Search Results for author:
Found 205 papers, 72 papers with code
POINTS1.5: Building a Vision-Language Model towards Real World Applications
Due to the scarcity of open-source Chinese datasets for vision-language models, we collect numerous images from the Internet and annotate them using a combination of manual and automatic methods.
Money Burning Improves Mediated Communication
This paper explores the problem of mediated communication enhanced by money-burning tactics for commitment power.
Universal and Context-Independent Triggers for Precise Control of LLM Outputs
Large language models (LLMs) have been widely adopted in applications such as automated content generation and even critical decision-making systems.
Stable Continual Reinforcement Learning via Diffusion-based Trajectory Replay
Given the inherent non-stationarity prevalent in real-world applications, continual Reinforcement Learning (RL) aims to equip the agent with the capability to address a series of sequentially presented decision-making tasks.
WHALE: Towards Generalizable and Scalable World Models for Embodied Decision-making
Incorporating these two techniques, we present Whale-ST, a scalable spatial-temporal transformer-based world model with enhanced generalizability.
MPT: A Large-scale Multi-Phytoplankton Tracking Benchmark
Phytoplankton are a crucial component of aquatic ecosystems, and effective monitoring of them can provide valuable insights into ocean environments and ecosystem changes.
LLMOPT: Learning to Define and Solve General Optimization Problems from Scratch
Namely, the accuracy of most current LLM-based methods and the generality of optimization problem types that they can model are still limited.
ZipGait: Bridging Skeleton and Silhouette with Diffusion Model for Advancing Gait Recognition
Current gait recognition research predominantly focuses on extracting appearance features effectively, but the performance is severely compromised by the vulnerability of silhouettes under unconstrained scenes.
TS-SAM: Fine-Tuning Segment-Anything Model for Downstream Tasks
Adapter based fine-tuning has been studied for improving the performance of SAM on downstream tasks.
Energy-Guided Diffusion Sampling for Offline-to-Online Reinforcement Learning
Combining offline and online reinforcement learning (RL) techniques is indeed crucial for achieving efficient and safe learning where data acquisition is expensive.
UnmixingSR: Material-aware Network with Unsupervised Unmixing as Auxiliary Task for Hyperspectral Image Super-resolution
We regard HU as an auxiliary task and incorporate it into the HSI SR process by exploring the constraints between LR and HR abundances.
Hindsight Preference Learning for Offline Preference-based Reinforcement Learning
Offline preference-based reinforcement learning (RL), which focuses on optimizing policies using human preferences between pairs of trajectory segments selected from an offline dataset, has emerged as a practical avenue for RL applications.
Q-Adapter: Customizing Pre-trained LLMs to New Preferences with Forgetting Mitigation
Thanks to the residual Q-learning framework, we can restore the customized LLM with the pre-trained LLM and the \emph{residual Q-function} without the reward function $r_1$.
Improving Sample Efficiency of Reinforcement Learning with Background Knowledge from Large Language Models
In this paper, we introduce a framework that harnesses LLMs to extract background knowledge of an environment, which contains general understandings of the entire environment, making various downstream RL tasks benefit from one-time knowledge representation.
PhyTracker: An Online Tracker for Phytoplankton
Phytoplankton, a crucial component of aquatic ecosystems, requires efficient monitoring to understand marine ecological processes and environmental conditions.
BWArea Model: Learning World Model, Inverse Dynamics, and Policy for Controllable Language Generation
In a similar vein, our proposed system, the BWArea model, conceptualizes language generation as a decision-making task.
Any-step Dynamics Model Improves Future Predictions for Online and Offline Reinforcement Learning
In the online setting, ADMPO-ON demonstrates improved sample efficiency compared to previous state-of-the-art methods.
Efficient Recurrent Off-Policy RL Requires a Context-Encoder-Specific Learning Rate
Recent progress has demonstrated that recurrent reinforcement learning (RL), which consists of a context encoder based on recurrent neural networks (RNNs) for unobservable state prediction and a multilayer perceptron (MLP) policy for decision making, can mitigate partial observability and serve as a robust baseline for POMDP tasks.
Knowledgeable Agents by Offline Reinforcement Learning from Large Language Model Rollouts
Furthermore, KALM effectively enables the LLM to comprehend environmental dynamics, resulting in the generation of meaningful imaginary rollouts that reflect novel skills and demonstrate the seamless integration of large language models and reinforcement learning.
SceneTracker: Long-term Scene Flow Estimation Network
Considering the complementarity of scene flow estimation in the spatial domain's focusing capability and 3D object tracking in the temporal domain's coherence, this study aims to address a comprehensive new task that can simultaneously capture fine-grained and long-term 3D motion in an online manner: long-term scene flow estimation (LSFE).
Disentangling Policy from Offline Task Representation Learning via Adversarial Data Augmentation
Specifically, the objective of adversarial data augmentation is not merely to generate data analogous to offline data distribution; instead, it aims to create adversarial examples designed to confound learned task representations and lead to incorrect task identification.
Debiased Offline Representation Learning for Fast Online Adaptation in Non-stationary Dynamics
DORA incorporates an information bottleneck principle that maximizes mutual information between the dynamics encoding and the environmental data, while minimizing mutual information between the dynamics encoding and the actions of the behavior policy.
Learning by Doing: An Online Causal Reinforcement Learning Framework with Causal-Aware Policy
As a key component to intuitive cognition and reasoning solutions in human intelligence, causal knowledge provides great potential for reinforcement learning (RL) agents' interpretability towards decision-making by helping reduce the searching space.
Empowering Language Models with Active Inquiry for Deeper Understanding
The rise of large language models (LLMs) has revolutionized the way that we interact with artificial intelligence systems through natural language.
Towards an Information Theoretic Framework of Context-Based Offline Meta-Reinforcement Learning
As demonstrations, we propose a supervised and a self-supervised implementation of $I(Z; M)$, and empirically show that the corresponding optimization algorithms exhibit remarkable generalization across a broad spectrum of RL benchmarks, context shift scenarios, data qualities and deep learning architectures.
FedGT: Federated Node Classification with Scalable Graph Transformer
However, existing methods have the following limitations: (1) The links between local subgraphs are missing in subgraph federated learning.
Beimingwu: A Learnware Dock System
The learnware paradigm proposed by Zhou [2016] aims to enable users to reuse numerous existing well-trained models instead of building machine learning models from scratch, with the hope of solving new user tasks even beyond models' original purposes.
Unmixing Before Fusion: A Generalized Paradigm for Multi-Source-based Hyperspectral Image Synthesis
By integrating unmixing this work maps unpaired HSI and RGB data to a low-dimensional abundance space greatly alleviating the difficulty of generating high-dimensional samples.
Generalizable Task Representation Learning for Offline Meta-Reinforcement Learning with Data Limitations
GENTLE employs Task Auto-Encoder~(TAE), which is an encoder-decoder architecture to extract the characteristics of the tasks.
Episodic Return Decomposition by Difference of Implicitly Assigned Sub-Trajectory Reward
Real-world decision-making problems are usually accompanied by delayed rewards, which affects the sample efficiency of Reinforcement Learning, especially in the extremely delayed case where the only feedback is the episodic reward obtained at the end of an episode.
Policy Optimization in RLHF: The Impact of Out-of-preference Data
These methods, either explicitly or implicitly, learn a reward model from preference data and differ in the data used for policy optimization to unlock the generalization ability of the reward model.
Efficient Human-AI Coordination via Preparatory Language-based Convention
Developing intelligent agents capable of seamless coordination with humans is a critical step towards achieving artificial general intelligence.
ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models
ReMax can save about 46% GPU memory than PPO when training a 7B model and enables training on A800-80GB GPUs without the memory-saving offloading technique needed by PPO.
AdaptSSR: Pre-training User Model with Augmentation-Adaptive Self-Supervised Ranking
Specifically, we adopt a multiple pairwise ranking loss which trains the user model to capture the similarity orders between the implicitly augmented view, the explicitly augmented view, and views from other users.
Reward-Consistent Dynamics Models are Strongly Generalizable for Offline Reinforcement Learning
MOREC learns a generalizable dynamics reward function from offline data, which is subsequently employed as a transition filter in any offline MBRL method: when generating transitions, the dynamics model generates a batch of transitions and selects the one with the highest dynamics reward value.
Imitator Learning: Achieve Out-of-the-Box Imitation Ability in Variable Environments
In this work, we focus on imitator learning based on only one expert demonstration.
Improve the efficiency of deep reinforcement learning through semantic exploration guided by natural language
We assume that the interaction can be modeled as a sequence of templated questions and answers, and that there is a large corpus of previous interactions available.
ACT: Empowering Decision Transformer with Dynamic Programming via Advantage Conditioning
Third, we train an Advantage-Conditioned Transformer (ACT) to generate actions conditioned on the estimated advantages.
Hide and Seek (HaS): A Lightweight Framework for Prompt Privacy Protection
Numerous companies have started offering services based on large language models (LLM), such as ChatGPT, which inevitably raises privacy concerns as users' prompts are exposed to the model provider.
Sensiverse: A dataset for ISAC study
In order to address the lack of applicable channel models for ISAC research and evaluation, we release Sensiverse, a dataset that can be used for ISAC research.
Synergistic Signal Denoising for Multimodal Time Series of Structure Vibration
Structural Health Monitoring (SHM) plays an indispensable role in ensuring the longevity and safety of infrastructure.
Transformer-Based Denoising of Mechanical Vibration Signals
Mechanical vibration signal denoising is a pivotal task in various industrial applications, including system health monitoring and failure prediction.
Disentangling Multi-view Representations Beyond Inductive Bias
In this paper, we propose a novel multi-view representation disentangling method that aims to go beyond inductive biases, ensuring both interpretability and generalizability of the resulting representations.
Car-Studio: Learning Car Radiance Fields from Single-View and Endless In-the-wild Images
However, previous studies learned within a sequence of autonomous driving datasets, resulting in unsatisfactory blurring when rotating the car in the simulator.
Model-Bellman Inconsistency for Model-based Offline Reinforcement Learning
MOBILE conducts uncertainty quantification through the inconsistency of Bellman estimations under an ensemble of learned dynamics models, which can be a better approximator to the true Bellman error, and penalizes the Bellman estimation based on this uncertainty.
A Unified View of Deep Learning for Reaction and Retrosynthesis Prediction: Current Status and Future Challenges
Reaction and retrosynthesis prediction are fundamental tasks in computational chemistry that have recently garnered attention from both the machine learning and drug discovery communities.
SplatFlow: Learning Multi-frame Optical Flow via Splatting
The occlusion problem remains a crucial challenge in optical flow estimation (OFE).
NPVForensics: Jointing Non-critical Phonemes and Visemes for Deepfake Detection
Next, we design a phoneme-viseme awareness module for cross-modal feature fusion and representation alignment, so that the modality gap can be reduced and the intrinsic complementarity of the two modalities can be better explored.
Policy Regularization with Dataset Constraint for Offline Reinforcement Learning
A common taxonomy of existing offline RL works is policy regularization, which typically constrains the learned policy by distribution or support of the behavior policy.
Provably Efficient Adversarial Imitation Learning with Unknown Transitions
Adversarial imitation learning (AIL), a subset of IL methods, is particularly promising, but its theoretical foundation in the presence of unknown transitions has yet to be fully developed.
Doubly Stochastic Graph-based Non-autoregressive Reaction Prediction
However, the current non-autoregressive decoder does not satisfy two essential rules of electron redistribution modeling simultaneously: the electron-counting rule and the symmetry rule.
Language Model Self-improvement by Reinforcement Learning Contemplation
We demonstrate that SIRLC can be applied to various NLP tasks, such as reasoning problems, text generation, and machine translation.
Robust multi-agent coordination via evolutionary generation of auxiliary adversarial attackers
Concretely, to avoid the ego-system overfitting to a specific attacker, we maintain a set of attackers, which is optimized to guarantee the attackers high attacking quality and behavior diversity.
Communication-Robust Multi-Agent Learning by Adaptable Auxiliary Multi-Agent Adversary Generation
In specific, we introduce a novel message-attacking approach that models the learning of the auxiliary attacker as a cooperative problem under a shared goal to minimize the coordination ability of the ego system, with which every information channel may suffer from distinct message attacks.
Multi-agent Continual Coordination via Progressive Task Contextualization
Towards tackling the mentioned issue, this paper proposes an approach Multi-Agent Continual Coordination via Progressive Task Contextualization, dubbed MACPro.
Robust Multi-agent Communication via Multi-view Message Certification
Many multi-agent scenarios require message sharing among agents to promote coordination, hastening the robustness of multi-agent communication when policies are deployed in a message perturbation environment.
Sim2Rec: A Simulator-based Decision-making Approach to Optimize Real-World Long-term User Engagement in Sequential Recommender Systems
However, building a user simulator with no reality-gap, i. e., can predict user's feedback exactly, is unrealistic because the users' reaction patterns are complex and historical logs for each user are limited, which might mislead the simulator-based recommendation policy.
Adaptive Negative Evidential Deep Learning for Open-set Semi-supervised Learning
Open-set semi-supervised learning (Open-set SSL) considers a more practical scenario, where unlabeled data and test data contain new categories (outliers) not observed in labeled data (inliers).
Beware of Instantaneous Dependence in Reinforcement Learning
Playing an important role in Model-Based Reinforcement Learning (MBRL), environment models aim to predict future states based on the past.
Model-based Reinforcement Learning
reinforcement-learning
+2
How To Guide Your Learner: Imitation Learning with Active Adaptive Expert Involvement
In this paper, we propose a novel active imitation learning framework based on a teacher-student interaction model, in which the teacher's goal is to identify the best teaching behavior and actively affect the student's learning process.
Uncertainty Estimation by Fisher Information-based Evidential Deep Learning
To address this problem, we propose a novel method, Fisher Information-based Evidential Deep Learning ($\mathcal{I}$-EDL).
Efficient Communication via Self-supervised Information Aggregation for Online and Offline Multi-agent Reinforcement Learning
We also release the built offline benchmarks in this paper as a testbed for communication ability validation to facilitate further future research.
Natural Language-conditioned Reinforcement Learning with Inside-out Task Language Development and Translation
To ease the learning burden of the policy, we investigate an inside-out scheme for natural language-conditioned RL by developing a task language (TL) that is task-related and unique.
Theoretical Analysis of Offline Imitation With Supplementary Dataset
This paper considers a situation where, besides the small amount of expert data, a supplementary dataset is available, which can be collected cheaply from sub-optimal policies.
A Clustering-guided Contrastive Fusion for Multi-view Representation Learning
To this end, we utilize a deep fusion network to fuse view-specific representations into the view-common representation, extracting high-level semantics for obtaining robust representation.
Untargeted Attack against Federated Recommendation Systems via Poisonous Item Embeddings and the Defense
Experiments on two public datasets show that ClusterAttack can effectively degrade the performance of FedRec systems while circumventing many defense methods, and UNION can improve the resistance of the system against various untargeted attacks, including our ClusterAttack.
Momentum Calibration for Text Generation
The input and output of most text generation tasks can be transformed to two sequences of tokens and they can be modeled using sequence-to-sequence learning modeling tools such as Transformers.
Ranked #3 on
Text Summarization
on SAMSum
Learning Physically Realizable Skills for Online Packing of General 3D Shapes
We study the problem of learning online packing skills for irregular 3D shapes, which is arguably the most challenging setting of bin packing problems.
Real-time Blind Deblurring Based on Lightweight Deep-Wiener-Network
In this paper, we address the problem of blind deblurring with high efficiency.
Does Debiasing Inevitably Degrade the Model Performance
We use our theoretical framework to explain why the current debiasing methods cause performance degradation.
Knowledge is Power: Understanding Causality Makes Legal judgment Prediction Models More Generalizable and Robust
To validate our theoretical analysis, we further propose another method using our proposed Causality-Aware Self-Attention Mechanism (CASAM) to guide the model to learn the underlying causality knowledge in legal texts.
Semantic Structure Enhanced Contrastive Adversarial Hash Network for Cross-media Representation Learning
Secondly, for further improving learning ability of implicit cross-media semantic associations, a semantic label association graph is constructed, and the graph convolutional network is utilized to mine the implicit semantic structures, thus guiding learning of discriminative features of different modalities.
Domain generalization Person Re-identification on Attention-aware multi-operation strategery
Domain generalization person re-identification (DG Re-ID) aims to directly deploy a model trained on the source domain to the unseen target domain with good generalization, which is a challenging problem and has practical value in a real-world deployment.
Multi-agent Dynamic Algorithm Configuration
MA-DAC formulates the dynamic configuration of a complex algorithm with multiple types of hyperparameters as a contextual multi-agent Markov decision process and solves it by a cooperative multi-agent RL (MARL) algorithm.
Understanding or Manipulation: Rethinking Online Performance Gains of Modern Recommender Systems
The increase in the measured performance, however, can have two possible attributions: a better understanding of user preferences, and a more proactive ability to utilize human bounded rationality to seduce user over-consumption.
MARS: A Motif-based Autoregressive Model for Retrosynthesis Prediction
In this paper, we propose a novel end-to-end graph generation model for retrosynthesis prediction, which sequentially identifies the reaction center, generates the synthons, and adds motifs to the synthons to generate reactants.
Ranked #2 on
Single-step retrosynthesis
on USPTO-50k
On Efficient Reinforcement Learning for Full-length Game of StarCraft II
In this work, we investigate a set of RL techniques for the full-length game of StarCraft II.
WeLM: A Well-Read Pre-trained Language Model for Chinese
Large Language Models pre-trained with self-supervised learning have demonstrated impressive zero-shot generalization capabilities on a wide spectrum of tasks.
ImDrug: A Benchmark for Deep Imbalanced Learning in AI-aided Drug Discovery
The last decade has witnessed a prosperous development of computational methods and dataset curation for AI-aided drug discovery (AIDD).
Model-based Reinforcement Learning with Multi-step Plan Value Estimation
The new model-based reinforcement learning algorithm MPPVE (Model-based Planning Policy Learning with Multi-step Plan Value Estimation) shows a better utilization of the learned model and achieves a better sample efficiency than state-of-the-art model-based RL approaches.
Model-based Reinforcement Learning
reinforcement-learning
+2
Deep Anomaly Detection and Search via Reinforcement Learning
Semi-supervised Anomaly Detection (AD) is a kind of data mining task which aims at learning features from partially-labeled datasets to help detect outliers.
MORI-RAN: Multi-view Robust Representation Learning via Hybrid Contrastive Fusion
To this end, in this paper, we proposed a hybrid contrastive fusion algorithm to extract robust view-common representation from unlabeled data.
Convolutional Neural Networks with A Topographic Representation Module for EEG-Based Brain-Computer Interfaces
Significance: We improve the classification performance of 3 CNNs on 2 datasets by the use of TRM, indicating that it has the capability to mine the EEG spatial topological information.
Unified Policy Optimization for Continuous-action Reinforcement Learning in Non-stationary Tasks and Games
This paper addresses policy learning in non-stationary environments and games with continuous actions.
Heterogeneous Multi-agent Zero-Shot Coordination by Coevolution
Generating agents that can achieve zero-shot coordination (ZSC) with unseen partners is a new challenge in cooperative multi-agent reinforcement learning (MARL).
Understanding Adversarial Imitation Learning in Small Sample Regime: A Stage-coupled Analysis
Imitation learning learns a policy from expert trajectories.
Pseudo-label Guided Cross-video Pixel Contrast for Robotic Surgical Scene Segmentation with Limited Annotations
Concretely, for trusty representation learning, we propose to incorporate pseudo labels to instruct the pair selection, obtaining more reliable representation pairs for pixel contrast.
A Survey on Model-based Reinforcement Learning
In this survey, we take a review of MBRL with a focus on the recent progress in deep RL.
Hybrid Value Estimation for Off-policy Evaluation and Offline Reinforcement Learning
Value function estimation is an indispensable subroutine in reinforcement learning, which becomes more challenging in the offline setting.
Offline Reinforcement Learning with Causal Structured World Models
Model-based methods have recently shown promising for offline reinforcement learning (RL), aiming to learn good policies from historical data without interacting with the environment.
Transferable Reward Learning by Dynamics-Agnostic Discriminator Ensemble
In this work, we present a dynamics-agnostic discriminator-ensemble reward learning method (DARL) within the AIL framework, capable of learning both state-action and state-only reward functions.
Model Generation with Provable Coverability for Offline Reinforcement Learning
Model-based offline optimization with dynamics-aware policy provides a new perspective for policy learning and out-of-distribution generalization, where the learned policy could adapt to different dynamics enumerated at the training stage.
Exploring Intra- and Inter-Video Relation for Surgical Semantic Scene Segmentation
Automatic surgical scene segmentation is fundamental for facilitating cognitive intelligence in the modern operating theatre.
Enhancing Neural Mathematical Reasoning by Abductive Combination with Symbolic Library
On a mathematical reasoning dataset, we adopt the recently proposed abductive learning framework, and propose the ABL-Sym algorithm that combines the Transformer neural models with a symbolic mathematics library.
A Note on Target Q-learning For Solving Finite MDPs with A Generative Oracle
In particular, we demonstrate that the sample complexity of the target Q-learning algorithm in [Lee and He, 2020] is $\widetilde{\mathcal O}(|\mathcal S|^2|\mathcal A|^2 (1-\gamma)^{-5}\varepsilon^{-2})$.
Multi-Agent Policy Transfer via Task Relationship Modeling
We demonstrate that the task representation can capture the relationship among tasks, and can generalize to unseen tasks.
Attentive Temporal Pooling for Conformer-based Streaming Language Identification in Long-form Speech
In this paper, we introduce a novel language identification system based on conformer layers.
Rethinking ValueDice: Does It Really Improve Performance?
First, we show that ValueDice could reduce to BC under the offline setting.
Online Allocation Problem with Two-sided Resource Constraints
As a result, only limited violations of constraints or pessimistic competitive bounds could be guaranteed.
RetroComposer: Composing Templates for Template-Based Retrosynthesis Prediction
To overcome this limitation, we propose an innovative retrosynthesis prediction framework that can compose novel templates beyond training templates.
Ranked #3 on
Single-step retrosynthesis
on USPTO-50k
Progressive Multi-stage Interactive Training in Mobile Network for Fine-grained Recognition
Finally, using the progressive training (P), the features extracted by the model in different stages can be fully utilized and fused with each other.
Tiny-NewsRec: Effective and Efficient PLM-based News Recommendation
We further propose a two-stage knowledge distillation method to improve the efficiency of the large PLM-based news recommendation model while maintaining its performance.
Offline Model-based Adaptable Policy Learning
Current offline reinforcement learning methods commonly learn in the policy space constrained to in-support regions by the offline dataset, in order to ensure the robustness of the outcome policies.
Adaptive Online Packing-guided Search for POMDPs
A belief is a distribution of states representing state uncertainty.
Cross-modal Domain Adaptation for Cost-Efficient Visual Reinforcement Learning
Experiments on MuJoCo and Hand Manipulation Suite tasks show that the agents deployed with our method achieve similar performance as it has in the source domain, while those deployed with previous methods designed for same-modal domain adaptation suffer a larger performance gap.
Stochastic optimal scheduling of demand response-enabled microgrids with renewable generations: An analytical-heuristic approach
In order to solve this model, this research combines Jaya algorithm and interior point method (IPM) to develop a hybrid analysis-heuristic solution method called Jaya-IPM, where the lower- and upper- levels are respectively addressed by the IPM and the Jaya, and the scheduling scheme is obtained via iterations between the two levels.
Calculus of Consent via MARL: Legitimating the Collaborative Governance Supplying Public Goods
Experimental results in an exemplary environment show that our MARL approach is able to demonstrate the effectiveness and necessity of restrictions on individual liberty for collaborative supply of public goods.
Learning Efficient Online 3D Bin Packing on Packing Configuration Trees
PCT is a full-fledged description of the state and action space of bin packing which can support packing policy learning based on deep reinforcement learning (DRL).
LINDA: Multi-Agent Local Information Decomposition for Awareness of Teammates
During long-time observations, agents can build \textit{awareness} for teammates to alleviate the problem of partial observability.
UserBERT: Contrastive User Model Pre-training
Two self-supervision tasks are incorporated in UserBERT for user model pre-training on unlabeled user behavior data to empower user modeling.
Neural-to-Tree Policy Distillation with Policy Improvement Criterion
The empirical results show that the proposed method can preserve a higher cumulative reward than behavior cloning and learn a more consistent policy to the original one.
PatrickStar: Parallel Training of Pre-trained Models via Chunk-based Memory Management
PatrickStar uses the CPU-GPU heterogeneous memory space to store the model data.
Imitate TheWorld: A Search Engine Simulation Platform
Recent E-commerce applications benefit from the growth of deep learning techniques.
On Generalization of Adversarial Imitation Learning and Beyond
For some MDPs, we show that vanilla AIL has a worse sample complexity than BC.
HieRec: Hierarchical User Interest Modeling for Personalized News Recommendation
Instead of a single user embedding, in our method each user is represented in a hierarchical interest tree to better capture their diverse and multi-grained interest in news.
Context-Aware Sparse Deep Coordination Graphs
Learning sparse coordination graphs adaptive to the coordination dynamics among agents is a long-standing problem in cooperative multi-agent learning.
Active Hierarchical Exploration with Stable Subgoal Representation Learning
Although GCHRL possesses superior exploration ability by decomposing tasks via subgoals, existing GCHRL methods struggle in temporally extended tasks with sparse external rewards, since the high-level policy learning relies on external rewards.
Reinforcement Learning With Sparse-Executing Actions via Sparsity Regularization
To tackle the issue of limited action execution in RL, this paper first formalizes the problem as a Sparse Action Markov Decision Process (SA-MDP), in which specific actions in the action space can only be executed for a limited time.
Regret Minimization Experience Replay in Off-Policy Reinforcement Learning
In reinforcement learning, experience replay stores past samples for further reuse.
An Introduction of mini-AlphaStar
StarCraft II (SC2) is a real-time strategy game in which players produce and control multiple units to fight against opponent's units.
Distributed Bootstrap for Simultaneous Inference Under High Dimensionality
We propose a distributed bootstrap method for simultaneous inference on high-dimensional massive data that are stored and processed with many machines.
Derivative-Free Reinforcement Learning: A Review
In this article, we summarize methods of derivative-free reinforcement learning to date, and organize the methods in aspects including parameter updating, model selection, exploration, and parallel/distributed methods.
Self-supervised learning for fast and scalable time series hyper-parameter tuning
Hyper-parameters of time series models play an important role in time series analysis.
NewsBERT: Distilling Pre-trained Language Model for Intelligent News Application
However, existing language models are pre-trained and distilled on general corpus like Wikipedia, which has some gaps with the news domain and may be suboptimal for news intelligence.
NeoRL: A Near Real-World Benchmark for Offline Reinforcement Learning
We evaluate existing offline RL algorithms on NeoRL and argue that the performance of a policy should also be compared with the deterministic version of the behavior policy, instead of the dataset reward.
The Flare and Warp of the Young Stellar Disk traced with LAMOST DR5 OB-type stars
We present analysis of the spatial density structure for the outer disk from 8$-$14 \, kpc with the LAMOST DR5 13534 OB-type stars and observe similar flaring on north and south sides of the disk implying that the flaring structure is symmetrical about the Galactic plane, for which the scale height at different Galactocentric distance is from 0. 14 to 0. 5 \, kpc.
Astrophysics of Galaxies
ASBSO: An Improved Brain Storm Optimization With Flexible Search Length and Memory-Based Selection
This proposed method, adaptive step length based on memory selection BSO, namely ASBSO, applies multiple step lengths to modify the generation process of new solutions, thus supplying a flexible search according to corresponding problems and convergent periods.
Offline Adaptive Policy Leaning in Real-World Sequential Recommendation Systems
Instead of increasing the fidelity of models for policy learning, we handle the distortion issue via learning to adapt to diverse simulators generated by the offline dataset.
Cross-Modal Domain Adaptation for Reinforcement Learning
Domain adaptation is a promising direction for deploying RL agents in real-world applications, where vision-based robotics tasks constitute an important part.
Interactive Search Based on Deep Reinforcement Learning
With the continuous development of machine learning technology, major e-commerce platforms have launched recommendation systems based on it to serve a large number of customers with different needs more efficiently.
Circles are like Ellipses, or Ellipses are like Circles? Measuring the Degree of Asymmetry of Static and Contextual Embeddings and the Implications to Representation Learning
Human judgments of word similarity have been a popular method of evaluating the quality of word embedding.
Offline Imitation Learning with a Misspecified Simulator
In this work, we investigate policy learning in the condition of a few expert demonstrations and a simulator with misspecified dynamics.
OrgMining 2.0: A Novel Framework for Organizational Model Mining from Event Logs
We demonstrate the feasibility of this framework by proposing an approach underpinned by the framework for organizational model discovery, and also conduct experiments on real-life event logs to discover and evaluate organizational models.
Angular Embedding: A New Angular Robust Principal Component Analysis
As a widely used method in machine learning, principal component analysis (PCA) shows excellent properties for dimensionality reduction.
RetroXpert: Decompose Retrosynthesis Prediction like a Chemist
Retrosynthesis is the process of recursively decomposing target molecules into available building blocks.
Mining Generalized Features for Detecting AI-Manipulated Fake Faces
Recently, AI-manipulated face techniques have developed rapidly and constantly, which has raised new security issues in society.
Error Bounds of Imitating Policies and Environments
In this paper, we firstly analyze the value gap between the expert policy and imitated policies by two imitation methods, behavioral cloning and generative adversarial imitation.
Multiple-element joint detection for Aspect-Based Sentiment Analysis
In this paper, we propose a novel end-to-end multiple-element joint detection model (MEJD), which effectively extracts all (target, aspect, sentiment) triples from a sentence.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+2
Difference-in-Differences: Bridging Normalization and Disentanglement in PG-GAN
We discover that pixel normalization causes object entanglement by in-painting the area occupied by ablated objects.
TurboTransformers: An Efficient GPU Serving System For Transformer Models
This paper designed a transformer serving system called TurboTransformers, which consists of a computing runtime and a serving framework to solve the above challenges.
Reinforced Epidemic Control: Saving Both Lives and Economy
Saving lives or economy is a dilemma for epidemic control in most cities while smart-tracing technology raises people's privacy concerns.
QPLEX: Duplex Dueling Multi-Agent Q-Learning
This paper presents a novel MARL approach, called duPLEX dueling multi-agent Q-learning (QPLEX), which takes a duplex dueling network architecture to factorize the joint value function.
Local Neighbor Propagation Embedding
Manifold Learning occupies a vital role in the field of nonlinear dimensionality reduction and its ideas also serve for other relevant methods.
Affect inTweets: A Transfer Learning Approach
As opposed to the traditional machine learning models which require considerable effort in designing task specific features, our model can be well adapted to the proposed tasks with a very limited amount of fine-tuning, which significantly reduces the manual effort in feature engineering.
The Role of the Hercules Autonomous Vehicle During the COVID-19 Pandemic: An Autonomous Logistic Vehicle for Contactless Goods Transportation
Moreover, many countries have imposed tough lockdown measures to reduce the virus transmission (e. g., retail, catering) during the pandemic, which causes inconveniences for human daily life.
AliExpress Learning-To-Rank: Maximizing Online Model Performance without Going Online
The framework consists of an evaluator that generalizes to evaluate recommendations involving the context, and a generator that maximizes the evaluator score by reinforcement learning, and a discriminator that ensures the generalization of the evaluator.
Novelty-Prepared Few-Shot Classification
We disclose that a classically fully trained feature extractor can leave little embedding space for unseen classes, which keeps the model from well-fitting the new classes.
Simultaneous Inference for Massive Data: Distributed Bootstrap
In this paper, we propose a bootstrap method applied to massive data processed distributedly in a large number of machines.
Residual Bootstrap Exploration for Bandit Algorithms
In this paper, we propose a novel perturbation-based exploration method in bandit algorithms with bounded or unbounded rewards, called residual bootstrap exploration (\texttt{ReBoot}).
Temporal-adaptive Hierarchical Reinforcement Learning
Hierarchical reinforcement learning (HRL) helps address large-scale and sparse reward issues in reinforcement learning.