Search Results for author:
Found 64 papers, 30 papers with code
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.
Do Encoder Representations of Generative Dialogue Models have sufficient summary of the Information about the task ?
Predicting the next utterance in dialogue is contingent on encoding of users’ input text to generate appropriate and relevant response in data-driven approaches.
Towards Few-shot Coordination: Revisiting Ad-hoc Teamplay Challenge In the Game of Hanabi
In this work, we show empirically that state-of-the-art ZSC algorithms have poor performance when paired with agents trained with different learning methods, and they require millions of interaction samples to adapt to these new partners.
Lookbehind Optimizer: k steps back, 1 step forward
The Lookahead optimizer improves the training stability of deep neural networks by having a set of fast weights that "look ahead" to guide the descent direction.
Promoting Exploration in Memory-Augmented Adam using Critical Momenta
Adaptive gradient-based optimizers, particularly Adam, have left their mark in training large-scale deep learning models.
Thompson sampling for improved exploration in GFlowNets
Generative flow networks (GFlowNets) are amortized variational inference algorithms that treat sampling from a distribution over compositional objects as a sequential decision-making problem with a learnable action policy.
Measuring the Knowledge Acquisition-Utilization Gap in Pretrained Language Models
We propose a systematic framework to measure parametric knowledge utilization in PLMs.
Should We Attend More or Less? Modulating Attention for Fairness
In this work, we investigate the role of attention, a widely-used technique in current state-of-the-art NLP models, in the propagation of social biases.
Conditionally Optimistic Exploration for Cooperative Deep Multi-Agent Reinforcement Learning
Efficient exploration is critical in cooperative deep Multi-Agent Reinforcement Learning (MARL).
Replay Buffer With Local Forgetting for Adaptive Deep Model-Based Reinforcement Learning
This is challenging for deep-learning-based world models due to catastrophic forgetting.
Model-based Reinforcement Learning
reinforcement-learning
+1
Dealing With Non-stationarity in Decentralized Cooperative Multi-Agent Deep Reinforcement Learning via Multi-Timescale Learning
In our proposed method, when one agent updates its policy, other agents are allowed to update their policies as well, but at a slower rate.
Deep Learning on a Healthy Data Diet: Finding Important Examples for Fairness
The fairness achieved by our method surpasses that of data augmentation on three text classification datasets, using no more than half of the examples in the augmented dataset.
SAMSON: Sharpness-Aware Minimization Scaled by Outlier Normalization for Improving DNN Generalization and Robustness
In this work, we show that applying sharpness-aware training, by optimizing for both the loss value and loss sharpness, significantly improves robustness to noisy hardware at inference time without relying on any assumptions about the target hardware.
PatchBlender: A Motion Prior for Video Transformers
We show that our method is successful at enabling vision transformers to encode the temporal component of video data.
Local Structure Matters Most in Most Languages
In this work, we replicate a study on the importance of local structure, and the relative unimportance of global structure, in a multilingual setting.
Detecting Languages Unintelligible to Multilingual Models through Local Structure Probes
However, this transfer is not universal, with many languages not currently understood by multilingual approaches.
Segmentation of Multiple Sclerosis Lesions across Hospitals: Learn Continually or Train from Scratch?
Segmentation of Multiple Sclerosis (MS) lesions is a challenging problem.
Improving Meta-Learning Generalization with Activation-Based Early-Stopping
Specifically, we analyze the evolution, during meta-training, of the neural activations at each hidden layer, on a small set of unlabelled support examples from a single task of the target tasks distribution, as this constitutes a minimal and justifiably accessible information from the target problem.
An Introduction to Lifelong Supervised Learning
Following these different classes of learning algorithms, we discuss the commonly used evaluation benchmarks and metrics for lifelong learning (Chapter 6) and wrap up with a discussion of future challenges and important research directions in Chapter 7.
Towards Evaluating Adaptivity of Model-Based Reinforcement Learning Methods
We empirically validate these insights in the case of linear function approximation by demonstrating that a modified version of linear Dyna achieves effective adaptation to local changes.
Model-based Reinforcement Learning
reinforcement-learning
+1
Improving Sample Efficiency of Value Based Models Using Attention and Vision Transformers
Much of recent Deep Reinforcement Learning success is owed to the neural architecture's potential to learn and use effective internal representations of the world.
An Empirical Investigation of the Role of Pre-training in Lifelong Learning
The lifelong learning paradigm in machine learning is an attractive alternative to the more prominent isolated learning scheme not only due to its resemblance to biological learning but also its potential to reduce energy waste by obviating excessive model re-training.
Scaling Laws for the Few-Shot Adaptation of Pre-trained Image Classifiers
Empirical science of neural scaling laws is a rapidly growing area of significant importance to the future of machine learning, particularly in the light of recent breakthroughs achieved by large-scale pre-trained models such as GPT-3, CLIP and DALL-e.
Early-Stopping for Meta-Learning: Estimating Generalization from the Activation Dynamics
To this end, we empirically show that as meta-training progresses, a model's generalization to a target distribution of novel tasks can be estimated by analysing the dynamics of its neural activations.
Post-hoc Interpretability for Neural NLP: A Survey
Neural networks for NLP are becoming increasingly complex and widespread, and there is a growing concern if these models are responsible to use.
Local Structure Matters Most: Perturbation Study in NLU
Recent research analyzing the sensitivity of natural language understanding models to word-order perturbations has shown that neural models are surprisingly insensitive to the order of words.
Do Encoder Representations of Generative Dialogue Models Encode Sufficient Information about the Task ?
Predicting the next utterance in dialogue is contingent on encoding of users' input text to generate appropriate and relevant response in data-driven approaches.
A Brief Study on the Effects of Training Generative Dialogue Models with a Semantic loss
Neural models trained for next utterance generation in dialogue task learn to mimic the n-gram sequences in the training set with training objectives like negative log-likelihood (NLL) or cross-entropy.
Memory Augmented Optimizers for Deep Learning
Popular approaches for minimizing loss in data-driven learning often involve an abstraction or an explicit retention of the history of gradients for efficient parameter updates.
TAG: Task-based Accumulated Gradients for Lifelong learning
We also show that our method performs better than several state-of-the-art methods in lifelong learning on complex datasets with a large number of tasks.
A Survey of Data Augmentation Approaches for NLP
In this paper, we present a comprehensive and unifying survey of data augmentation for NLP by summarizing the literature in a structured manner.
Continuous Coordination As a Realistic Scenario for Lifelong Learning
Its large strategy space makes it a desirable environment for lifelong RL tasks.
Out-of-Distribution Classification and Clustering
This includes left out classes from the same dataset, as well as entire datasets never trained on.
IIRC: Incremental Implicitly-Refined Classification
We develop a standardized benchmark that enables evaluating models on the IIRC setup.
Maximum Reward Formulation In Reinforcement Learning
Reinforcement learning (RL) algorithms typically deal with maximizing the expected cumulative return (discounted or undiscounted, finite or infinite horizon).
MLMLM: Link Prediction with Mean Likelihood Masked Language Model
They however scale with man-hours and high-quality data.
Ranked #10 on
Link Prediction
on WN18RR
(using extra training data)
How To Evaluate Your Dialogue System: Probe Tasks as an Alternative for Token-level Evaluation Metrics
To bridge this gap in evaluation, we propose designing a set of probing tasks to evaluate dialogue models.
Slot Contrastive Networks: A Contrastive Approach for Representing Objects
Unsupervised extraction of objects from low-level visual data is an important goal for further progress in machine learning.
The LoCA Regret: A Consistent Metric to Evaluate Model-Based Behavior in Reinforcement Learning
For example, the common single-task sample-efficiency metric conflates improvements due to model-based learning with various other aspects, such as representation learning, making it difficult to assess true progress on model-based RL.
Model-based Reinforcement Learning
Reinforcement Learning (RL)
+1
Chaotic Continual Learning
Most proposed approaches for this issue try to compensate for the effects of parameter updates in the batch incremental setup in which the training model visits a lot of samples for several epochs.
PatchUp: A Feature-Space Block-Level Regularization Technique for Convolutional Neural Networks
Our approach improves the robustness of CNN models against the manifold intrusion problem that may occur in other state-of-the-art mixing approaches.
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.
Towards Lossless Encoding of Sentences
A lot of work has been done in the field of image compression via machine learning, but not much attention has been given to the compression of natural language.
Do Neural Dialog Systems Use the Conversation History Effectively? An Empirical Study
Neural generative models have been become increasingly popular when building conversational agents.
Structure Learning for Neural Module Networks
In current formulations of such networks only the parameters of the neural modules and/or the order of their execution is learned.
The Hanabi Challenge: A New Frontier for AI Research
From the early days of computing, games have been important testbeds for studying how well machines can do sophisticated decision making.
Towards Non-saturating Recurrent Units for Modelling Long-term Dependencies
Modelling long-term dependencies is a challenge for recurrent neural networks.
Environments for Lifelong Reinforcement Learning
To achieve general artificial intelligence, reinforcement learning (RL) agents should learn not only to optimize returns for one specific task but also to constantly build more complex skills and scaffold their knowledge about the world, without forgetting what has already been learned.
Towards Training Recurrent Neural Networks for Lifelong Learning
Both these models are proposed in the context of feedforward networks and we evaluate the feasibility of using them for recurrent networks.
Language Expansion In Text-Based Games
Text-based games are suitable test-beds for designing agents that can learn by interaction with the environment in the form of natural language text.
Complex Sequential Question Answering: Towards Learning to Converse Over Linked Question Answer Pairs with a Knowledge Graph
Further, unlike existing large scale QA datasets which contain simple questions that can be answered from a single tuple, the questions in our dialogs require a larger subgraph of the KG.
A Deep Reinforcement Learning Chatbot (Short Version)
We present MILABOT: a deep reinforcement learning chatbot developed by the Montreal Institute for Learning Algorithms (MILA) for the Amazon Alexa Prize competition.
A Deep Reinforcement Learning Chatbot
By applying reinforcement learning to crowdsourced data and real-world user interactions, the system has been trained to select an appropriate response from the models in its ensemble.
Memory Augmented Neural Networks with Wormhole Connections
We use discrete addressing for read/write operations which helps to substantially to reduce the vanishing gradient problem with very long sequences.
GuessWhat?! Visual object discovery through multi-modal dialogue
Our key contribution is the collection of a large-scale dataset consisting of 150K human-played games with a total of 800K visual question-answer pairs on 66K images.
Dynamic Neural Turing Machine with Soft and Hard Addressing Schemes
We investigate the mechanisms and effects of learning to read and write into a memory through experiments on Facebook bAbI tasks using both a feedforward and GRUcontroller.
Ranked #5 on
Question Answering
on bAbi
A Correlational Encoder Decoder Architecture for Pivot Based Sequence Generation
However, there is no parallel training data available between X and Y but, training data is available between X & Z and Z & Y (as is often the case in many real world applications).
Hierarchical Memory Networks
In this paper, we explore a form of hierarchical memory network, which can be considered as a hybrid between hard and soft attention memory networks.
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.
Bridge Correlational Neural Networks for Multilingual Multimodal Representation Learning
In this work, we address a real-world scenario where no direct parallel data is available between two views of interest (say, $V_1$ and $V_2$) but parallel data is available between each of these views and a pivot view ($V_3$).
TSEB: More Efficient Thompson Sampling for Policy Learning
In this paper, we propose TSEB, a Thompson Sampling based algorithm with adaptive exploration bonus that aims to solve the problem with tighter PAC guarantees, while being cautious on the regret as well.
Reasoning about Linguistic Regularities in Word Embeddings using Matrix Manifolds
In this paper, we introduce a new approach to capture analogies in continuous word representations, based on modeling not just individual word vectors, but rather the subspaces spanned by groups of words.
Clustering is Efficient for Approximate Maximum Inner Product Search
Efficient Maximum Inner Product Search (MIPS) is an important task that has a wide applicability in recommendation systems and classification with a large number of classes.
Correlational Neural Networks
CCA based approaches learn a joint representation by maximizing correlation of the views when projected to the common subspace.
