arXiv subjects

Jianling Wang

Publications and source records attributed to Jianling Wang.

At least 37 records · Page 2Linked to original sources

arXiv2023

The Accretion History of the Milky Way: III. Hydrodynamical Simulations of Galactic Dwarf Galaxies at First Infall

Most Milky Way dwarf galaxies are much less bound to their host than are relics of Gaia-Sausage-Enceladus and Sgr. These dwarfs are expected to have fallen into the Galactic halo less than 3 Gyr ago, and will therefore have undergone no more than one full orbit. Here, we have performed hydrodynamical simulations of this process, assuming that their progenitors are gas-rich, rotation-supported dwarfs. We follow their transformation through interactions with the hot corona and gravitational field of the Galaxy. Our dedicated simulations reproduce the structural properties of three dwarf galaxies: Sculptor, Antlia II and, with somewhat a lower accuracy, Crater II. This includes reproducing their large velocity dispersions, which are caused by ram-pressure stripping and Galactic tidal shocks. Differences between dwarfs can be interpreted as due to different orbital paths, as well as to different initial conditions for their progenitor gas and stellar contents. However, we failed to suppress in a single orbit the rotational support of our Sculptor analog if it is fully dark-matter dominated. In addition, we have found that classical dwarf galaxies like Sculptor may have stellar cores sufficiently dense to survive the pericenter passage through adiabatic contraction. On the contrary, our Antlia II and Crater II analogs are tidally stripped, explaining their large sizes, extremely low surface brightnesses, and velocity dispersion. This modeling explains differences between dwarf galaxies by reproducing them as being at different stages of out-of-equilibrium stellar systems.

astro-ph.GA↗

arXiv2023

Detection of the Keplerian decline in the Milky Way rotation curve

Our position inside the Galactic disc had prevented us from establishing an accurate rotation curve, until the advent of Gaia, whose third data release (Gaia DR3) made it possible to specify it up to twice the optical radius. We aim to establish a new rotation curve of the Galaxy from the Gaia DR3, by drastically reducing uncertainties and systematics, and with the goal to provide a new estimate of the mass of the Galaxy. We have compared different estimates, established a robust assessment of the systematic uncertainties, and addressed differences in methodologies, particularly regarding distance estimates. This results in a sharply decreasing rotation curve for the Milky Way, the decrease in velocity between 19.5 and 26.5 kpc is approximately 30 km s$^{-1}$. We have identified, for the first time, a Keplerian decline of the rotation curve, starting at $\sim$ 19 kpc and up to $\sim$ 26.5 kpc from the Galaxy center, while a flat rotation curve is rejected with a significance of 3$σ$. The total mass is revised downwards to $2.06^{+0.24}_{-0.13}\times 10^{11}\ M_{\odot}$, in agreement with an absence of significant mass increase at radii larger than 19 kpc. The upper limit of the total mass was evaluated by considering the upper values of velocity measurements, which leads to a strict, unsurpassable, limit of $5.4\times 10^{11}\ M_{\odot}$.

astro-ph.GA↗

arXiv2023

Everything Perturbed All at Once: Enabling Differentiable Graph Attacks

As powerful tools for representation learning on graphs, graph neural networks (GNNs) have played an important role in applications including social networks, recommendation systems, and online web services. However, GNNs have been shown to be vulnerable to adversarial attacks, which can significantly degrade their effectiveness. Recent state-of-the-art approaches in adversarial attacks rely on gradient-based meta-learning to selectively perturb a single edge with the highest attack score until they reach the budget constraint. While effective in identifying vulnerable links, these methods are plagued by high computational costs. By leveraging continuous relaxation and parameterization of the graph structure, we propose a novel attack method called Differentiable Graph Attack (DGA) to efficiently generate effective attacks and meanwhile eliminate the need for costly retraining. Compared to the state-of-the-art, DGA achieves nearly equivalent attack performance with 6 times less training time and 11 times smaller GPU memory footprint on different benchmark datasets. Additionally, we provide extensive experimental analyses of the transferability of the DGA among different graph models, as well as its robustness against widely-used defense mechanisms.

cs.LG↗

arXiv2023

Revisiting mass estimates of the Milky Way

We use the rotation curve from Gaia data release (DR) 3 to estimate the mass of the Milky Way. We consider an Einasto density profile to model the dark matter component. We extrapolate and obtain a dynamical mass $M=2.75^{+3.11}_{-0.48}\times 10^{11} M_\odot$ at $112$ kpc. This lower-mass Milky Way is consistent with the significant declining rotation curve, and can provide new insights into our Galaxy and halo inhabitants.

astro-ph.GA↗

arXiv2023

The Formation of Magellanic System and the total mass of Large Magellanic Cloud

The Magellanic Stream is unique to sample the MW potential from ~50 kpc to 300 kpc, and is also unique in constraining the LMC mass, an increasingly important question for the Local Group/Milky Way modeling. Here we compare strengths and weaknesses of the two types of models (tidal and ram-pressure) of the Magellanic Stream formation. I will present our modeling for the formation of the Magellanic System, including those of the most recent discoveries in the Stream, in the Bridge and at the outskirts of Magellanic Clouds. This model has been successful in predicting most recent observations in both properties of stellar and gas phase. It appears that it is an over-constrained model and provides a good path to investigate the Stream properties. In particular, this model requires a LMC mass significantly smaller than 110^{11} Msun

astro-ph.GA↗

arXiv2023

Fresh Content Needs More Attention: Multi-funnel Fresh Content Recommendation

Recommendation system serves as a conduit connecting users to an incredibly large, diverse and ever growing collection of contents. In practice, missing information on fresh (and tail) contents needs to be filled in order for them to be exposed and discovered by their audience. We here share our success stories in building a dedicated fresh content recommendation stack on a large commercial platform. To nominate fresh contents, we built a multi-funnel nomination system that combines (i) a two-tower model with strong generalization power for coverage, and (ii) a sequence model with near real-time update on user feedback for relevance. The multi-funnel setup effectively balances between coverage and relevance. An in-depth study uncovers the relationship between user activity level and their proximity toward fresh contents, which further motivates a contextual multi-funnel setup. Nominated fresh candidates are then scored and ranked by systems considering prediction uncertainty to further bootstrap content with less exposure. We evaluate the benefits of the dedicated fresh content recommendation stack, and the multi-funnel nomination system in particular, through user corpus co-diverted live experiments. We conduct multiple rounds of live experiments on a commercial platform serving billion of users demonstrating efficacy of our proposed methods.

cs.IR↗

arXiv2023

Learning Strong Graph Neural Networks with Weak Information

Graph Neural Networks (GNNs) have exhibited impressive performance in many graph learning tasks. Nevertheless, the performance of GNNs can deteriorate when the input graph data suffer from weak information, i.e., incomplete structure, incomplete features, and insufficient labels. Most prior studies, which attempt to learn from the graph data with a specific type of weak information, are far from effective in dealing with the scenario where diverse data deficiencies exist and mutually affect each other. To fill the gap, in this paper, we aim to develop an effective and principled approach to the problem of graph learning with weak information (GLWI). Based on the findings from our empirical analysis, we derive two design focal points for solving the problem of GLWI, i.e., enabling long-range propagation in GNNs and allowing information propagation to those stray nodes isolated from the largest connected component. Accordingly, we propose D$^2$PT, a dual-channel GNN framework that performs long-range information propagation not only on the input graph with incomplete structure, but also on a global graph that encodes global semantic similarities. We further develop a prototype contrastive alignment algorithm that aligns the class-level prototypes learned from two channels, such that the two different information propagation processes can mutually benefit from each other and the finally learned model can well handle the GLWI problem. Extensive experiments on eight real-world benchmark datasets demonstrate the effectiveness and efficiency of our proposed methods in various GLWI scenarios.

cs.LG↗

arXiv2023

Enhancing User Personalization in Conversational Recommenders

Conversational recommenders are emerging as a powerful tool to personalize a user's recommendation experience. Through a back-and-forth dialogue, users can quickly hone in on just the right items. Many approaches to conversational recommendation, however, only partially explore the user preference space and make limiting assumptions about how user feedback can be best incorporated, resulting in long dialogues and poor recommendation performance. In this paper, we propose a novel conversational recommendation framework with two unique features: (i) a greedy NDCG attribute selector, to enhance user personalization in the interactive preference elicitation process by prioritizing attributes that most effectively represent the actual preference space of the user; and (ii) a user representation refiner, to effectively fuse together the user preferences collected from the interactive elicitation process to obtain a more personalized understanding of the user. Through extensive experiments on four frequently used datasets, we find the proposed framework not only outperforms all the state-of-the-art conversational recommenders (in terms of both recommendation performance and conversation efficiency), but also provides a more personalized experience for the user under the proposed multi-groundtruth multi-round conversational recommendation setting.

cs.IR↗

arXiv2023

Closed-book Question Generation via Contrastive Learning

Question Generation (QG) is a fundamental NLP task for many downstream applications. Recent studies on open-book QG, where supportive answer-context pairs are provided to models, have achieved promising progress. However, generating natural questions under a more practical closed-book setting that lacks these supporting documents still remains a challenge. In this work, we propose a new QG model for this closed-book setting that is designed to better understand the semantics of long-form abstractive answers and store more information in its parameters through contrastive learning and an answer reconstruction module. Through experiments, we validate the proposed QG model on both public datasets and a new WikiCQA dataset. Empirical results show that the proposed QG model outperforms baselines in both automatic evaluation and human evaluation. In addition, we show how to leverage the proposed model to improve existing question-answering systems. These results further indicate the effectiveness of our QG model for enhancing closed-book question-answering tasks.

cs.CL↗

arXiv2023

The accretion history of the Milky Way. I. How it shapes globular clusters and dwarf galaxies

Halo inhabitants are individual stars, stellar streams, star and globular clusters, and dwarf galaxies. Here we compare the two last categories that include objects of similar stellar mass, which are often studied as self-dynamical equilibrium systems. We discover that the half-light radius of globular clusters depends on their orbital pericenter and total energy, and that Milky Way (MW) tides may explain the observed correlation. We also suggest that the accretion epoch of stellar systems in the MW halo can be calibrated by the total orbital energy, and that such a relation is due to both the mass growth of the MW and dynamical friction affecting mostly satellites with numerous orbits. This calibration starts from the bulge, to Kraken, Gaia Sausage Enceladus, Sagittarius stellar systems, and finally to the new coming dwarfs, either or not linked to the vast-polar structure. The most eccentric globular clusters and dwarfs have their half-light radius scaling as the inverse of their binding energy, and this over more than two decades. This means that earlier arriving satellites are smaller due to the tidal effects of the MW. Therefore, most halo inhabitants appear to have their structural parameters shaped by MW tides and also by ram-pressure for the most recent arrivals, the dwarf galaxies. The correlations found in this study can be used as tools to further investigate the origin of globular clusters and dwarfs, as well as the assembly history of our Galaxy.

astro-ph.GA↗

arXiv2022

Robust Graph Meta-learning for Weakly-supervised Few-shot Node Classification

Graphs are widely used to model the relational structure of data, and the research of graph machine learning (ML) has a wide spectrum of applications ranging from drug design in molecular graphs to friendship recommendation in social networks. Prevailing approaches for graph ML typically require abundant labeled instances in achieving satisfactory results, which is commonly infeasible in real-world scenarios since labeled data for newly emerged concepts (e.g., new categorizations of nodes) on graphs is limited. Though meta-learning has been applied to different few-shot graph learning problems, most existing efforts predominately assume that all the data from those seen classes is gold-labeled, while those methods may lose their efficacy when the seen data is weakly-labeled with severe label noise. As such, we aim to investigate a novel problem of weakly-supervised graph meta-learning for improving the model robustness in terms of knowledge transfer. To achieve this goal, we propose a new graph meta-learning framework -- Graph Hallucination Networks (Meta-GHN) in this paper. Based on a new robustness-enhanced episodic training, Meta-GHN is meta-learned to hallucinate clean node representations from weakly-labeled data and extracts highly transferable meta-knowledge, which enables the model to quickly adapt to unseen tasks with few labeled instances. Extensive experiments demonstrate the superiority of Meta-GHN over existing graph meta-learning studies on the task of weakly-supervised few-shot node classification.

cs.LG↗

arXiv2022

Towards Fair Conversational Recommender Systems

Conversational recommender systems have demonstrated great success. They can accurately capture a user's current detailed preference -- through a multi-round interaction cycle -- to effectively guide users to a more personalized recommendation. Alas, conversational recommender systems can be plagued by the adverse effects of bias, much like traditional recommenders. In this work, we argue for increased attention on the presence of and methods for counteracting bias in these emerging systems. As a starting point, we propose three fundamental questions that should be deeply examined to enable fairness in conversational recommender systems.

cs.IR↗

arXiv2022

Quantifying and Mitigating Popularity Bias in Conversational Recommender Systems

Conversational recommender systems (CRS) have shown great success in accurately capturing a user's current and detailed preference through the multi-round interaction cycle while effectively guiding users to a more personalized recommendation. Perhaps surprisingly, conversational recommender systems can be plagued by popularity bias, much like traditional recommender systems. In this paper, we systematically study the problem of popularity bias in CRSs. We demonstrate the existence of popularity bias in existing state-of-the-art CRSs from an exposure rate, a success rate, and a conversational utility perspective, and propose a suite of popularity bias metrics designed specifically for the CRS setting. We then introduce a debiasing framework with three unique features: (i) Popularity-Aware Focused Learning to reduce the popularity-distorting impact on preference prediction; (ii) Cold-Start Item Embedding Reconstruction via Attribute Mapping, to improve the modeling of cold-start items; and (iii) Dual-Policy Learning, to better guide the CRS when dealing with either popular or unpopular items. Through extensive experiments on two frequently used CRS datasets, we find the proposed model-agnostic debiasing framework not only mitigates the popularity bias in state-of-the-art CRSs but also improves the overall recommendation performance.

cs.IR↗

arXiv2022

Lessons from the Magellanic System and its modeling

The prominent Magellanic Stream that dominates the HI sky provides a tantalizing number of observations that potentially constrains the Magellanic Clouds and the Milky Way outskirts. Here we show that the 'ram-pressure plus collision' model naturally explain these properties, and is able to predict some of the most recent observations made after the model was made. These include the complexity of the stellar populations in the Magellanic Bridge, for which kinematics, ages, and distances are well measured, and the North Tidal Arm, for which the model predicts its formation from the Milky Way tidal forces. It appears that this over-constrained model provides a good path to investigate the Stream properties. This contrasts with tidal models that reproduce only half of the Stream's main properties, in particular a tidal tail cannot reproduce the observed inter-twisted filaments, and its gas content is not sufficiently massive to provide the large amount of HI and HII gas associated to the Stream. Despite the efforts made to reproduce the large amounts of gas brought by the Clouds, it seems that no viable solution for the tidal model could be foreseen. Since the 'ram-pressure plus collision' model has not succeeded for a Large Magellanic Cloud mass above 2 $\times10^{10}$ $M_{\odot}$, we conjecture that a low mass is required to form the Stream.

astro-ph.GA↗

arXiv2022

Exploring Heterogeneous Metadata for Video Recommendation with Two-tower Model

Online video services acquire new content on a daily basis to increase engagement, and improve the user experience. Traditional recommender systems solely rely on watch history, delaying the recommendation of newly added titles to the right customer. However, one can use the metadata information of a cold-start title to bootstrap the personalization. In this work, we propose to adopt a two-tower model, in which one tower is to learn the user representation based on their watch history, and the other tower is to learn the effective representations for titles using metadata. The contribution of this work can be summarized as: (1) we show the feasibility of using two-tower model for recommendations and conduct a series of offline experiments to show its performance for cold-start titles; (2) we explore different types of metadata (categorical features, text description, cover-art image) and an attention layer to fuse them; (3) with our Amazon proprietary data, we show that the attention layer can assign weights adaptively to different metadata with improved recommendation for warm- and cold-start items.

cs.IR↗

arXiv2022

Learning to Augment for Casual User Recommendation

Users who come to recommendation platforms are heterogeneous in activity levels. There usually exists a group of core users who visit the platform regularly and consume a large body of content upon each visit, while others are casual users who tend to visit the platform occasionally and consume less each time. As a result, consumption activities from core users often dominate the training data used for learning. As core users can exhibit different activity patterns from casual users, recommender systems trained on historical user activity data usually achieve much worse performance on casual users than core users. To bridge the gap, we propose a model-agnostic framework L2Aug to improve recommendations for casual users through data augmentation, without sacrificing core user experience. L2Aug is powered by a data augmentor that learns to generate augmented interaction sequences, in order to fine-tune and optimize the performance of the recommendation system for casual users. On four real-world public datasets, L2Aug outperforms other treatment methods and achieves the best sequential recommendation performance for both casual and core users. We also test L2Aug in an online simulation environment with real-time feedback to further validate its efficacy, and showcase its flexibility in supporting different augmentation actions.

cs.IR↗

arXiv2022

Meta Propagation Networks for Graph Few-shot Semi-supervised Learning

Inspired by the extensive success of deep learning, graph neural networks (GNNs) have been proposed to learn expressive node representations and demonstrated promising performance in various graph learning tasks. However, existing endeavors predominately focus on the conventional semi-supervised setting where relatively abundant gold-labeled nodes are provided. While it is often impractical due to the fact that data labeling is unbearably laborious and requires intensive domain knowledge, especially when considering the heterogeneity of graph-structured data. Under the few-shot semi-supervised setting, the performance of most of the existing GNNs is inevitably undermined by the overfitting and oversmoothing issues, largely owing to the shortage of labeled data. In this paper, we propose a decoupled network architecture equipped with a novel meta-learning algorithm to solve this problem. In essence, our framework Meta-PN infers high-quality pseudo labels on unlabeled nodes via a meta-learned label propagation strategy, which effectively augments the scarce labeled data while enabling large receptive fields during training. Extensive experiments demonstrate that our approach offers easy and substantial performance gains compared to existing techniques on various benchmark datasets.

cs.LG↗

arXiv2021

Session-based Recommendation with Hypergraph Attention Networks

Session-based recommender systems aim to improve recommendations in short-term sessions that can be found across many platforms. A critical challenge is to accurately model user intent with only limited evidence in these short sessions. For example, is a flower bouquet being viewed meant as part of a wedding purchase or for home decoration? Such different perspectives greatly impact what should be recommended next. Hence, this paper proposes a novel session-based recommendation system empowered by hypergraph attention networks. Three unique properties of the proposed approach are: (i) it constructs a hypergraph for each session to model the item correlations defined by various contextual windows in the session simultaneously, to uncover item meanings; (ii) it is equipped with hypergraph attention layers to generate item embeddings by flexibly aggregating the contextual information from correlated items in the session; and (iii) it aggregates the dynamic item representations for each session to infer the general purpose and current need, which is decoded to infer the next interesting item in the session. Through experiments on three benchmark datasets, we find the proposed model is effective in generating informative dynamic item embeddings and providing more accurate recommendations compared to the state-of-the-art.

cs.IR↗