Search Results for author:
Found 59 papers, 26 papers with code
Nested Named Entity Recognition with Span-level Graphs
In this work, we try to improve the span representation by utilizing retrieval-based span-level graphs, connecting spans and entities in the training data based on n-gram features.
Multi-Level Interaction Reranking with User Behavior History
MIR combines low-level cross-item interaction and high-level set-to-list interaction, where we view the candidate items to be reranked as a set and the users' behavior history in chronological order as a list.
PerfectDou: Dominating DouDizhu with Perfect Information Distillation
To this end, we characterize card and game features for DouDizhu to represent the perfect and imperfect information.
A Roadmap for Big Model
With the rapid development of deep learning, training Big Models (BMs) for multiple downstream tasks becomes a popular paradigm.
Model-based Multi-agent Reinforcement Learning: Recent Progress and Prospects
Significant advances have recently been achieved in Multi-Agent Reinforcement Learning (MARL) which tackles sequential decision-making problems involving multiple participants.
Plan Your Target and Learn Your Skills: Transferable State-Only Imitation Learning via Decoupled Policy Optimization
Recent progress in state-only imitation learning extends the scope of applicability of imitation learning to real-world settings by relieving the need for observing expert actions.
Multi-View Graph Representation for Programming Language Processing: An Investigation into Algorithm Detection
We thoroughly evaluate our proposed MVG approach in the context of algorithm detection, an important and challenging subfield of PLP.
Neural Re-ranking in Multi-stage Recommender Systems: A Review
As the final stage of the multi-stage recommender system (MRS), re-ranking directly affects user experience and satisfaction by rearranging the input ranking lists, and thereby plays a critical role in MRS. With the advances in deep learning, neural re-ranking has become a trending topic and been widely applied in industrial applications.
Who to Watch Next: Two-side Interactive Networks for Live Broadcast Recommendation
With the prevalence of live broadcast business nowadays, a new type of recommendation service, called live broadcast recommendation, is widely used in many mobile e-commerce Apps.
Learn over Past, Evolve for Future: Search-based Time-aware Recommendation with Sequential Behavior Data
More concretely, we first design a search-based module to retrieve a user's relevant historical behaviors, which are then mixed up with her recent records to be fed into a time-aware sequential network for capturing her time-sensitive demands.
Efficient Policy Space Response Oracles
Policy Space Response Oracle method (PSRO) provides a general solution to Nash equilibrium in two-player zero-sum games but suffers from two problems: (1) the computation inefficiency due to consistently evaluating current populations by simulations; and (2) the exploration inefficiency due to learning best responses against a fixed meta-strategy at each iteration.
Generative Adversarial Exploration for Reinforcement Learning
Exploration is crucial for training the optimal reinforcement learning (RL) policy, where the key is to discriminate whether a state visiting is novel.
DropNAS: Grouped Operation Dropout for Differentiable Architecture Search
Neural architecture search (NAS) has shown encouraging results in automating the architecture design.
Towards Collaborative Question Answering: A Preliminary Study
Knowledge and expertise in the real-world can be disjointedly owned.
Goal-Conditioned Reinforcement Learning: Problems and Solutions
Goal-conditioned reinforcement learning (GCRL), related to a set of complex RL problems, trains an agent to achieve different goals under particular scenarios.
Phrase-level Adversarial Example Generation for Neural Machine Translation
In this paper, we propose a phrase-level adversarial example generation (PAEG) method to enhance the robustness of the model.
Offline Pre-trained Multi-Agent Decision Transformer: One Big Sequence Model Tackles All SMAC Tasks
In this paper, we facilitate the research by providing large-scale datasets, and use them to examine the usage of the Decision Transformer in the context of MARL.
Curriculum Offline Imitating Learning
However, IL is usually limited in the capability of the behavioral policy and tends to learn a mediocre behavior from the dataset collected by the mixture of policies.
Towards Return Parity in Markov Decision Processes
We first provide a decomposition theorem for return disparity, which decomposes the return disparity of any two MDPs sharing the same state and action spaces into the distance between group-wise reward functions, the discrepancy of group policies, and the discrepancy between state visitation distributions induced by the group policies.
QA4PRF: A Question Answering based Framework for Pseudo Relevance Feedback
Pseudo relevance feedback (PRF) automatically performs query expansion based on top-retrieved documents to better represent the user's information need so as to improve the search results.
On Effective Scheduling of Model-based Reinforcement Learning
Model-based reinforcement learning has attracted wide attention due to its superior sample efficiency.
Learning Logic Rules for Document-level Relation Extraction
LogiRE treats logic rules as latent variables and consists of two modules: a rule generator and a relation extractor.
Ranked #18 on
Relation Extraction
on DocRED
AIM: Automatic Interaction Machine for Click-Through Rate Prediction
To address these three issues mentioned above, we propose Automatic Interaction Machine (AIM) with three core components, namely, Feature Interaction Search (FIS), Interaction Function Search (IFS) and Embedding Dimension Search (EDS), to select significant feature interactions, appropriate interaction functions and necessary embedding dimensions automatically in a unified framework.
Curriculum Offline Imitation Learning
However, IL is usually limited in the capability of the behavioral policy and tends to learn a mediocre behavior from the dataset collected by the mixture of policies.
Context-aware Reranking with Utility Maximization for Recommendation
As a critical task for large-scale commercial recommender systems, reranking has shown the potential of improving recommendation results by uncovering mutual influence among items.
Why Propagate Alone? Parallel Use of Labels and Features on Graphs
In this regard, it has recently been proposed to use a randomly-selected portion of the training labels as GNN inputs, concatenated with the original node features for making predictions on the remaining labels.
Inductive Relation Prediction Using Analogy Subgraph Embeddings
Prevailing methods for relation prediction in heterogeneous graphs aim at learning latent representations (i. e., embeddings) of observed nodes and relations, and thus are limited to the transductive setting where the relation types must be known during training.
Graph-Enhanced Exploration for Goal-oriented Reinforcement Learning
Goal-oriented Reinforcement Learning (GoRL) is a promising approach for scaling up RL techniques on sparse reward environments requiring long horizon planning.
Plan Your Target and Learn Your Skills: State-Only Imitation Learning via Decoupled Policy Optimization
State-only imitation learning (SOIL) enables agents to learn from massive demonstrations without explicit action or reward information.
AARL: Automated Auxiliary Loss for Reinforcement Learning
A good state representation is crucial to reinforcement learning (RL) while an ideal representation is hard to learn only with signals from the RL objective.
Deep Ensemble Policy Learning
Ensemble learning, which can consistently improve the prediction performance in supervised learning, has drawn increasing attentions in reinforcement learning (RL).
Offline Pre-trained Multi-Agent Decision Transformer
Offline reinforcement learning leverages static datasets to learn optimal policies with no necessity to access the environment.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Task-wise Split Gradient Boosting Trees for Multi-center Diabetes Prediction
To tackle the above challenges, we employ gradient boosting decision trees (GBDT) to handle data heterogeneity and introduce multi-task learning (MTL) to solve data insufficiency.
Retrieval & Interaction Machine for Tabular Data Prediction
Prediction over tabular data is an essential task in many data science applications such as recommender systems, online advertising, medical treatment, etc.
A Graph-Enhanced Click Model for Web Search
To better exploit search logs and model users' behavior patterns, numerous click models are proposed to extract users' implicit interaction feedback.
MALib: A Parallel Framework for Population-based Multi-agent Reinforcement Learning
Our framework is comprised of three key components: (1) a centralized task dispatching model, which supports the self-generated tasks and scalable training with heterogeneous policy combinations; (2) a programming architecture named Actor-Evaluator-Learner, which achieves high parallelism for both training and sampling, and meets the evaluation requirement of auto-curriculum learning; (3) a higher-level abstraction of MARL training paradigms, which enables efficient code reuse and flexible deployments on different distributed computing paradigms.
Learning to Select Cuts for Efficient Mixed-Integer Programming
In the online A/B testing of the product planning problems with more than $10^7$ variables and constraints daily, Cut Ranking has achieved the average speedup ratio of 12. 42% over the production solver without any accuracy loss of solution.
MapGo: Model-Assisted Policy Optimization for Goal-Oriented Tasks
In Goal-oriented Reinforcement learning, relabeling the raw goals in past experience to provide agents with hindsight ability is a major solution to the reward sparsity problem.
Model-based Multi-agent Policy Optimization with Adaptive Opponent-wise Rollouts
We specify the dynamics sample complexity and the opponent sample complexity in MARL, and conduct a theoretic analysis of return discrepancy upper bound.
Deep Learning for Click-Through Rate Estimation
In this survey, we provide a comprehensive review of deep learning models for CTR estimation tasks.
An Adversarial Imitation Click Model for Information Retrieval
Modern information retrieval systems, including web search, ads placement, and recommender systems, typically rely on learning from user feedback.
Bag of Tricks for Node Classification with Graph Neural Networks
Over the past few years, graph neural networks (GNN) and label propagation-based methods have made significant progress in addressing node classification tasks on graphs.
Ranked #1 on
Node Property Prediction
on ogbn-proteins
MARS: Markov Molecular Sampling for Multi-objective Drug Discovery
Searching for novel molecules with desired chemical properties is crucial in drug discovery.
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.
Universal Trading for Order Execution with Oracle Policy Distillation
As a fundamental problem in algorithmic trading, order execution aims at fulfilling a specific trading order, either liquidation or acquirement, for a given instrument.
Regioned Episodic Reinforcement Learning
Goal-oriented reinforcement learning algorithms are often good at exploration, not exploitation, while episodic algorithms excel at exploitation, not exploration.
Explore with Dynamic Map: Graph Structured Reinforcement Learning
In reinforcement learning, a map with states and transitions built based on historical trajectories is often helpful in exploration and exploitation.
Non-iterative Parallel Text Generation via Glancing Transformer
Although non-autoregressive models with one-iteration generation achieves remarkable inference speed-up, they still falls behind their autoregressive counterparts inprediction accuracy.
Which Heroes to Pick? Learning to Draft in MOBA Games with Neural Networks and Tree Search
Hero drafting is essential in MOBA game playing as it builds the team of each side and directly affects the match outcome.
An Embedding Learning Framework for Numerical Features in CTR Prediction
In this paper, we propose a novel embedding learning framework for numerical features in CTR prediction (AutoDis) with high model capacity, end-to-end training and unique representation properties preserved.
Fork or Fail: Cycle-Consistent Training with Many-to-One Mappings
Cycle-consistent training is widely used for jointly learning a forward and inverse mapping between two domains of interest without the cumbersome requirement of collecting matched pairs within each domain.
Towards Generalized Implementation of Wasserstein Distance in GANs
Wasserstein GANs (WGANs), built upon the Kantorovich-Rubinstein (KR) duality of Wasserstein distance, is one of the most theoretically sound GAN models.
Reciprocal Supervised Learning Improves Neural Machine Translation
Despite the recent success on image classification, self-training has only achieved limited gains on structured prediction tasks such as neural machine translation (NMT).
GraphHINGE: Learning Interaction Models of Structured Neighborhood on Heterogeneous Information Network
Heterogeneous information network (HIN) has been widely used to characterize entities of various types and their complex relations.
U-rank: Utility-oriented Learning to Rank with Implicit Feedback
To this end, we propose a novel ranking framework called U-rank that directly optimizes the expected utility of the ranking list.
Efficient Projection-Free Algorithms for Saddle Point Problems
The Frank-Wolfe algorithm is a classic method for constrained optimization problems.
Model-based Policy Optimization with Unsupervised Model Adaptation
However, due to the potential distribution mismatch between simulated data and real data, this could lead to degraded performance.
SMARTS: Scalable Multi-Agent Reinforcement Learning Training School for Autonomous Driving
We open-source the SMARTS platform and the associated benchmark tasks and evaluation metrics to encourage and empower research on multi-agent learning for autonomous driving.
Feature-Based Matrix Factorization
Recommender system has been more and more popular and widely used in many applications recently.
