Search Results for author:
Found 575 papers, 294 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.
hBERT + BiasCorp - Fighting Racism on the Web
In this work, we present hBERT, where we modify certain layers of the pretrained BERT model with the new Hopfield Layer.
Towards DNA-Encoded Library Generation with GFlowNets
DNA-encoded libraries (DELs) are a powerful approach for rapidly screening large numbers of diverse compounds.
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).
Language Models Can Reduce Asymmetry in Information Markets
This work addresses the buyer's inspection paradox for information markets.
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.
Machine learning and information theory concepts towards an AI Mathematician
The current state-of-the-art in artificial intelligence is impressive, especially in terms of mastery of language, but not so much in terms of mathematical reasoning.
Discrete Probabilistic Inference as Control in Multi-path Environments
We consider the problem of sampling from a discrete and structured distribution as a sequential decision problem, where the objective is to find a stochastic policy such that objects are sampled at the end of this sequential process proportionally to some predefined reward.
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.
On diffusion models for amortized inference: Benchmarking and improving stochastic control and sampling
We study the problem of training diffusion models to sample from a distribution with a given unnormalized density or energy function.
Efficient Causal Graph Discovery Using Large Language Models
We propose a novel framework that leverages LLMs for full causal graph discovery.
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.
Improving Gradient-guided Nested Sampling for Posterior Inference
We present a performant, general-purpose gradient-guided nested sampling algorithm, ${\tt GGNS}$, combining the state of the art in differentiable programming, Hamiltonian slice sampling, clustering, mode separation, dynamic nested sampling, and parallelization.
Unlearning via Sparse Representations
Machine \emph{unlearning}, which involves erasing knowledge about a \emph{forget set} from a trained model, can prove to be costly and infeasible by existing techniques.
Mitigating Biases with Diverse Ensembles and Diffusion Models
Spurious correlations in the data, where multiple cues are predictive of the target labels, often lead to a phenomenon known as shortcut learning, where a model relies on erroneous, easy-to-learn cues while ignoring reliable ones.
SatBird: Bird Species Distribution Modeling with Remote Sensing and Citizen Science Data
The wide availability of remote sensing data and the growing adoption of citizen science tools to collect species observations data at low cost offer an opportunity for improving biodiversity monitoring and enabling the modelling of complex ecosystems.
Object-centric architectures enable efficient causal representation learning
Causal representation learning has showed a variety of settings in which we can disentangle latent variables with identifiability guarantees (up to some reasonable equivalence class).
OC-NMN: Object-centric Compositional Neural Module Network for Generative Visual Analogical Reasoning
A key aspect of human intelligence is the ability to imagine -- composing learned concepts in novel ways -- to make sense of new scenarios.
Managing AI Risks in an Era of Rapid Progress
In this short consensus paper, we outline risks from upcoming, advanced AI systems.
Causal machine learning for single-cell genomics
Advances in single-cell omics allow for unprecedented insights into the transcription profiles of individual cells.
Towards equilibrium molecular conformation generation with GFlowNets
Sampling diverse, thermodynamically feasible molecular conformations plays a crucial role in predicting properties of a molecule.
A cry for help: Early detection of brain injury in newborns
Since the 1960s, neonatal clinicians have known that newborns suffering from certain neurological conditions exhibit altered crying patterns such as the high-pitched cry in birth asphyxia.
PhyloGFN: Phylogenetic inference with generative flow networks
Phylogenetics is a branch of computational biology that studies the evolutionary relationships among biological entities.
On the importance of catalyst-adsorbate 3D interactions for relaxed energy predictions
The use of machine learning for material property prediction and discovery has traditionally centered on graph neural networks that incorporate the geometric configuration of all atoms.
Crystal-GFN: sampling crystals with desirable properties and constraints
Accelerating material discovery holds the potential to greatly help mitigate the climate crisis.
Amortizing intractable inference in large language models
Autoregressive large language models (LLMs) compress knowledge from their training data through next-token conditional distributions.
Pre-Training and Fine-Tuning Generative Flow Networks
However, as they are typically trained from a given extrinsic reward function, it remains an important open challenge about how to leverage the power of pre-training and train GFlowNets in an unsupervised fashion for efficient adaptation to downstream tasks.
Causal Inference in Gene Regulatory Networks with GFlowNet: Towards Scalability in Large Systems
Understanding causal relationships within Gene Regulatory Networks (GRNs) is essential for unraveling the gene interactions in cellular processes.
Local Search GFlowNets
Generative Flow Networks (GFlowNets) are amortized sampling methods that learn a distribution over discrete objects proportional to their rewards.
Learning to Scale Logits for Temperature-Conditional GFlowNets
We find that the challenge is greatly reduced if a learned function of the temperature is used to scale the policy's logits directly.
Expected flow networks in stochastic environments and two-player zero-sum games
Generative flow networks (GFlowNets) are sequential sampling models trained to match a given distribution.
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.
Discrete, compositional, and symbolic representations through attractor dynamics
Compositionality is an important feature of discrete symbolic systems, such as language and programs, as it enables them to have infinite capacity despite a finite symbol set.
Delta-AI: Local objectives for amortized inference in sparse graphical models
We present a new algorithm for amortized inference in sparse probabilistic graphical models (PGMs), which we call $\Delta$-amortized inference ($\Delta$-AI).
Leveraging Diffusion Disentangled Representations to Mitigate Shortcuts in Underspecified Visual Tasks
Spurious correlations in the data, where multiple cues are predictive of the target labels, often lead to shortcut learning phenomena, where a model may rely on erroneous, easy-to-learn, cues while ignoring reliable ones.
Consciousness-Inspired Spatio-Temporal Abstractions for Better Generalization in Reinforcement Learning
Inspired by human conscious planning, we propose Skipper, a model-based reinforcement learning framework utilizing spatio-temporal abstractions to generalize better in novel situations.
Tree Cross Attention
In this work, we propose Tree Cross Attention (TCA) - a module based on Cross Attention that only retrieves information from a logarithmic $\mathcal{O}(\log(N))$ number of tokens for performing inference.
Consciousness in Artificial Intelligence: Insights from the Science of Consciousness
From these theories we derive "indicator properties" of consciousness, elucidated in computational terms that allow us to assess AI systems for these properties.
Benchmarking Bayesian Causal Discovery Methods for Downstream Treatment Effect Estimation
Nevertheless, a notable gap exists in the evaluation of causal discovery methods, where insufficient emphasis is placed on downstream inference.
AI For Global Climate Cooperation 2023 Competition Proceedings
On the other hand, an interdisciplinary panel of human experts in law, policy, sociology, economics and environmental science, evaluated the solutions qualitatively.
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.
Generative Flow Networks: a Markov Chain Perspective
While Markov chain Monte Carlo methods (MCMC) provide a general framework to sample from a probability distribution defined up to normalization, they often suffer from slow convergence to the target distribution when the latter is highly multi-modal.
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.
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.
BatchGFN: Generative Flow Networks for Batch Active Learning
We introduce BatchGFN -- a novel approach for pool-based active learning that uses generative flow networks to sample sets of data points proportional to a batch reward.
Constant Memory Attention Block
Modern foundation model architectures rely on attention mechanisms to effectively capture context.
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.
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.
Cycle Consistency Driven Object Discovery
To tackle the second limitation, we apply the learned object-centric representations from the proposed method to two downstream reinforcement learning tasks, demonstrating considerable performance enhancements compared to conventional slot-based and monolithic representation learning methods.
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.
Spotlight Attention: Robust Object-Centric Learning With a Spatial Locality Prior
The aim of object-centric vision is to construct an explicit representation of the objects in a scene.
Attention Schema in Neural Agents
A strong prediction of this theory is that an agent can use its own AS to also infer the states of other agents' attention and consequently enhance coordination with other agents.
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.
Model evaluation for extreme risks
Current approaches to building general-purpose AI systems tend to produce systems with both beneficial and harmful capabilities.
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.
Memory Efficient Neural Processes via Constant Memory Attention Block
Neural Processes (NPs) are popular meta-learning methods for efficiently modelling predictive uncertainty.
FAENet: Frame Averaging Equivariant GNN for Materials Modeling
Applications of machine learning techniques for materials modeling typically involve functions known to be equivariant or invariant to specific symmetries.
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
Stochastic Generative Flow Networks
Generative Flow Networks (or GFlowNets for short) are a family of probabilistic agents that learn to sample complex combinatorial structures through the lens of "inference as control".
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.
Sources of Richness and Ineffability for Phenomenally Conscious States
Conscious states (states that there is something it is like to be in) seem both rich or full of detail, and ineffable or hard to fully describe or recall.
Distributional GFlowNets with Quantile Flows
Generative Flow Networks (GFlowNets) are a new family of probabilistic samplers where an agent learns a stochastic policy for generating complex combinatorial structure through a series of decision-making steps.
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.
Better Training of GFlowNets with Local Credit and Incomplete Trajectories
Generative Flow Networks or GFlowNets are related to Monte-Carlo Markov chain methods (as they sample from a distribution specified by an energy function), reinforcement learning (as they learn a policy to sample composed objects through a sequence of steps), generative models (as they learn to represent and sample from a distribution) and amortized variational methods (as they can be used to learn to approximate and sample from an otherwise intractable posterior, given a prior and a likelihood).
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.
GFlowNets for AI-Driven Scientific Discovery
However, in order to truly leverage large-scale data sets and high-throughput experimental setups, machine learning methods will need to be further improved and better integrated in the scientific discovery pipeline.
A theory of continuous generative flow networks
Generative flow networks (GFlowNets) are amortized variational inference algorithms that are trained to sample from unnormalized target distributions over compositional objects.
Leveraging the Third Dimension in Contrastive Learning
We evaluate these two approaches on three different SSL methods -- BYOL, SimSiam, and SwAV -- using ImageNette (10 class subset of ImageNet), ImageNet-100 and ImageNet-1k datasets.
Regeneration Learning: A Learning Paradigm for Data Generation
Regeneration learning extends the concept of representation learning to data generation tasks, and can be regarded as a counterpart of traditional representation learning, since 1) regeneration learning handles the abstraction (Y') of the target data Y for data generation while traditional representation learning handles the abstraction (X') of source data X for data understanding; 2) both the processes of Y'-->Y in regeneration learning and X-->X' in representation learning can be learned in a self-supervised way (e. g., pre-training); 3) both the mappings from X to Y' in regeneration learning and from X' to Y in representation learning are simpler than the direct mapping from X to Y.
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.
Synergies between Disentanglement and Sparsity: Generalization and Identifiability in Multi-Task Learning
Although disentangled representations are often said to be beneficial for downstream tasks, current empirical and theoretical understanding is limited.
PhAST: Physics-Aware, Scalable, and Task-specific GNNs for Accelerated Catalyst Design
Catalyst materials play a crucial role in the electrochemical reactions involved in numerous industrial processes key to this transition, such as renewable energy storage and electrofuel synthesis.
Latent Bottlenecked Attentive Neural Processes
We demonstrate that LBANPs can trade-off the computational cost and performance according to the number of latent vectors.
Equivariance with Learned Canonicalization Functions
Symmetry-based neural networks often constrain the architecture in order to achieve invariance or equivariance to a group of transformations.
Posterior samples of source galaxies in strong gravitational lenses with score-based priors
Inferring accurate posteriors for high-dimensional representations of the brightness of gravitationally-lensed sources is a major challenge, in part due to the difficulties of accurately quantifying the priors.
A General Purpose Neural Architecture for Geospatial Systems
Geospatial Information Systems are used by researchers and Humanitarian Assistance and Disaster Response (HADR) practitioners to support a wide variety of important applications.
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.
Consistent Training via Energy-Based GFlowNets for Modeling Discrete Joint Distributions
We hypothesize that this can lead to incompatibility between the inductive optimization biases in training $R$ and in training the GFlowNet, potentially leading to worse samples and slow adaptation to changes in the distribution.
Discrete Factorial Representations as an Abstraction for Goal Conditioned Reinforcement Learning
Goal-conditioned reinforcement learning (RL) is a promising direction for training agents that are capable of solving multiple tasks and reach a diverse set of objectives.
FL Games: A Federated Learning Framework for Distribution Shifts
Federated learning aims to train predictive models for data that is distributed across clients, under the orchestration of a server.
GFlowOut: Dropout with Generative Flow Networks
These methods face two important challenges: (a) the posterior distribution over masks can be highly multi-modal which can be difficult to approximate with standard variational inference and (b) it is not trivial to fully utilize sample-dependent information and correlation among dropout masks to improve posterior estimation.
Multi-Objective GFlowNets
We study the problem of generating diverse candidates in the context of Multi-Objective Optimization.
Toward Next-Generation Artificial Intelligence: Catalyzing the NeuroAI Revolution
Neuroscience has long been an essential driver of progress in artificial intelligence (AI).
Neural Attentive Circuits
Recent work has seen the development of general purpose neural architectures that can be trained to perform tasks across diverse data modalities.
Contrastive Retrospection: honing in on critical steps for rapid learning and generalization in RL
Distinct from other contemporary RL approaches to credit assignment, ConSpec takes advantage of the fact that it is easier to retrospectively identify the small set of steps that success is contingent upon (and ignoring other states) than it is to prospectively predict reward at every taken step.
Robust and Controllable Object-Centric Learning through Energy-based Models
Humans are remarkably good at understanding and reasoning about complex visual scenes.
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.
Generative Augmented Flow Networks
We specify intermediate rewards by intrinsic motivation to tackle the exploration problem in sparse reward environments.
Stateful active facilitator: Coordination and Environmental Heterogeneity in Cooperative Multi-Agent Reinforcement Learning
We formalize the notions of coordination level and heterogeneity level of an environment and present HECOGrid, a suite of multi-agent RL environments that facilitates empirical evaluation of different MARL approaches across different levels of coordination and environmental heterogeneity by providing a quantitative control over coordination and heterogeneity levels of the environment.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Latent State Marginalization as a Low-cost Approach for Improving Exploration
While the maximum entropy (MaxEnt) reinforcement learning (RL) framework -- often touted for its exploration and robustness capabilities -- is usually motivated from a probabilistic perspective, the use of deep probabilistic models has not gained much traction in practice due to their inherent complexity.
GFlowNets and variational inference
This paper builds bridges between two families of probabilistic algorithms: (hierarchical) variational inference (VI), which is typically used to model distributions over continuous spaces, and generative flow networks (GFlowNets), which have been used for distributions over discrete structures such as graphs.
Predictive Inference with Feature Conformal Prediction
Conformal prediction is a distribution-free technique for establishing valid prediction intervals.
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.
Interventional Causal Representation Learning
Can interventional data facilitate causal representation learning?
Graph-Based Active Machine Learning Method for Diverse and Novel Antimicrobial Peptides Generation and Selection
As antibiotic-resistant bacterial strains are rapidly spreading worldwide, infections caused by these strains are emerging as a global crisis causing the death of millions of people every year.
Designing Biological Sequences via Meta-Reinforcement Learning and Bayesian Optimization
The problem can be framed as a global optimization problem where the objective is an expensive black-box function such that we can query large batches restricted with a limitation of a low number of rounds.
Unifying Generative Models with GFlowNets and Beyond
Our framework provides a means for unifying training and inference algorithms, and provides a route to shine a unifying light over many generative models.
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.
Diversifying Design of Nucleic Acid Aptamers Using Unsupervised Machine Learning
Inverse design of short single-stranded RNA and DNA sequences (aptamers) is the task of finding sequences that satisfy a set of desired criteria.
Controlled Sparsity via Constrained Optimization or: How I Learned to Stop Tuning Penalties and Love Constraints
The performance of trained neural networks is robust to harsh levels of pruning.
Discrete Key-Value Bottleneck
Deep neural networks perform well on classification tasks where data streams are i. i. d.
Lookback for Learning to Branch
Given that B&B results in a tree of sub-MILPs, we ask (a) whether there are strong dependencies exhibited by the target heuristic among the neighboring nodes of the B&B tree, and (b) if so, whether we can incorporate them in our training procedure.
Your Autoregressive Generative Model Can be Better If You Treat It as an Energy-Based One
Autoregressive generative models are commonly used, especially for those tasks involving sequential data.
On the Generalization and Adaption Performance of Causal Models
Our analysis shows that the modular neural causal models outperform other models on both zero and few-shot adaptation in low data regimes and offer robust generalization.
On Neural Architecture Inductive Biases for Relational Tasks
Recent work has explored how forcing relational representations to remain distinct from sensory representations, as it seems to be the case in the brain, can help artificial systems.
Building Robust Ensembles via Margin Boosting
Consequently, an emerging line of work has focused on learning an ensemble of neural networks to defend against adversarial attacks.
Is a Modular Architecture Enough?
Inspired from human cognition, machine learning systems are gradually revealing advantages of sparser and more modular architectures.
Weakly Supervised Representation Learning with Sparse Perturbations
We show that if the perturbations are applied only on mutually exclusive blocks of latents, we identify the latents up to those blocks.
Agnostic Physics-Driven Deep Learning
This work establishes that a physical system can perform statistical learning without gradient computations, via an Agnostic Equilibrium Propagation (Aeqprop) procedure that combines energy minimization, homeostatic control, and nudging towards the correct response.
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.
FL Games: A federated learning framework for distribution shifts
Federated learning aims to train predictive models for data that is distributed across clients, under the orchestration of a server.
Coordinating Policies Among Multiple Agents via an Intelligent Communication Channel
In Multi-Agent Reinforcement Learning (MARL), specialized channels are often introduced that allow agents to communicate directly with one another.
Intelligent Communication
Multi-agent Reinforcement Learning
+2
FedILC: Weighted Geometric Mean and Invariant Gradient Covariance for Federated Learning on Non-IID Data
Federated learning is a distributed machine learning approach which enables a shared server model to learn by aggregating the locally-computed parameter updates with the training data from spatially-distributed client silos.
A Highly Adaptive Acoustic Model for Accurate Multi-Dialect Speech Recognition
In this paper, we propose a novel acoustic modeling technique for accurate multi-dialect speech recognition with a single AM.
Temporal Abstractions-Augmented Temporally Contrastive Learning: An Alternative to the Laplacian in RL
In reinforcement learning, the graph Laplacian has proved to be a valuable tool in the task-agnostic setting, with applications ranging from skill discovery to reward shaping.
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.
Continuous-Time Meta-Learning with Forward Mode Differentiation
Drawing inspiration from gradient-based meta-learning methods with infinitely small gradient steps, we introduce Continuous-Time Meta-Learning (COMLN), a meta-learning algorithm where adaptation follows the dynamics of a gradient vector field.
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.
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.
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.
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.
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.
Adaptive Discrete Communication Bottlenecks with Dynamic Vector Quantization
Vector Quantization (VQ) is a method for discretizing latent representations and has become a major part of the deep learning toolkit.
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.
Towards Scaling Difference Target Propagation by Learning Backprop Targets
As such, it is important to explore learning algorithms that come with strong theoretical guarantees and can match the performance of backpropagation (BP) on complex tasks.
Boosting Exploration in Multi-Task Reinforcement Learning using Adversarial Networks
Our proposed adversarial training regime for Multi-Task Reinforcement Learning (MT-RL) addresses the limitations of conventional training methods in RL, especially in meta-RL environments where the agent faces new tasks.
The Effect of Diversity in Meta-Learning
Recent studies show that task distribution plays a vital role in the meta-learner's performance.
Multi-Domain Balanced Sampling Improves Out-of-Distribution Generalization of Chest X-ray Pathology Prediction Models
Learning models that generalize under different distribution shifts in medical imaging has been a long-standing research challenge.
Multi-scale Feature Learning Dynamics: Insights for Double Descent
A key challenge in building theoretical foundations for deep learning is the complex optimization dynamics of neural networks, resulting from the high-dimensional interactions between the large number of network parameters.
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.
Properties from Mechanisms: An Equivariance Perspective on Identifiable Representation Learning
These results suggest that by exploiting inductive biases on mechanisms, it is possible to design a range of new identifiable representation learning approaches.
From Machine Learning to Robotics: Challenges and Opportunities for Embodied Intelligence
Machine learning has long since become a keystone technology, accelerating science and applications in a broad range of domains.
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.
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.
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
Dynamic Inference with Neural Interpreters
Modern neural network architectures can leverage large amounts of data to generalize well within the training distribution.
Unifying Likelihood-free Inference with Black-box Optimization and Beyond
Black-box optimization formulations for biological sequence design have drawn recent attention due to their promising potential impact on the pharmaceutical industry.
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.
Divide and Explore: Multi-Agent Separate Exploration with Shared Intrinsic Motivations
One of the greatest challenges of reinforcement learning is efficient exploration, especially when training signals are sparse or deceptive.
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.
Discrete-Valued Neural Communication
Deep learning has advanced from fully connected architectures to structured models organized into components, e. g., the transformer composed of positional elements, modular architectures divided into slots, and graph neural nets made up of nodes.
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.
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.
Variational Causal Networks: Approximate Bayesian Inference over Causal Structures
However, a crucial aspect to acting intelligently upon the knowledge about causal structure which has been inferred from finite data demands reasoning about its uncertainty.
Exploration-Driven Representation Learning in Reinforcement Learning
In this work, we introduce a method that explicitly couples representation learning with exploration when the agent is not provided with a uniform prior over the state space.
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.
SpeechBrain: A General-Purpose Speech Toolkit
SpeechBrain is an open-source and all-in-one speech toolkit.
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.
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
Fast and Slow Learning of Recurrent Independent Mechanisms
To study these ideas, we propose a particular training framework in which we assume that the pieces of knowledge an agent needs and its reward function are stationary and can be re-used across tasks.
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.
Comparative Study of Learning Outcomes for Online Learning Platforms
Personalization and active learning are key aspects to successful learning.
HBert + BiasCorp -- Fighting Racism on the Web
In this work, we present hBERT, where we modify certain layers of the pretrained BERT model with the new Hopfield Layer.
Neural Production Systems: Learning Rule-Governed Visual Dynamics
First, GNNs do not predispose interactions to be sparse, as relationships among independent entities are likely to be.
Coordination Among Neural Modules Through a Shared Global Workspace
We explore the use of such a communication channel in the context of deep learning for modeling the structure of complex environments.
Exploring the Wasserstein metric for survival analysis
Survival analysis is a type of semi-supervised task where the target output (the survival time) is often right-censored.
Transformers with Competitive Ensembles of Independent Mechanisms
In this work we explore a way in which the Transformer architecture is deficient: it represents each position with a large monolithic hidden representation and a single set of parameters which are applied over the entire hidden representation.
Towards Causal Representation Learning
The two fields of machine learning and graphical causality arose and developed separately.
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.
DEUP: Direct Epistemic Uncertainty Prediction
Epistemic Uncertainty is a measure of the lack of knowledge of a learner which diminishes with more evidence.
Structured Sparsity Inducing Adaptive Optimizers for Deep Learning
The parameters of a neural network are naturally organized in groups, some of which might not contribute to its overall performance.
Scaling Equilibrium Propagation to Deep ConvNets by Drastically Reducing its Gradient Estimator Bias
Equilibrium Propagation (EP) is a biologically-inspired counterpart of Backpropagation Through Time (BPTT) which, owing to its strong theoretical guarantees and the locality in space of its learning rule, fosters the design of energy-efficient hardware dedicated to learning.
Spatially Structured Recurrent Modules
Capturing the structure of a data-generating process by means of appropriate inductive biases can help in learning models that generalise well and are robust to changes in the input distribution.
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.
Neural Bayes: A Generic Parameterization Method for Unsupervised Learning
Disjoint Manifold Separation: Neural Bayes allows us to formulate an objective which can optimally label samples from disjoint manifolds present in the support of a continuous distribution.
Conditional Networks
In this work we tackle the problem of out-of-distribution generalization through conditional computation.
Factorizing Declarative and Procedural Knowledge in Structured, Dynamical Environments
To use a video game as an illustration, two enemies of the same type will share schemata but will have separate object files to encode their distinct state (e. g., health, position).
Systematic generalisation with group invariant predictions
We consider situations where the presence of dominant simpler correlations with the target variable in a training set can cause an SGD-trained neural network to be less reliant on more persistently-correlating complex features.
Meta Attention Networks: Meta-Learning Attention to Modulate Information Between Recurrent Independent Mechanisms
Decomposing knowledge into interchangeable pieces promises a generalization advantage when there are changes in distribution.
Dependency Structure Discovery from Interventions
Promising results have driven a recent surge of interest in continuous optimization methods for Bayesian network structure learning from observational data.
Machine Learning for Glacier Monitoring in the Hindu Kush Himalaya
Glacier mapping is key to ecological monitoring in the hkh region.
Untangling tradeoffs between recurrence and self-attention in artificial neural networks
Attention and self-attention mechanisms, are now central to state-of-the-art deep learning on sequential tasks.
Inductive Biases for Deep Learning of Higher-Level Cognition
A fascinating hypothesis is that human and animal intelligence could be explained by a few principles (rather than an encyclopedic list of heuristics).
RetroGNN: Approximating Retrosynthesis by Graph Neural Networks for De Novo Drug Design
A natural idea to mitigate this problem is to bias the search process towards more easily synthesizable molecules using a proxy for synthetic accessibility.
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
COVI-AgentSim: an Agent-based Model for Evaluating Methods of Digital Contact Tracing
The rapid global spread of COVID-19 has led to an unprecedented demand for effective methods to mitigate the spread of the disease, and various digital contact tracing (DCT) methods have emerged as a component of the solution.
Predicting Infectiousness for Proactive Contact Tracing
Predictions are used to provide personalized recommendations to the individual via an app, as well as to send anonymized messages to the individual's contacts, who use this information to better predict their own infectiousness, an approach we call proactive contact tracing (PCT).
NU-GAN: High resolution neural upsampling with GAN
In this paper, we propose NU-GAN, a new method for resampling audio from lower to higher sampling rates (upsampling).
Cross-Modal Information Maximization for Medical Imaging: CMIM
In hospitals, data are siloed to specific information systems that make the same information available under different modalities such as the different medical imaging exams the patient undergoes (CT scans, MRI, PET, Ultrasound, etc.)
Neural Function Modules with Sparse Arguments: A Dynamic Approach to Integrating Information across Layers
Feed-forward neural networks consist of a sequence of layers, in which each layer performs some processing on the information from the previous layer.
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.
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.
Visual Concept Reasoning Networks
It approximates sparsely connected networks by explicitly defining multiple branches to simultaneously learn representations with different visual concepts or properties.
Mastering Rate based Curriculum Learning
Recent automatic curriculum learning algorithms, and in particular Teacher-Student algorithms, rely on the notion of learning progress, making the assumption that the good next tasks are the ones on which the learner is making the fastest progress or digress.
Deriving Differential Target Propagation from Iterating Approximate Inverses
We show that a particular form of target propagation, i. e., relying on learned inverses of each layer, which is differential, i. e., where the target is a small perturbation of the forward propagation, gives rise to an update rule which corresponds to an approximate Gauss-Newton gradient-based optimization, without requiring the manipulation or inversion of large matrices.
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.
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 %.
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.
S2RMs: Spatially Structured Recurrent Modules
Capturing the structure of a data-generating process by means of appropriate inductive biases can help in learning models that generalize well and are robust to changes in the input distribution.
Compositional Generalization by Factorizing Alignment and Translation
Standard methods in deep learning for natural language processing fail to capture the compositional structure of human language that allows for systematic generalization outside of the training distribution.
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.
Object Files and Schemata: Factorizing Declarative and Procedural Knowledge in Dynamical Systems
To use a video game as an illustration, two enemies of the same type will share schemata but will have separate object files to encode their distinct state (e. g., health, position).
Hybrid Models for Learning to Branch
First, in a more realistic setting where only a CPU is available, is the GNN model still competitive?
Rethinking Distributional Matching Based Domain Adaptation
In this paper, in order to devise robust DA algorithms, we first systematically analyze the limitations of DM based methods, and then build new benchmarks with more realistic domain shifts to evaluate the well-accepted DM methods.
Image-to-image Mapping with Many Domains by Sparse Attribute Transfer
Unsupervised image-to-image translation consists of learning a pair of mappings between two domains without known pairwise correspondences between points.
HNHN: Hypergraph Networks with Hyperedge Neurons
Hypergraphs provide a natural representation for many real world datasets.
Untangling tradeoffs between recurrence and self-attention in neural networks
Attention and self-attention mechanisms, are now central to state-of-the-art deep learning on sequential tasks.
Learning Causal Models Online
One solution for achieving strong generalization is to incorporate causal structures in the models; such structures constrain learning by ignoring correlations that contradict them.
Scaling Equilibrium Propagation to Deep ConvNets by Drastically Reducing its Gradient Estimator Bias
In this work, we show that a bias in the gradient estimate of EP, inherent in the use of finite nudging, is responsible for this phenomenon and that cancelling it allows training deep ConvNets by EP.
Training End-to-End Analog Neural Networks with Equilibrium Propagation
We introduce a principled method to train end-to-end analog neural networks by stochastic gradient descent.
