sequence Learning
A slow stream that is recurrent in nature aims to learn a specialized and compressed representation, by forcing chunks of $K$ time steps into a single representation which is divided into multiple vectors.
Unsupervised State Representation Learning in Atari
State representation learning, or the ability to capture latent generative factors of an environment, is crucial for building intelligent agents that can perform a wide variety of tasks.
Benchmarking Graph Neural Networks
In the last few years, graph neural networks (GNNs) have become the standard toolkit for analyzing and learning from data on graphs.
Ranked #1 on
Link Prediction
on COLLAB
Quaternion Recurrent Neural Networks
Recurrent neural networks (RNNs) are powerful architectures to model sequential data, due to their capability to learn short and long-term dependencies between the basic elements of a sequence.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Twin Regularization for online speech recognition
Online speech recognition is crucial for developing natural human-machine interfaces.
Twin Networks: Matching the Future for Sequence Generation
We propose a simple technique for encouraging generative RNNs to plan ahead.
The PyTorch-Kaldi Speech Recognition Toolkit
Experiments, that are conducted on several datasets and tasks, show that PyTorch-Kaldi can effectively be used to develop modern state-of-the-art speech recognizers.
Ranked #1 on
Distant Speech Recognition
on DIRHA English WSJ
Interpretable Convolutional Filters with SincNet
Deep learning is currently playing a crucial role toward higher levels of artificial intelligence.
Ranked #3 on
Distant Speech Recognition
on DIRHA English WSJ
Learning General Purpose Distributed Sentence Representations via Large Scale Multi-task Learning
In this work, we present a simple, effective multi-task learning framework for sentence representations that combines the inductive biases of diverse training objectives in a single model.
Ranked #1 on
Semantic Textual Similarity
on SentEval
BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning
Allowing humans to interactively train artificial agents to understand language instructions is desirable for both practical and scientific reasons, but given the poor data efficiency of the current learning methods, this goal may require substantial research efforts.
The Variational Bandwidth Bottleneck: Stochastic Evaluation on an Information Budget
This is typically the case when we have a standard conditioning input, such as a state observation, and a "privileged" input, which might correspond to the goal of a task, the output of a costly planning algorithm, or communication with another agent.
Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations
Quantized recurrent neural networks were tested over the Penn Treebank dataset, and achieved comparable accuracy as their 32-bit counterparts using only 4-bits.
Torchmeta: A Meta-Learning library for PyTorch
The constant introduction of standardized benchmarks in the literature has helped accelerating the recent advances in meta-learning research.
Gradient based sample selection for online continual learning
To prevent forgetting, a replay buffer is usually employed to store the previous data for the purpose of rehearsal.
On Using Very Large Target Vocabulary for Neural Machine Translation
The models trained by the proposed approach are empirically found to outperform the baseline models with a small vocabulary as well as the LSTM-based neural machine translation models.
Gradient Starvation: A Learning Proclivity in Neural Networks
We identify and formalize a fundamental gradient descent phenomenon resulting in a learning proclivity in over-parameterized neural networks.
Ranked #1 on
Out-of-Distribution Generalization
on ImageNet-W
Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization
To answer these questions, we revisit the fundamental assumptions in linear regression tasks, where invariance-based approaches were shown to provably generalize OOD.
FitNets: Hints for Thin Deep Nets
In this paper, we extend this idea to allow the training of a student that is deeper and thinner than the teacher, using not only the outputs but also the intermediate representations learned by the teacher as hints to improve the training process and final performance of the student.
Attention-Based Models for Speech Recognition
Recurrent sequence generators conditioned on input data through an attention mechanism have recently shown very good performance on a range of tasks in- cluding machine translation, handwriting synthesis and image caption gen- eration.
Ranked #17 on
Speech Recognition
on TIMIT
Blocks and Fuel: Frameworks for deep learning
We introduce two Python frameworks to train neural networks on large datasets: Blocks and Fuel.
Speaker Recognition from Raw Waveform with SincNet
Rather than employing standard hand-crafted features, the latter CNNs learn low-level speech representations from waveforms, potentially allowing the network to better capture important narrow-band speaker characteristics such as pitch and formants.
Speech and Speaker Recognition from Raw Waveform with SincNet
Deep neural networks can learn complex and abstract representations, that are progressively obtained by combining simpler ones.
Hyena Hierarchy: Towards Larger Convolutional Language Models
Recent advances in deep learning have relied heavily on the use of large Transformers due to their ability to learn at scale.
Ranked #37 on
Language Modelling
on WikiText-103
Learning deep representations by mutual information estimation and maximization
In this work, we perform unsupervised learning of representations by maximizing mutual information between an input and the output of a deep neural network encoder.
Improving and generalizing flow-based generative models with minibatch optimal transport
CFM features a stable regression objective like that used to train the stochastic flow in diffusion models but enjoys the efficient inference of deterministic flow models.
Simulation-free Schrödinger bridges via score and flow matching
We present simulation-free score and flow matching ([SF]$^2$M), a simulation-free objective for inferring stochastic dynamics given unpaired samples drawn from arbitrary source and target distributions.
Deep Complex Networks
Despite their attractive properties and potential for opening up entirely new neural architectures, complex-valued deep neural networks have been marginalized due to the absence of the building blocks required to design such models.
Ranked #3 on
Music Transcription
on MusicNet
Avoidance Learning Using Observational Reinforcement Learning
We define avoidance learning as the process of optimizing the agent's reward while avoiding dangerous behaviors given by a demonstrator.
BabyAI 1.1
This increases reinforcement learning sample efficiency by up to 3 times and improves imitation learning performance on the hardest level from 77 % to 90. 4 %.
An Actor-Critic Algorithm for Sequence Prediction
We present an approach to training neural networks to generate sequences using actor-critic methods from reinforcement learning (RL).
Ranked #8 on
Machine Translation
on IWSLT2015 English-German
NICE: Non-linear Independent Components Estimation
It is based on the idea that a good representation is one in which the data has a distribution that is easy to model.
Ranked #73 on
Image Generation
on CIFAR-10
(bits/dimension metric)
Maxout Networks
We consider the problem of designing models to leverage a recently introduced approximate model averaging technique called dropout.
Ranked #35 on
Image Classification
on MNIST
Manifold Mixup: Better Representations by Interpolating Hidden States
Deep neural networks excel at learning the training data, but often provide incorrect and confident predictions when evaluated on slightly different test examples.
Ranked #18 on
Image Classification
on OmniBenchmark
Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation
Using insights from Temporal Difference learning, we propose GFlowNet, based on a view of the generative process as a flow network, making it possible to handle the tricky case where different trajectories can yield the same final state, e. g., there are many ways to sequentially add atoms to generate some molecular graph.
Trajectory balance: Improved credit assignment in GFlowNets
Generative flow networks (GFlowNets) are a method for learning a stochastic policy for generating compositional objects, such as graphs or strings, from a given unnormalized density by sequences of actions, where many possible action sequences may lead to the same object.
Learning GFlowNets from partial episodes for improved convergence and stability
Generative flow networks (GFlowNets) are a family of algorithms for training a sequential sampler of discrete objects under an unnormalized target density and have been successfully used for various probabilistic modeling tasks.
Plug & Play Generative Networks: Conditional Iterative Generation of Images in Latent Space
PPGNs are composed of 1) a generator network G that is capable of drawing a wide range of image types and 2) a replaceable "condition" network C that tells the generator what to draw.
SampleRNN: An Unconditional End-to-End Neural Audio Generation Model
In this paper we propose a novel model for unconditional audio generation based on generating one audio sample at a time.
HyenaDNA: Long-Range Genomic Sequence Modeling at Single Nucleotide Resolution
Leveraging Hyena's new long-range capabilities, we present HyenaDNA, a genomic foundation model pretrained on the human reference genome with context lengths of up to 1 million tokens at the single nucleotide-level - an up to 500x increase over previous dense attention-based models.
The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation
State-of-the-art approaches for semantic image segmentation are built on Convolutional Neural Networks (CNNs).
Ranked #9 on
Semantic Segmentation
on CamVid
Combined Reinforcement Learning via Abstract Representations
In the quest for efficient and robust reinforcement learning methods, both model-free and model-based approaches offer advantages.
Noisy Activation Functions
Common nonlinear activation functions used in neural networks can cause training difficulties due to the saturation behavior of the activation function, which may hide dependencies that are not visible to vanilla-SGD (using first order gradients only).
Manifold Mixup: Learning Better Representations by Interpolating Hidden States
Because the hidden states are learned, this has an important effect of encouraging the hidden states for a class to be concentrated in such a way so that interpolations within the same class or between two different classes do not intersect with the real data points from other classes.
Iterative Alternating Neural Attention for Machine Reading
We propose a novel neural attention architecture to tackle machine comprehension tasks, such as answering Cloze-style queries with respect to a document.
Ranked #3 on
Question Answering
on Children's Book Test
(Accuracy-NE metric)
Learning Problem-agnostic Speech Representations from Multiple Self-supervised Tasks
Learning good representations without supervision is still an open issue in machine learning, and is particularly challenging for speech signals, which are often characterized by long sequences with a complex hierarchical structure.
Ranked #2 on
Distant Speech Recognition
on DIRHA English WSJ
Multi-task self-supervised learning for Robust Speech Recognition
We then propose a revised encoder that better learns short- and long-term speech dynamics with an efficient combination of recurrent and convolutional networks.
Challenges in Representation Learning: A report on three machine learning contests
The ICML 2013 Workshop on Challenges in Representation Learning focused on three challenges: the black box learning challenge, the facial expression recognition challenge, and the multimodal learning challenge.
Ranked #12 on
Facial Expression Recognition (FER)
on FER2013
HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering
Existing question answering (QA) datasets fail to train QA systems to perform complex reasoning and provide explanations for answers.
Ranked #34 on
Question Answering
on HotpotQA
GMNN: Graph Markov Neural Networks
Statistical relational learning methods can effectively model the dependency of object labels through conditional random fields for collective classification, whereas graph neural networks learn effective object representations for classification through end-to-end training.
Neural Networks with Few Multiplications
For most deep learning algorithms training is notoriously time consuming.
Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
In this paper we compare different types of recurrent units in recurrent neural networks (RNNs).
Ranked #10 on
Music Modeling
on JSB Chorales
Generative Adversarial Nets
We propose a new framework for estimating generative models via adversarial nets, in which we simultaneously train two models: a generative model G that captures the data distribution, and a discriminative model D that estimates the probability that a sample came from the training data rather than G. The training procedure for G is to maximize the probability of D making a mistake.
Deep Generative Stochastic Networks Trainable by Backprop
We introduce a novel training principle for probabilistic models that is an alternative to maximum likelihood.
Variance Reduction in SGD by Distributed Importance Sampling
This leads the model to update using an unbiased estimate of the gradient which also has minimum variance when the sampling proposal is proportional to the L2-norm of the gradient.
MINE: Mutual Information Neural Estimation
We argue that the estimation of mutual information between high dimensional continuous random variables can be achieved by gradient descent over neural networks.
Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations
We propose zoneout, a novel method for regularizing RNNs.
A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues
Sequential data often possesses a hierarchical structure with complex dependencies between subsequences, such as found between the utterances in a dialogue.
Multiresolution Recurrent Neural Networks: An Application to Dialogue Response Generation
We introduce the multiresolution recurrent neural network, which extends the sequence-to-sequence framework to model natural language generation as two parallel discrete stochastic processes: a sequence of high-level coarse tokens, and a sequence of natural language tokens.
Ranked #1 on
Dialogue Generation
on Ubuntu Dialogue (Activity)
Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models
We investigate the task of building open domain, conversational dialogue systems based on large dialogue corpora using generative models.
Brain Tumor Segmentation with Deep Neural Networks
Finally, we explore a cascade architecture in which the output of a basic CNN is treated as an additional source of information for a subsequent CNN.
Ranked #1 on
Brain Tumor Segmentation
on BRATS-2013 leaderboard
A Recurrent Latent Variable Model for Sequential Data
In this paper, we explore the inclusion of latent random variables into the dynamic hidden state of a recurrent neural network (RNN) by combining elements of the variational autoencoder.
HighRes-net: Multi-Frame Super-Resolution by Recursive Fusion
Multi-frame Super-Resolution (MFSR) offers a more grounded approach to the ill-posed problem, by conditioning on multiple low-resolution views.
Ranked #6 on
Multi-Frame Super-Resolution
on PROBA-V
HighRes-net: Recursive Fusion for Multi-Frame Super-Resolution of Satellite Imagery
Multi-frame Super-Resolution (MFSR) offers a more grounded approach to the ill-posed problem, by conditioning on multiple low-resolution views.
Ranked #6 on
Multi-Frame Super-Resolution
on PROBA-V
Oracle performance for visual captioning
The task of associating images and videos with a natural language description has attracted a great amount of attention recently.
End-to-End Attention-based Large Vocabulary Speech Recognition
Many of the current state-of-the-art Large Vocabulary Continuous Speech Recognition Systems (LVCSR) are hybrids of neural networks and Hidden Markov Models (HMMs).
Task Loss Estimation for Sequence Prediction
Our idea is that this score can be interpreted as an estimate of the task loss, and that the estimation error may be used as a consistent surrogate loss.
Artificial Neural Networks Applied to Taxi Destination Prediction
We describe our first-place solution to the ECML/PKDD discovery challenge on taxi destination prediction.
Ensemble of Generative and Discriminative Techniques for Sentiment Analysis of Movie Reviews
Sentiment analysis is a common task in natural language processing that aims to detect polarity of a text document (typically a consumer review).
Graph Neural Networks with Learnable Structural and Positional Representations
An approach to tackle this issue is to introduce Positional Encoding (PE) of nodes, and inject it into the input layer, like in Transformers.
Ranked #12 on
Graph Regression
on ZINC-500k
Speech Model Pre-training for End-to-End Spoken Language Understanding
Whereas conventional spoken language understanding (SLU) systems map speech to text, and then text to intent, end-to-end SLU systems map speech directly to intent through a single trainable model.
Ranked #15 on
Spoken Language Understanding
on Fluent Speech Commands
(using extra training data)
CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learning
To facilitate research addressing this problem, we propose CausalWorld, a benchmark for causal structure and transfer learning in a robotic manipulation environment.
Meta-learning framework with applications to zero-shot time-series forecasting
Can meta-learning discover generic ways of processing time series (TS) from a diverse dataset so as to greatly improve generalization on new TS coming from different datasets?
GFlowNet Foundations
Generative Flow Networks (GFlowNets) have been introduced as a method to sample a diverse set of candidates in an active learning context, with a training objective that makes them approximately sample in proportion to a given reward function.
torchgfn: A PyTorch GFlowNet library
The growing popularity of generative flow networks (GFlowNets or GFNs) from a range of researchers with diverse backgrounds and areas of expertise necessitates a library which facilitates the testing of new features such as training losses that can be easily compared to standard benchmark implementations, or on a set of common environments.
Chunked Autoregressive GAN for Conditional Waveform Synthesis
We show that simple pitch and periodicity conditioning is insufficient for reducing this error relative to using autoregression.
A Hierarchical Recurrent Encoder-Decoder For Generative Context-Aware Query Suggestion
Our novel hierarchical recurrent encoder-decoder architecture allows the model to be sensitive to the order of queries in the context while avoiding data sparsity.
Plan, Attend, Generate: Planning for Sequence-to-Sequence Models
We investigate the integration of a planning mechanism into sequence-to-sequence models using attention.
Plan, Attend, Generate: Character-level Neural Machine Translation with Planning in the Decoder
We investigate the integration of a planning mechanism into an encoder-decoder architecture with an explicit alignment for character-level machine translation.
A Character-Level Decoder without Explicit Segmentation for Neural Machine Translation
The existing machine translation systems, whether phrase-based or neural, have relied almost exclusively on word-level modelling with explicit segmentation.
Ranked #3 on
Machine Translation
on WMT2015 English-German
An Empirical Study of Example Forgetting during Deep Neural Network Learning
Inspired by the phenomenon of catastrophic forgetting, we investigate the learning dynamics of neural networks as they train on single classification tasks.
On the Properties of Neural Machine Translation: Encoder-Decoder Approaches
In this paper, we focus on analyzing the properties of the neural machine translation using two models; RNN Encoder--Decoder and a newly proposed gated recursive convolutional neural network.
Interpolated Adversarial Training: Achieving Robust Neural Networks without Sacrificing Too Much Accuracy
Adversarial robustness has become a central goal in deep learning, both in the theory and the practice.
Maximum Entropy Generators for Energy-Based Models
Maximum likelihood estimation of energy-based models is a challenging problem due to the intractability of the log-likelihood gradient.
Interpolation Consistency Training for Semi-Supervised Learning
We introduce Interpolation Consistency Training (ICT), a simple and computation efficient algorithm for training Deep Neural Networks in the semi-supervised learning paradigm.
Hierarchical Multiscale Recurrent Neural Networks
Multiscale recurrent neural networks have been considered as a promising approach to resolve this issue, yet there has been a lack of empirical evidence showing that this type of models can actually capture the temporal dependencies by discovering the latent hierarchical structure of the sequence.
Ranked #19 on
Language Modelling
on Text8
ReSeg: A Recurrent Neural Network-based Model for Semantic Segmentation
Moreover, ReNet layers are stacked on top of pre-trained convolutional layers, benefiting from generic local features.
Ranked #18 on
Semantic Segmentation
on CamVid
ReNet: A Recurrent Neural Network Based Alternative to Convolutional Networks
In this paper, we propose a deep neural network architecture for object recognition based on recurrent neural networks.
Ranked #35 on
Image Classification
on MNIST
A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms
We show that causal structures can be parameterized via continuous variables and learned end-to-end.
Multi-Fidelity Active Learning with GFlowNets
For example, in scientific discovery, we are often faced with the problem of exploring very large, high-dimensional spaces, where querying a high fidelity, black-box objective function is very expensive.
Crystal-GFN: sampling crystals with desirable properties and constraints
Accelerating material discovery holds the potential to greatly help mitigate the climate crisis.
RNNLogic: Learning Logic Rules for Reasoning on Knowledge Graphs
Then in the E-step, we select a set of high-quality rules from all generated rules with both the rule generator and reasoning predictor via posterior inference; and in the M-step, the rule generator is updated with the rules selected in the E-step.
BilBOWA: Fast Bilingual Distributed Representations without Word Alignments
We introduce BilBOWA (Bilingual Bag-of-Words without Alignments), a simple and computationally-efficient model for learning bilingual distributed representations of words which can scale to large monolingual datasets and does not require word-aligned parallel training data.
Ranked #1 on
Document Classification
on Reuters En-De
Cross-Lingual Document Classification
Document Classification
+3
Recurrent Independent Mechanisms
Learning modular structures which reflect the dynamics of the environment can lead to better generalization and robustness to changes which only affect a few of the underlying causes.
MaD TwinNet: Masker-Denoiser Architecture with Twin Networks for Monaural Sound Source Separation
Current state of the art (SOTA) results in monaural singing voice separation are obtained with deep learning based methods.
Sound Audio and Speech Processing
Equivalence of Equilibrium Propagation and Recurrent Backpropagation
Recurrent Backpropagation and Equilibrium Propagation are supervised learning algorithms for fixed point recurrent neural networks which differ in their second phase.
Equilibrium Propagation: Bridging the Gap Between Energy-Based Models and Backpropagation
Because the objective function is defined in terms of local perturbations, the second phase of Equilibrium Propagation corresponds to only nudging the prediction (fixed point, or stationary distribution) towards a configuration that reduces prediction error.
Generalization of Equilibrium Propagation to Vector Field Dynamics
The biological plausibility of the backpropagation algorithm has long been doubted by neuroscientists.
Learning to Understand Phrases by Embedding the Dictionary
Distributional models that learn rich semantic word representations are a success story of recent NLP research.
Representation Learning: A Review and New Perspectives
The success of machine learning algorithms generally depends on data representation, and we hypothesize that this is because different representations can entangle and hide more or less the different explanatory factors of variation behind the data.
Learning Fixed Points in Generative Adversarial Networks: From Image-to-Image Translation to Disease Detection and Localization
Qualitative and quantitative evaluations demonstrate that the proposed method outperforms the state of the art in multi-domain image-to-image translation and that it surpasses predominant weakly-supervised localization methods in both disease detection and localization.
Learning Neural Causal Models from Unknown Interventions
Promising results have driven a recent surge of interest in continuous optimization methods for Bayesian network structure learning from observational data.
Learning Neural Causal Models with Active Interventions
Discovering causal structures from data is a challenging inference problem of fundamental importance in all areas of science.
Ant Colony Sampling with GFlowNets for Combinatorial Optimization
This paper introduces the Generative Flow Ant Colony Sampler (GFACS), a novel neural-guided meta-heuristic algorithm for combinatorial optimization.
On the Spectral Bias of Neural Networks
Neural networks are known to be a class of highly expressive functions able to fit even random input-output mappings with $100\%$ accuracy.
Image-to-image translation for cross-domain disentanglement
We compare our model to the state-of-the-art in multi-modal image translation and achieve better results for translation on challenging datasets as well as for cross-domain retrieval on realistic datasets.
Amortizing intractable inference in large language models
Autoregressive large language models (LLMs) compress knowledge from their training data through next-token conditional distributions.
Tell, Draw, and Repeat: Generating and Modifying Images Based on Continual Linguistic Instruction
Conditional text-to-image generation is an active area of research, with many possible applications.
Ranked #2 on
Text-to-Image Generation
on GeNeVA (i-CLEVR)
Towards Gene Expression Convolutions using Gene Interaction Graphs
We find this approach provides an advantage for particular tasks in a low data regime but is very dependent on the quality of the graph used.
Generative Flow Networks for Discrete Probabilistic Modeling
We present energy-based generative flow networks (EB-GFN), a novel probabilistic modeling algorithm for high-dimensional discrete data.
Bayesian Structure Learning with Generative Flow Networks
In Bayesian structure learning, we are interested in inferring a distribution over the directed acyclic graph (DAG) structure of Bayesian networks, from data.
A Hitchhiker's Guide to Geometric GNNs for 3D Atomic Systems
In these graphs, the geometric attributes transform according to the inherent physical symmetries of 3D atomic systems, including rotations and translations in Euclidean space, as well as node permutations.
GraphMix: Improved Training of GNNs for Semi-Supervised Learning
We present GraphMix, a regularization method for Graph Neural Network based semi-supervised object classification, whereby we propose to train a fully-connected network jointly with the graph neural network via parameter sharing and interpolation-based regularization.
Ranked #1 on
Node Classification
on Pubmed random partition
ClimateGAN: Raising Climate Change Awareness by Generating Images of Floods
Climate change is a major threat to humanity, and the actions required to prevent its catastrophic consequences include changes in both policy-making and individual behaviour.
Biological Sequence Design with GFlowNets
In this work, we propose an active learning algorithm leveraging epistemic uncertainty estimation and the recently proposed GFlowNets as a generator of diverse candidate solutions, with the objective to obtain a diverse batch of useful (as defined by some utility function, for example, the predicted anti-microbial activity of a peptide) and informative candidates after each round.
Fraternal Dropout
We show that our regularization term is upper bounded by the expectation-linear dropout objective which has been shown to address the gap due to the difference between the train and inference phases of dropout.
Ranked #28 on
Language Modelling
on Penn Treebank (Word Level)
An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks
Catastrophic forgetting is a problem faced by many machine learning models and algorithms.
Training deep neural networks with low precision multiplications
For each of those datasets and for each of those formats, we assess the impact of the precision of the multiplications on the final error after training.
Learning To Navigate The Synthetically Accessible Chemical Space Using Reinforcement Learning
Over the last decade, there has been significant progress in the field of machine learning for de novo drug design, particularly in deep generative models.
Learning to Navigate in Synthetically Accessible Chemical Space Using Reinforcement Learning
In this work, we propose a novel reinforcement learning (RL) setup for drug discovery that addresses this challenge by embedding the concept of synthetic accessibility directly into the de novo compound design system.
GEO-Bench: Toward Foundation Models for Earth Monitoring
Recent progress in self-supervision has shown that pre-training large neural networks on vast amounts of unsupervised data can lead to substantial increases in generalization to downstream tasks.
Straight to the Tree: Constituency Parsing with Neural Syntactic Distance
In this work, we propose a novel constituency parsing scheme.
Parameterizing Branch-and-Bound Search Trees to Learn Branching Policies
We aim instead at learning a policy that generalizes across heterogeneous MILPs: our main hypothesis is that parameterizing the state of the B&B search tree can aid this type of generalization.
Equilibrated adaptive learning rates for non-convex optimization
Parameter-specific adaptive learning rate methods are computationally efficient ways to reduce the ill-conditioning problems encountered when training large deep networks.
A Consciousness-Inspired Planning Agent for Model-Based Reinforcement Learning
We present an end-to-end, model-based deep reinforcement learning agent which dynamically attends to relevant parts of its state during planning.
Model-based Reinforcement Learning
Out-of-Distribution Generalization
+2
Bayesian Model-Agnostic Meta-Learning
Learning to infer Bayesian posterior from a few-shot dataset is an important step towards robust meta-learning due to the model uncertainty inherent in the problem.
Towards an Automatic Turing Test: Learning to Evaluate Dialogue Responses
Automatically evaluating the quality of dialogue responses for unstructured domains is a challenging problem.
Foundational Challenges in Assuring Alignment and Safety of Large Language Models
This work identifies 18 foundational challenges in assuring the alignment and safety of large language models (LLMs).
Count-ception: Counting by Fully Convolutional Redundant Counting
Our contribution is redundant counting instead of predicting a density map in order to average over errors.
Improving day-ahead Solar Irradiance Time Series Forecasting by Leveraging Spatio-Temporal Context
Solar power harbors immense potential in mitigating climate change by substantially reducing CO$_{2}$ emissions.
Learning Independent Features with Adversarial Nets for Non-linear ICA
We propose to learn independent features with adversarial objectives which optimize such measures implicitly.
An End-to-End Framework for Molecular Conformation Generation via Bilevel Programming
Specifically, the molecular graph is first encoded in a latent space, and then the 3D structures are generated by solving a principled bilevel optimization program.
Reweighted Wake-Sleep
The wake-sleep algorithm relies on training not just the directed generative model but also a conditional generative model (the inference network) that runs backward from visible to latent, estimating the posterior distribution of latent given visible.
Combining Modular Skills in Multitask Learning
By jointly learning these and a task-skill allocation matrix, the network for each task is instantiated as the average of the parameters of active skills.
Unitary Evolution Recurrent Neural Networks
When the eigenvalues of the hidden to hidden weight matrix deviate from absolute value 1, optimization becomes difficult due to the well studied issue of vanishing and exploding gradients, especially when trying to learn long-term dependencies.
Ranked #26 on
Sequential Image Classification
on Sequential MNIST
Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning
A central goal for AI and causality is thus the joint discovery of abstract representations and causal structure.
DynGFN: Towards Bayesian Inference of Gene Regulatory Networks with GFlowNets
In this paper we leverage the fact that it is possible to estimate the "velocity" of gene expression with RNA velocity techniques to develop an approach that addresses both challenges.
Learning Neural Generative Dynamics for Molecular Conformation Generation
Inspired by the recent progress in deep generative models, in this paper, we propose a novel probabilistic framework to generate valid and diverse conformations given a molecular graph.
Interactive Language Learning by Question Answering
In QAit, an agent must interact with a partially observable text-based environment to gather information required to answer questions.
Hybrid Models for Learning to Branch
First, in a more realistic setting where only a CPU is available, is the GNN model still competitive?
Let the Flows Tell: Solving Graph Combinatorial Optimization Problems with GFlowNets
In this paper, we design Markov decision processes (MDPs) for different combinatorial problems and propose to train conditional GFlowNets to sample from the solution space.
Generating Factoid Questions With Recurrent Neural Networks: The 30M Factoid Question-Answer Corpus
Over the past decade, large-scale supervised learning corpora have enabled machine learning researchers to make substantial advances.
Bidirectional Helmholtz Machines
We present a lower-bound for the likelihood of this model and we show that optimizing this bound regularizes the model so that the Bhattacharyya distance between the bottom-up and top-down approximate distributions is minimized.
Tackling Climate Change with Machine Learning
Climate change is one of the greatest challenges facing humanity, and we, as machine learning experts, may wonder how we can help.
Diffusion Generative Flow Samplers: Improving learning signals through partial trajectory optimization
We tackle the problem of sampling from intractable high-dimensional density functions, a fundamental task that often appears in machine learning and statistics.
Gated Orthogonal Recurrent Units: On Learning to Forget
We present a novel recurrent neural network (RNN) based model that combines the remembering ability of unitary RNNs with the ability of gated RNNs to effectively forget redundant/irrelevant information in its memory.
Ranked #7 on
Question Answering
on bAbi
(Accuracy (trained on 1k) metric)
FigureQA: An Annotated Figure Dataset for Visual Reasoning
To resolve, such questions often require reference to multiple plot elements and synthesis of information distributed spatially throughout a figure.
Ranked #3 on
Visual Question Answering (VQA)
on FigureQA - test 1
Do Neural Dialog Systems Use the Conversation History Effectively? An Empirical Study
Neural generative models have been become increasingly popular when building conversational agents.
HNHN: Hypergraph Networks with Hyperedge Neurons
Hypergraphs provide a natural representation for many real world datasets.
Diet Networks: Thin Parameters for Fat Genomics
It is based on the idea that we can first learn or provide a distributed representation for each input feature (e. g. for each position in the genome where variations are observed), and then learn (with another neural network called the parameter prediction network) how to map a feature's distributed representation to the vector of parameters specific to that feature in the classifier neural network (the weights which link the value of the feature to each of the hidden units).
Z-Forcing: Training Stochastic Recurrent Networks
Stochastic recurrent models have been successful in capturing the variability observed in natural sequential data such as speech.
A Closer Look at Memorization in Deep Networks
We examine the role of memorization in deep learning, drawing connections to capacity, generalization, and adversarial robustness.
Difference Target Propagation
Back-propagation has been the workhorse of recent successes of deep learning but it relies on infinitesimal effects (partial derivatives) in order to perform credit assignment.
On Adversarial Mixup Resynthesis
In this paper, we explore new approaches to combining information encoded within the learned representations of auto-encoders.
Data-Driven Approach to Encoding and Decoding 3-D Crystal Structures
We present a method to encode and decode the position of atoms in 3-D molecules from a dataset of nearly 50, 000 stable crystal unit cells that vary from containing 1 to over 100 atoms.
DiVA: Diverse Visual Feature Aggregation for Deep Metric Learning
Visual Similarity plays an important role in many computer vision applications.
Ranked #13 on
Metric Learning
on CUB-200-2011
(using extra training data)
Light Gated Recurrent Units for Speech Recognition
A field that has directly benefited from the recent advances in deep learning is Automatic Speech Recognition (ASR).
Ranked #6 on
Speech Recognition
on TIMIT
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Improving speech recognition by revising gated recurrent units
First, we suggest to remove the reset gate in the GRU design, resulting in a more efficient single-gate architecture.
Icentia11K: An Unsupervised Representation Learning Dataset for Arrhythmia Subtype Discovery
We release the largest public ECG dataset of continuous raw signals for representation learning containing 11 thousand patients and 2 billion labelled beats.
MAgNet: Mesh Agnostic Neural PDE Solver
The computational complexity of classical numerical methods for solving Partial Differential Equations (PDE) scales significantly as the resolution increases.
Is a Modular Architecture Enough?
Inspired from human cognition, machine learning systems are gradually revealing advantages of sparser and more modular architectures.
AI for Global Climate Cooperation: Modeling Global Climate Negotiations, Agreements, and Long-Term Cooperation in RICE-N
To facilitate this research, here we introduce RICE-N, a multi-region integrated assessment model that simulates the global climate and economy, and which can be used to design and evaluate the strategic outcomes for different negotiation and agreement frameworks.
GFlowNet-EM for learning compositional latent variable models
Latent variable models (LVMs) with discrete compositional latents are an important but challenging setting due to a combinatorially large number of possible configurations of the latents.
Machine Learning for Glacier Monitoring in the Hindu Kush Himalaya
Glacier mapping is key to ecological monitoring in the hkh region.
Multi-Image Super-Resolution for Remote Sensing using Deep Recurrent Networks
High-resolution satellite imagery is critical for various earth observation applications related to environment monitoring, geoscience, forecasting, and land use analysis.
FloW: A Dataset and Benchmark for Floating Waste Detection in Inland Waters
To promote the practical application for autonomous floating wastes cleaning, we present FloW, the first dataset for floating waste detection in inland water areas.
Towards end-to-end spoken language understanding
Spoken language understanding system is traditionally designed as a pipeline of a number of components.
Natural Language Understanding
Spoken Language Understanding
Variational Walkback: Learning a Transition Operator as a Stochastic Recurrent Net
The energy function is then modified so the model and data distributions match, with no guarantee on the number of steps required for the Markov chain to converge.
Identifying and attacking the saddle point problem in high-dimensional non-convex optimization
Gradient descent or quasi-Newton methods are almost ubiquitously used to perform such minimizations, and it is often thought that a main source of difficulty for these local methods to find the global minimum is the proliferation of local minima with much higher error than the global minimum.
Learning to Combine Top-Down and Bottom-Up Signals in Recurrent Neural Networks with Attention over Modules
To effectively utilize the wealth of potential top-down information available, and to prevent the cacophony of intermixed signals in a bidirectional architecture, mechanisms are needed to restrict information flow.
DEUP: Direct Epistemic Uncertainty Prediction
Epistemic Uncertainty is a measure of the lack of knowledge of a learner which diminishes with more evidence.
The Causal-Neural Connection: Expressiveness, Learnability, and Inference
Given this property, one may be tempted to surmise that a collection of neural nets is capable of learning any SCM by training on data generated by that SCM.
MixupE: Understanding and Improving Mixup from Directional Derivative Perspective
Mixup is a popular data augmentation technique for training deep neural networks where additional samples are generated by linearly interpolating pairs of inputs and their labels.
Predictive Inference with Feature Conformal Prediction
Conformal prediction is a distribution-free technique for establishing valid prediction intervals.
Iterated Denoising Energy Matching for Sampling from Boltzmann Densities
Efficiently generating statistically independent samples from an unnormalized probability distribution, such as equilibrium samples of many-body systems, is a foundational problem in science.
Iterative Neural Autoregressive Distribution Estimator (NADE-k)
Training of the neural autoregressive density estimator (NADE) can be viewed as doing one step of probabilistic inference on missing values in data.
Ranked #7 on
Image Generation
on Binarized MNIST
Iterative Neural Autoregressive Distribution Estimator NADE-k
Training of the neural autoregressive density estimator (NADE) can be viewed as doing one step of probabilistic inference on missing values in data.
Ranked #8 on
Image Generation
on Binarized MNIST
RECOVER: sequential model optimization platform for combination drug repurposing identifies novel synergistic compounds in vitro
For large libraries of small molecules, exhaustive combinatorial chemical screens become infeasible to perform when considering a range of disease models, assay conditions, and dose ranges.
Interventional Causal Representation Learning
Can interventional data facilitate causal representation learning?
Non-normal Recurrent Neural Network (nnRNN): learning long time dependencies while improving expressivity with transient dynamics
A recent strategy to circumvent the exploding and vanishing gradient problem in RNNs, and to allow the stable propagation of signals over long time scales, is to constrain recurrent connectivity matrices to be orthogonal or unitary.
