In-Context Reinforcement Learning (ICRL) enables agents to learn automatically and on-the-fly from their interactive experiences. However, a major challenge in scaling up ICRL is the lack of scalable task collections. To address this, we propose the procedurally generated tabular Markov Decision Processes, named AnyMDP. Through a carefully designed randomization process, AnyMDP is capable of generating high-quality tasks on a large scale while maintaining relatively low structural biases. To facilitate efficient meta-training at scale, we further introduce decoupled policy distillation and induce prior information in the ICRL framework. Our results demonstrate that, with a sufficiently large scale of AnyMDP tasks, the proposed model can generalize to tasks that were not considered in the training set through versatile in-context learning paradigms. The scalable task set provided by AnyMDP also enables a more thorough empirical investigation of the relationship between data distribution and ICRL performance. We further show that the generalization of ICRL potentially comes at the cost of increased task diversity and longer adaptation periods. This finding carries critical implications for scaling robust ICRL capabilities, highlighting the necessity of diverse and extensive task design, and prioritizing asymptotic performance over few-shot adaptation.

Object-goal navigation (ObjNav) tasks an agent with navigating to the location of a specific object in an unseen environment. Embodied agents equipped with large language models (LLMs) and online constructed navigation maps can perform ObjNav in a zero-shot manner. However, existing agents heavily rely on giant LLMs on the cloud, e.g., GPT-4, while directly switching to small LLMs, e.g., LLaMA3.2-11b, suffer from significant success rate drops due to limited model capacity for understanding complex navigation maps, which prevents deploying ObjNav on local devices. At the same time, the long prompt introduced by the navigation map description will cause high planning latency on local devices. In this paper, we propose EfficientNav to enable on-device efficient LLM-based zero-shot ObjNav. To help the smaller LLMs better understand the environment, we propose semantics-aware memory retrieval to prune redundant information in navigation maps. To reduce planning latency, we propose discrete memory caching and attention-based memory clustering to efficiently save and re-use the KV cache. Extensive experimental results demonstrate that EfficientNav achieves 11.1\% improvement in success rate on HM3D benchmark over GPT-4-based baselines, and demonstrates 6.7$\times$ real-time latency reduction and 4.7$\times$ end-to-end latency reduction over GPT-4 planner. Our code is available on https://github.com/PKU-SEC-Lab/EfficientNav.

The Track-1 of DSTC9 aims to effectively answer user requests or questions during task-oriented dialogues, which are out of the scope of APIs/DB. By leveraging external knowledge resources, relevant information can be retrieved and encoded into the response generation for these out-of-API-coverage queries. In this work, we have explored several advanced techniques to enhance the utilization of external knowledge and boost the quality of response generation, includingschema guided knowledge decision,negatives enhanced knowledge selection, andknowledge grounded response generation. To evaluate the performance of our proposed method, comprehensive experiments have been carried out on the publicly available dataset. Our approach was ranked as the best in human evaluation of DSTC9 Track-1.

Drug discovery often relies on the successful prediction of protein-ligand binding affinity. Recent advances have shown great promise in applying graph neural networks (GNNs) for better affinity prediction by learning the representations of protein-ligand complexes. However, existing solutions usually treat protein-ligand complexes as topological graph data, thus the 3D geometry-based biomolecular structural information is not fully utilized. The essential intermolecular interactions with long-range dependencies, including type-wise interactions and molecule-wise interactions, are also neglected in GNN models. To this end, we propose a geometry-aware interactive graph neural network (GIaNt) which consists of two components: 3D geometric graph learning network (3DG-Net) and pairwise interactive learning network (Pi-Net). Specifically,3DG-Netiteratively performs the node-edge interaction process to update embeddings of nodes and edges in a unified framework while preserving the 3D geometric factors among atoms, including spatial distance, polar angle and dihedral angle information in 3D space. Moreover,Pi-Netis adopted to incorporate both element type-level and molecule-level interactions. Specially, interactive edges are gathered with a subsequent reconstruction loss to reflect the global type-level interactions. Meanwhile, a pairwise attentive pooling scheme is designed to identify the critical interactive atoms for complex representation learning from a semantic view. An exhaustive experimental study on two benchmarks verifies the superiority ofGIaNt.

Many open-domain dialogue models pretrained with social media comments can generate coherent replies but have difficulties producing engaging responses.This phenomenon might mainly result from the deficiency of annotated human-human conversations and the misalignment with human preference.In this paper, we propose a novel and efficient framework Diamante to boost the open-domain chatbot, where two kinds of human feedback (including explicit demonstration and implicit preference) are collected and leveraged.By asking annotators to select or amend the modelgenerated candidate responses, Diamante efficiently collects the human demonstrated responses and constructs a Chinese chit-chat dataset.To enhance the alignment with human preference, Diamante leverages the implicit preference in the data collection process and introduces the generation-evaluation joint training.Comprehensive experiments indicate that the Diamante dataset and joint training paradigm can significantly boost the performance of pre-trained dialogue models.The overall engagingness of the previous state-ofthe-art model has been improved remarkably by 50% in Chinese open-domain conversations.

In this paper, we propose an unsupervised query enhanced approach for knowledgeintensive conversations, namely QKConv.There are three modules in QKConv: a query generator, an off-the-shelf knowledge selector, and a response generator.QKConv is optimized through joint training, which produces the response by exploring multiple candidate queries and leveraging corresponding selected knowledge.The joint training solely relies on the dialogue context and target response, getting exempt from extra query annotations or knowledge provenances.To evaluate the effectiveness of the proposed QKConv, we conduct experiments on three representative knowledgeintensive conversation datasets: conversational question-answering, task-oriented dialogue, and knowledge-grounded conversation.Experimental results reveal that QKConv performs better than all unsupervised methods across three datasets and achieves competitive performance compared to supervised methods.

MOTIVATION: Protein representation learning methods have shown great potential to many downstream tasks in biological applications. A few recent studies have demonstrated that the self-supervised learning is a promising solution to addressing insufficient labels of proteins, which is a major obstacle to effective protein representation learning. However, existing protein representation learning is usually pretrained on protein sequences without considering the important protein structural information. RESULTS: In this work, we propose a novel structure-aware protein self-supervised learning method to effectively capture structural information of proteins. In particular, a graph neural network model is pretrained to preserve the protein structural information with self-supervised tasks from a pairwise residue distance perspective and a dihedral angle perspective, respectively. Furthermore, we propose to leverage the available protein language model pretrained on protein sequences to enhance the self-supervised learning. Specifically, we identify the relation between the sequential information in the protein language model and the structural information in the specially designed graph neural network model via a novel pseudo bi-level optimization scheme. We conduct experiments on three downstream tasks: the binary classification into membrane/non-membrane proteins, the location classification into 10 cellular compartments, and the enzyme-catalyzed reaction classification into 384 EC numbers, and these experiments verify the effectiveness of our proposed method. AVAILABILITY AND IMPLEMENTATION: The Alphafold2 database is available in https://alphafold.ebi.ac.uk/. The PDB files are available in https://www.rcsb.org/. The downstream tasks are available in https://github.com/phermosilla/IEConv\_proteins/tree/master/Datasets. The code of the proposed method is available in https://github.com/GGchen1997/STEPS_Bioinformatics.

Electric Vehicle (EV) has become preferable choices in modern transportation system due to its environmental and energy sustainability. However, in many large cities, EV drivers often fail to find proper spots for charging because of the limited charging infrastructures and spatiotemporally unbalanced charging demands. Indeed, the recent emergence of deep reinforcement learning provides great potential to improve charging experience over long-term horizons. In this paper, we propose RLCharge for intelligent EV charging station recommendation by jointly considering various long-term spatiotemporal factors. Specifically, by regarding each charging station as an agent, we formulate the problem as a multi-objective multi-agent reinforcement learning task. We first develop a multi-agent actor-critic framework with centralized training decentralized execution. Particularly, we propose a tailor designed centralized attentive critic with the delayed access strategy to coordinate the recommendation between geo-distributed agents during centralized training. Besides, we propose the spatio-temporal heterogeneous graph convolution module to handle the partial observability problem during decentralized execution. After that, to effectively optimize multiple divergent objectives, we develop a dynamic gradient re-weighting strategy to adaptively guide the optimization direction, and propose an adaptive imitation learning scheme to further accelerate and stabilize the policy convergence. Finally, extensive experiments on two real-world datasets demonstrate that RLCHARGE achieves the best comprehensive performance compared with ten baseline approaches.

Efficient exploration of the chemical space to search the candidate drugs that satisfy various constraints is a fundamental task of drug discovery. Advanced deep generative methods attempt to optimize the molecules in the compact latent space instead of the discrete original space, but the mapping between the original and latent spaces is always kept unchanged during the entire optimization process. The unchanged mapping makes those methods challenging to fast adapt to various optimization scenes and leads to the great demand for assessed molecules (samples) to provide optimization direction, which is a considerable expense for drug discovery. To this end, we design a sample-efficient molecular generative method, HelixMO, which explores the scene-sensitive latent space to promote sample efficiency. The scene-sensitive latent space focuses more on modeling the promising molecules by dynamically adjusting the space mapping by leveraging the correlations between the general and scene-specific characteristics during the optimization process. Extensive experiments demonstrate that HelixMO can achieve competitive performance with only a few assessed samples on four molecular optimization scenes. Ablation studies verify the positive impact of the scene-specific latent space, which is capable of identifying the critical characteristics of the promising molecules. We also deployed HelixMO on the website PaddleHelix (https://paddlehelix.baidu.com/app/drug/drugdesign/forecast) to provide drug design service.

Existing pipelined task-oriented dialogue systems usually have difficulties adapting to unseen domains, whereas end-to-end systems are plagued by large-scale knowledge bases in practice.In this paper, we introduce a novel querydriven task-oriented dialogue system, namely Q-TOD.The essential information from the dialogue context is extracted into a query, which is further employed to retrieve relevant knowledge records for response generation.Firstly, as the query is in the form of natural language and not confined to the schema of the knowledge base, the issue of domain adaption is alleviated remarkably in Q-TOD.Secondly, as the query enables the decoupling of knowledge retrieval from the generation, Q-TOD gets rid of the issue of knowledge base scalability.To evaluate the effectiveness of the proposed Q-TOD, we collect query annotations for three publicly available task-oriented dialogue datasets.Comprehensive experiments verify that Q-TOD outperforms strong baselines and establishes a new state-of-the-art performance on these datasets.

Drug combination therapies are superior to monotherapy for cancer treatment in many ways. Identifying novel drug combinations by screening is challenging for the wet-lab experiments due to the time-consuming process of the enormous search space of possible drug pairs. Thus, computational methods have been developed to predict drug pairs with potential synergistic functions. Notwithstanding the success of current models, understanding the mechanism of drug synergy from a chemical-gene-tissue interaction perspective lacks study, hindering current algorithms from drug mechanism study. Here, we proposed a deep neural network model termed DTSyn (Dual Transformer encoder model for drug pair Synergy prediction) based on a multi-head attention mechanism to identify novel drug combinations. We designed a fine-granularity transformer encoder to capture chemical substructure-gene and gene-gene associations and a coarse-granularity transformer encoder to extract chemical-chemical and chemical-cell line interactions. DTSyn achieved the highest receiver operating characteristic area under the curve of 0.73, 0.78. 0.82 and 0.81 on four different cross-validation tasks, outperforming all competing methods. Further, DTSyn achieved the best True Positive Rate (TPR) over five independent data sets. The ablation study showed that both transformer encoder blocks contributed to the performance of DTSyn. In addition, DTSyn can extract interactions among chemicals and cell lines, representing the potential mechanisms of drug action. By leveraging the attention mechanism and pretrained gene embeddings, DTSyn shows improved interpretability ability. Thus, we envision our model as a valuable tool to prioritize synergistic drug pairs with chemical and cell line gene expression profile.

Candidate compounds with high binding affinities toward a target protein are likely to be developed as drugs. Deep neural networks (DNNs) have attracted increasing attention for drug-target affinity (DTA) estimation owning to their efficiency. However, the negative impact of batch effects caused by measure metrics, system technologies and other assay information is seldom discussed when training a DNN model for DTA. Suffering from the data deviation caused by batch effects, the DNN models can only be trained on a small amount of 'clean' data. Thus, it is challenging for them to provide precise and consistent estimations. We design a batch-sensitive training framework, namely BatchDTA, to train the DNN models. BatchDTA implicitly aligns multiple batches toward the same protein through learning the orders of candidate compounds with respect to the batches, alleviating the impact of the batch effects on the DNN models. Extensive experiments demonstrate that BatchDTA facilitates four mainstream DNN models to enhance the ability and robustness on multiple DTA datasets (BindingDB, Davis and KIBA). The average concordance index of the DNN models achieves a relative improvement of 4.0%. The case study reveals that BatchDTA can successfully learn the ranking orders of the compounds from multiple batches. In addition, BatchDTA can also be applied to the fused data collected from multiple sources to achieve further improvement.

MOTIVATION: Accurate ADMET (an abbreviation for 'absorption, distribution, metabolism, excretion and toxicity') predictions can efficiently screen out undesirable drug candidates in the early stage of drug discovery. In recent years, multiple comprehensive ADMET systems that adopt advanced machine learning models have been developed, providing services to estimate multiple endpoints. However, those ADMET systems usually suffer from weak extrapolation ability. First, due to the lack of labelled data for each endpoint, typical machine learning models perform frail for the molecules with unobserved scaffolds. Second, most systems only provide fixed built-in endpoints and cannot be customized to satisfy various research requirements. To this end, we develop a robust and endpoint extensible ADMET system, HelixADMET (H-ADMET). H-ADMET incorporates the concept of self-supervised learning to produce a robust pre-trained model. The model is then fine-tuned with a multi-task and multi-stage framework to transfer knowledge between ADMET endpoints, auxiliary tasks and self-supervised tasks. RESULTS: Our results demonstrate that H-ADMET achieves an overall improvement of 4%, compared with existing ADMET systems on comparable endpoints. Additionally, the pre-trained model provided by H-ADMET can be fine-tuned to generate new and customized ADMET endpoints, meeting various demands of drug research and development requirements. AVAILABILITY AND IMPLEMENTATION: H-ADMET is freely accessible at https://paddlehelix.baidu.com/app/drug/admet/train. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Machine learning shows great potential in virtual screening for drug discovery. Current efforts on accelerating docking-based virtual screening do not consider using existing data of other previously developed targets. To make use of the knowledge of the other targets and take advantage of the existing data, in this work, we apply multi-task learning to the problem of docking-based virtual screening. With two large docking datasets, the results of extensive experiments show that multi-task learning can achieve better performances on docking score prediction. By learning knowledge across multiple targets, the model trained by multi-task learning shows a better ability to adapt to a new target. Additional empirical study shows that other problems in drug discovery, such as the experimental drug-target affinity prediction, may also benefit from multi-task learning. Our results demonstrate that multi-task learning is a promising machine learning approach for docking-based virtual screening and accelerating the process of drug discovery.

Proactive human-robot interaction (HRI) allows the receptionist robots to actively greet people and offer services based on vision, which has been found to improve acceptability and customer satisfaction. Existing approaches are either based on multi-stage decision processes or based on end-to-end decision models. However, the rule-based approaches require sedulous expert efforts and only handle minimal pre-defined scenarios. On the other hand, existing works with end-to-end models are limited to very general greetings or few behavior patterns (typically less than 10). To address those challenges, we propose a new end-to-end framework, the TransFormer with Visual Tokens for Human-Robot Interaction (TFVT-HRI)1. The proposed framework extracts visual tokens of relative objects from an RGB camera first. To ensure the correct interpretation of the scenario, a transformer decision model is then employed to process the visual tokens, which is augmented with the temporal and spatial information. It predicts the appropriate action to take in each scenario and identifies the right target. Our data is collected from an in-service receptionist robot in an office building, which is then annotated by experts for appropriate proactive behavior. The action set includes 1000+ diverse patterns by combining language, emoji expression, and body motions. We compare our model with other SOTA end-to-end models on both offline test sets and online user experiments in realistic office building environments to validate this framework. It is demonstrated that the decision model achieves SOTA performance in action triggering and selection, resulting in more humanness and intelligence when compared with the previous reactive reception policies.

Travel time estimation (TTE) is one of the most critical modules at Baidu Maps, which plays a vital role in intelligent transportation services such as route planning and navigation. During the driving en route, the navigation system of Baidu Maps can provide real-time estimations on when a user will arrive at the destination. It automatically recalculates and updates the remaining travel time from the driver's current position to the destination (hereafter referred to as remaining route) every few minutes. The previously deployed TTE model at Baidu Maps, i.e., ConSTGAT, takes the remaining route as well as the current time as input and provides the corresponding estimated time of arrival. However, it ignores the route that has been already traveled from the origin to the driver's current position (hereafter referred to as traveled route), which could contribute to improving the accuracy of time estimation. In this work, we believe that the traveled route conveys valuable evidence that could facilitate the modeling of driving preference and take that into consideration for the task of en route travel time estimation (ER-TTE). This task is non-trivial because it requires adapting fast to a user's driving preference using a few observed behaviors in the traveled route. To this end, we frame ER-TTE as a few-shot learning problem and consider the observed behaviors in the traveled route as training examples while the future behaviors in the remaining route as test examples. To tackle the few-shot learning problem, we propose a novel model-based meta-learning approach, called SSML, to learn the meta-knowledge so as to fast adapt to a user's driving preference and improve the time estimation of the remaining route. SSML leverages the technique of self-supervised learning, which is equivalent to generating a significant number of synthetic learning tasks, to further improve the performance. Extensive offline tests conducted on large-scale real-world datasets collected from Baidu Maps demonstrate the superiority of SSML. The online tests before deploying in production were successfully performed, which confirms the practical applicability of SSML.

Drug discovery often relies on the successful prediction of protein-ligand binding affinity. Recent advances have shown great promise in applying graph neural networks (GNNs) for better affinity prediction by learning the representations of protein-ligand complexes. However, existing solutions usually treat protein-ligand complexes as topological graph data, thus the biomolecular structural information is not fully utilized. The essential long-range interactions among atoms are also neglected in GNN models. To this end, we propose a structure-aware interactive graph neural network (SIGN) which consists of two components: polar-inspired graph attention layers (PGAL) and pairwise interactive pooling (PiPool). Specifically, PGAL iteratively performs the node-edge aggregation process to update embeddings of nodes and edges while preserving the distance and angle information among atoms. Then, PiPool is adopted to gather interactive edges with a subsequent reconstruction loss to reflect the global interactions. Exhaustive experimental study on two benchmarks verifies the superiority of SIGN.

Electric Vehicle (EV) has become a preferable choice in the modern transportation system due to its environmental and energy sustainability. However, in many large cities, EV drivers often fail to find the proper spots for charging, because of the limited charging infrastructures and the spatiotemporally unbalanced charging demands. Indeed, the recent emergence of deep reinforcement learning provides great potential to improve the charging experience from various aspects over a long-term horizon. In this paper, we propose a framework, named Multi-Agent Spatio-Temporal Reinforcement Learning (Master), for intelligently recommending public accessible charging stations by jointly considering various long-term spatiotemporal factors. Specifically, by regarding each charging station as an individual agent, we formulate this problem as a multi-objective multi-agent reinforcement learning task. We first develop a multi-agent actor-critic framework with the centralized attentive critic to coordinate the recommendation between geo-distributed agents. Moreover, to quantify the influence of future potential charging competition, we introduce a delayed access strategy to exploit the knowledge of future charging competition during training. After that, to effectively optimize multiple learning objectives, we extend the centralized attentive critic to multi-critics and develop a dynamic gradient re-weighting strategy to adaptively guide the optimization direction. Finally, extensive experiments on two real-world datasets demonstrate that Master achieves the best comprehensive performance compared with nine baseline approaches.

Pre-training models have been proved effective for a wide range of natural language processing tasks.Inspired by this, we propose a novel dialogue generation pre-training framework to support various kinds of conversations, including chit-chat, knowledge grounded dialogues, and conversational question answering.In this framework, we adopt flexible attention mechanisms to fully leverage the bi-directional context and the uni-directional characteristic of language generation.We also introduce discrete latent variables to tackle the inherent one-to-many mapping problem in response generation.Two reciprocal tasks of response generation and latent act recognition are designed and carried out simultaneously within a shared network.Comprehensive experiments on three publicly available datasets verify the effectiveness and superiority of the proposed framework.

The task of travel time estimation (TTE), which estimates the travel time for a given route and departure time, plays an important role in intelligent transportation systems such as navigation, route planning, and ride-hailing services. This task is challenging because of many essential aspects, such as traffic prediction and contextual information. First, the accuracy of traffic prediction is strongly correlated with the traffic speed of the road segments in a route. Existing work mainly adopts spatial-temporal graph neural networks to improve the accuracy of traffic prediction, where spatial and temporal information is used separately. However, one drawback is that the spatial and temporal correlations are not fully exploited to obtain better accuracy. Second, contextual information of a route, i.e., the connections of adjacent road segments in the route, is an essential factor that impacts the driving speed. Previous work mainly uses sequential encoding models to address this issue. However, it is difficult to scale up sequential models to large-scale real-world services. In this paper, we propose an end-to-end neural framework named ConSTGAT, which integrates traffic prediction and contextual information to address these two problems. Specifically, we first propose a spatial-temporal graph neural network that adopts a novel graph attention mechanism, which is designed to fully exploit the joint relations of spatial and temporal information. Then, in order to efficiently take advantage of the contextual information, we design a computationally efficient model that applies convolutions over local windows to capture a route's contextual information and further employs multi-task learning to improve the performance. In this way, the travel time of each road segment can be computed in parallel and in advance. Extensive experiments conducted on large-scale real-world datasets demonstrate the superiority of ConSTGAT. In addition, ConSTGAT has already been deployed in production at Baidu Maps, and it successfully keeps serving tens of billions of requests every day. This confirms that ConSTGAT is a practical and robust solution for large-scale real-world TTE services.

In this paper, a novel Generation-Evaluation framework is developed for multi-turn conversations with the objective of letting both participants know more about each other.For the sake of rational knowledge utilization and coherent conversation flow, a dialogue strategy which controls knowledge selection is instantiated and continuously adapted via reinforcement learning.Under the deployed strategy, knowledge grounded conversations are conducted with two dialogue agents.The generated dialogues are comprehensively evaluated on aspects like informativeness and coherence, which are aligned with our objective and human instinct.These assessments are integrated as a compound reward to guide the evolution of dialogue strategy via policy gradient.Comprehensive experiments have been carried out on the publicly available dataset, demonstrating that the proposed method outperforms the other state-of-the-art approaches significantly.

In human conversation an input post is open to multiple potential responses, which is typically regarded as a one-to-many problem. Promising approaches mainly incorporate multiple latent mechanisms to build the one-to-many relationship. However, without accurate selection of the latent mechanism corresponding to the target response during training, these methods suffer from a rough optimization of latent mechanisms. In this paper, we propose a multi-mapping mechanism to better capture the one-to-many relationship, where multiple mapping modules are employed as latent mechanisms to model the semantic mappings from an input post to its diverse responses. For accurate optimization of latent mechanisms, a posterior mapping selection module is designed to select the corresponding mapping module according to the target response for further optimization. We also introduce an auxiliary matching loss to facilitate the optimization of posterior mapping selection. Empirical results demonstrate the superiority of our model in generating multiple diverse and informative responses over the state-of-the-art methods.

End-to-end neural models for intelligent dialogue systems suffer from the problem of generating uninformative responses. Various methods were proposed to generate more informative responses by leveraging external knowledge. However, few previous work has focused on selecting appropriate knowledge in the learning process. The inappropriate selection of knowledge could prohibit the model from learning to make full use of the knowledge. Motivated by this, we propose an end-to-end neural model which employs a novel knowledge selection mechanism where both prior and posterior distributions over knowledge are used to facilitate knowledge selection. Specifically, a posterior distribution over knowledge is inferred from both utterances and responses, and it ensures the appropriate selection of knowledge during the training process. Meanwhile, a prior distribution, which is inferred from utterances only, is used to approximate the posterior distribution so that appropriate knowledge can be selected even without responses during the inference process. Compared with the previous work, our model can better incorporate appropriate knowledge in response generation. Experiments on both automatic and human evaluation verify the superiority of our model over previous baselines.