Search Results for author:
Found 50 papers, 26 papers with code
LLMs for Literature Review: Are we there yet?
This paper explores the zero-shot abilities of recent Large Language Models (LLMs) in assisting with the writing of literature reviews based on an abstract.
Discovering Data Structures: Nearest Neighbor Search and Beyond
We also adapt our framework to the problem of estimating frequencies over a data stream, and believe it could also be a powerful discovery tool for new problems.
TEARS: Textual Representations for Scrutable Recommendations
We find the summaries capture user preferences uniquely.
Towards Modular LLMs by Building and Reusing a Library of LoRAs
The growing number of parameter-efficient adaptations of a base large language model (LLM) calls for studying whether we can reuse such trained adapters to improve performance for new tasks.
Integrating Present and Past in Unsupervised Continual Learning
We formulate a unifying framework for unsupervised continual learning (UCL), which disentangles learning objectives that are specific to the present and the past data, encompassing stability, plasticity, and cross-task consolidation.
LitLLM: A Toolkit for Scientific Literature Review
Conducting literature reviews for scientific papers is essential for understanding research, its limitations, and building on existing work.
Improving the generalizability and robustness of large-scale traffic signal control
Building upon the state-of-the-art previous model which uses a decentralized approach for large-scale traffic signal control with graph convolutional networks (GCNs), we first learn models using a distributional reinforcement learning (DisRL) approach.
Deep Reinforcement Learning
Distributional Reinforcement Learning
+5
Towards Compute-Optimal Transfer Learning
The field of transfer learning is undergoing a significant shift with the introduction of large pretrained models which have demonstrated strong adaptability to a variety of downstream tasks.
Bayesian learning of Causal Structure and Mechanisms with GFlowNets and Variational Bayes
We extend the method of Bayesian causal structure learning using GFlowNets to learn not only the posterior distribution over the structure, but also the parameters of a linear-Gaussian model.
Model-based graph reinforcement learning for inductive traffic signal control
Most reinforcement learning methods for adaptive-traffic-signal-control require training from scratch to be applied on any new intersection or after any modification to the road network, traffic distribution, or behavioral constraints experienced during training.
Challenging Common Assumptions about Catastrophic Forgetting
In this paper, we study the progressive knowledge accumulation (KA) in DNNs trained with gradient-based algorithms in long sequences of tasks with data re-occurrence.
Learning To Cut By Looking Ahead: Cutting Plane Selection via Imitation Learning
Cutting planes are essential for solving mixed-integer linear problems (MILPs), because they facilitate bound improvements on the optimal solution value.
Task-Agnostic Continual Reinforcement Learning: Gaining Insights and Overcoming Challenges
We pose two hypotheses: (1) task-agnostic methods might provide advantages in settings with limited data, computation, or high dimensionality, and (2) faster adaptation may be particularly beneficial in continual learning settings, helping to mitigate the effects of catastrophic forgetting.
Continual Learning with Foundation Models: An Empirical Study of Latent Replay
Motivated by this, we study the efficacy of pre-trained vision models as a foundation for downstream continual learning (CL) scenarios.
The Machine Learning for Combinatorial Optimization Competition (ML4CO): Results and Insights
Combinatorial optimization is a well-established area in operations research and computer science.
A New Era: Intelligent Tutoring Systems Will Transform Online Learning for Millions
AI-powered learning can provide millions of learners with a highly personalized, active and practical learning experience, which is key to successful learning.
Continual Learning via Local Module Composition
We introduce local module composition (LMC), an approach to modular CL where each module is provided a local structural component that estimates a module's relevance to the input.
Sequoia: A Software Framework to Unify Continual Learning Research
We propose a taxonomy of settings, where each setting is described as a set of assumptions.
Pretraining Representations for Data-Efficient Reinforcement Learning
Data efficiency is a key challenge for deep reinforcement learning.
Ranked #3 on
Atari Games 100k
on Atari 100k
(using extra training data)
Comparative Study of Learning Outcomes for Online Learning Platforms
Personalization and active learning are key aspects to successful learning.
Beyond Trivial Counterfactual Explanations with Diverse Valuable Explanations
Explainability for machine learning models has gained considerable attention within the research community given the importance of deploying more reliable machine-learning systems.
Pretraining Reward-Free Representations for Data-Efficient Reinforcement Learning
Data efficiency poses a major challenge for deep reinforcement learning.
Beyond Trivial Counterfactual Generations with Diverse Valuable Explanations
In computer vision applications, most methods explain models by displaying the regions in the input image that they focus on for their prediction, but it is difficult to improve models based on these explanations since they do not indicate why the model fail.
Online Fast Adaptation and Knowledge Accumulation (OSAKA): a New Approach to Continual Learning
The main challenge is that the agent must not forget previous tasks and also adapt to novel tasks in the stream.
Multi-XScience: A Large-scale Dataset for Extreme Multi-document Summarization of Scientific Articles
Multi-document summarization is a challenging task for which there exists little large-scale datasets.
Synbols: Probing Learning Algorithms with Synthetic Datasets
Progress in the field of machine learning has been fueled by the introduction of benchmark datasets pushing the limits of existing algorithms.
A Large-Scale, Open-Domain, Mixed-Interface Dialogue-Based ITS for STEM
We present Korbit, a large-scale, open-domain, mixed-interface, dialogue-based intelligent tutoring system (ITS).
Online Fast Adaptation and Knowledge Accumulation: a New Approach to Continual Learning
We propose Continual-MAML, an online extension of the popular MAML algorithm as a strong baseline for this scenario.
IG-RL: Inductive Graph Reinforcement Learning for Massive-Scale Traffic Signal Control
We compare IG-RL to multi-agent reinforcement learning and domain-specific baselines.
Multi-agent Reinforcement Learning
reinforcement-learning
+3
Online Continual Learning with Maximal Interfered Retrieval
Methods based on replay, either generative or from a stored memory, have been shown to be effective approaches for continual learning, matching or exceeding the state of the art in a number of standard benchmarks.
Online Continual Learning with Maximally Interfered Retrieval
Methods based on replay, either generative or from a stored memory, have been shown to be effective approaches for continual learning, matching or exceeding the state of the art in a number of standard benchmarks.
Exact Combinatorial Optimization with Graph Convolutional Neural Networks
Combinatorial optimization problems are typically tackled by the branch-and-bound paradigm.
Continual Learning of New Sound Classes using Generative Replay
We show that by incrementally refining a classifier with generative replay a generator that is 4% of the size of all previous training data matches the performance of refining the classifier keeping 20% of all previous training data.
Session-based Social Recommendation via Dynamic Graph Attention Networks
However, recommendation in online communities is a challenging problem: 1) users' interests are dynamic, and 2) users are influenced by their friends.
Ranked #1 on
Recommendation Systems
on Douban
(NDCG metric)
Towards Deep Conversational Recommendations
There has been growing interest in using neural networks and deep learning techniques to create dialogue systems.
Language GANs Falling Short
Generating high-quality text with sufficient diversity is essential for a wide range of Natural Language Generation (NLG) tasks.
The Deconfounded Recommender: A Causal Inference Approach to Recommendation
To this end, we develop a causal approach to recommendation, one where watching a movie is a "treatment" and a user's rating is an "outcome."
Focused Hierarchical RNNs for Conditional Sequence Processing
We evaluate this method on several types of tasks with different attributes.
Ranked #3 on
Open-Domain Question Answering
on SearchQA
(Unigram Acc metric)
Sparse Attentive Backtracking: Long-Range Credit Assignment in Recurrent Networks
A major drawback of backpropagation through time (BPTT) is the difficulty of learning long-term dependencies, coming from having to propagate credit information backwards through every single step of the forward computation.
Learnable Explicit Density for Continuous Latent Space and Variational Inference
In this paper, we study two aspects of the variational autoencoder (VAE): the prior distribution over the latent variables and its corresponding posterior.
Training End-to-End Dialogue Systems with the Ubuntu Dialogue Corpus
In this paper, we analyze neural network-based dialogue systems trained in an end-to-end manner using an updated version of the recent Ubuntu Dialogue Corpus, a dataset containing almost 1 million multi-turn dialogues, with a total of over 7 million utterances and 100 million words.
Generative Deep Neural Networks for Dialogue: A Short Review
Researchers have recently started investigating deep neural networks for dialogue applications.
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.
On the Evaluation of Dialogue Systems with Next Utterance Classification
An open challenge in constructing dialogue systems is developing methods for automatically learning dialogue strategies from large amounts of unlabelled data.
How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation
We investigate evaluation metrics for dialogue response generation systems where supervised labels, such as task completion, are not available.
A Survey of Available Corpora for Building Data-Driven Dialogue Systems
During the past decade, several areas of speech and language understanding have witnessed substantial breakthroughs from the use of data-driven models.
Modeling User Exposure in Recommendation
The exposure is modeled as a latent variable and the model infers its value from data.
Dynamic Poisson Factorization
Models for recommender systems use latent factors to explain the preferences and behaviors of users with respect to a set of items (e. g., movies, books, academic papers).
Content-based recommendations with Poisson factorization
We develop collaborative topic Poisson factorization (CTPF), a generative model of articles and reader preferences.
Deep Exponential Families
We describe \textit{deep exponential families} (DEFs), a class of latent variable models that are inspired by the hidden structures used in deep neural networks.
