[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82262-en":3,"doc-seo-82262-105":29,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},82262,962075114101,"Seraphina","https://ap-avatar.wpscdn.com/avatar/e000253a75eb197efd?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780044092746381165",8,"Research & Report","Temporal Knowledge Graph Forecasting under Distribution Shifts: A Synthetic Evaluation","Temporal knowledge graphs (TKGs) model evolving relational systems, where the data-generating processes change over time. Yet, most TKG forecasting studies rely on benchmark datasets that offer limited visibility into robustness against distribution shifts. This work evaluates TKG forecasting under controlled shift environments using a synthetic TKG generator driven by recurrence, homophily, and periodicity. Seven forecasting architectures are tested in stationary and shifting regimes, showing signal-dependent robustness and pronounced difficulties under structural breaks in latent entity-community structure.","arXiv :2607 .09232v 1 [ cs .LG] 10 Jul 2026  \nTemporal Knowledge Graph Forecasting under Distribution Shifts: A Synthetic Evaluation  \nKonrad Özdemir 1 , Julia Gastinger 1 ,  \nLukas Kirchdorfer 1 ,2 , and Heiner Stuckenschmidt 1  \n1 Data and Web Science Group, University of Mannheim, Germany  \n2 SAP Signavio, Walldorf, Germany  \nAbstract. Temporal knowledge graphs (TKGs) represent evolving relational systems, whose underlying data-generating processes often changeover time. Yet, TKG forecasting models are commonly evaluated only on empirical benchmark datasets that provide limited insight into the models’ robustness to such distribution shifts. Recognising this issue, we study TKG forecasting under controlled shift environments using a synthetic TKG generator that encodes three temporal and structural properties—recurrence, homophily, and periodicity—as data-generating mechanisms. This allows us to evaluate seven forecasting architectures under stationary and shifting regimes. Our experiments suggest that robustness in TKG forecasting is highly signal-dependent. Recurrencebased and periodic regularities are largely recoverable under stationary conditions, and simple memory-based baselines can be competitive when recurrence dominates the data. However, structural breaks reveal limitations in model adaptivity, with shifts in latent entity-community structure posing the strongest challenge in our study. Overall, our findings improve the understanding of the capabilities and limitations of current TKG models confronted with temporal distribution shifts.  \nKeywords: Temporal knowledge graphs · Forecasting · Distribution shifts · Synthetic data.  \n1 Introduction  \nTemporal knowledge graphs (TKGs) extend static knowledge graphs (KGs) with temporal information [14] . As such, they constitute an effective, systematic mechanism for storing event-based facts across time. In recent years, TKG forecasting, i.e., the prediction of facts for future timestamps, has been met with rising interest. Diverse approaches have been introduced in this domain (e.g., [4, 6, 21]) and application areas may reach from finance [19] to clinical environments [33] .  \nOne fundamental property of such real-world temporal systems is that their underlying data-generating processes (DGPs) evolve over time, i.e., they incur shifts with respect to their underlying distribution [8] . Typically, such shifts can be of sudden or gradual nature. The former may take place through the beginning of a war that can abruptly alter the interplay of diplomatic relations. The latter  \n2 K. Özdemir et al.  \nmay arise when a change in government restructures societal systems, such as the overhaul of South Africa’s education system following the end of apartheid [26] . As such, accounting for distribution shifts when modelling temporal data plays an integral role not only in classical time series forecasting, but also in adjacent sequential learning domains [16, 28, 35] .  \nIn the context of single-relational temporal graph learning, recent evidence in the form of a systematic evaluation has surfaced that several approaches struggle to capture rather basic temporal patterns like periodicity [15] . Motivated, among other things, by these observations, Blöcker et al. [2] argue for a stronger integration of insights from network science into temporal graph learning. They highlight that decades of research on temporal and structural patterns in evolving networks still remain underutilised in modern graph learning approaches and that models are often evaluated primarily through empirical benchmark performance, without a clear understanding of the specific patterns they capture [2] .  \nIn this work, we maintain that this discrepancy extends to directed, multirelational temporal graphs as well and, therefore, to the area of TKG forecasting. In TKG forecasting, robustness to distribution shifts remains a largely underexplored field of investigation and, to the best of our knowledge, no prio","cbCaijWTVisXR8bg","https://ap.wps.com/l/cbCaijWTVisXR8bg","pdf",677721,1,21,"English","en",105,"# Introduction\n# Related Work","[{\"question\":\"What limitation of existing TKG forecasting evaluations motivates this study?\",\"answer\":\"Most evaluations use benchmark datasets that provide limited insight into how models behave under distribution shifts, making robustness difficult to assess under controlled changes in the data-generating process.\"},{\"question\":\"How does the proposed synthetic evaluation environment model distribution shifts?\",\"answer\":\"It uses a synthetic TKG generator that encodes temporal and structural properties—recurrence, homophily, and periodicity—to create controllable shift environments for systematic testing.\"},{\"question\":\"Which types of distribution shifts are most challenging for TKG forecasting models in the experiments?\",\"answer\":\"Structural breaks that change latent entity-community structure pose the strongest challenge, revealing limitations in model adaptivity even when some temporal regularities remain recoverable.\"}]",1784179232,53,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":27},"temporal-knowledge-graph-forecasting-under-distribution-shifts-a-synthetic-evaluation","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/temporal-knowledge-graph-forecasting-under-distribution-shifts-a-synthetic-evaluation/82262/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-17","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What limitation of existing TKG forecasting evaluations motivates this study?","Question",{"text":75,"@type":76},"Most evaluations use benchmark datasets that provide limited insight into how models behave under distribution shifts, making robustness difficult to assess under controlled changes in the data-generating process.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the proposed synthetic evaluation environment model distribution shifts?",{"text":80,"@type":76},"It uses a synthetic TKG generator that encodes temporal and structural properties—recurrence, homophily, and periodicity—to create controllable shift environments for systematic testing.",{"name":82,"@type":73,"acceptedAnswer":83},"Which types of distribution shifts are most challenging for TKG forecasting models in the experiments?",{"text":84,"@type":76},"Structural breaks that change latent entity-community structure pose the strongest challenge, revealing limitations in model adaptivity even when some temporal regularities remain recoverable.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":45,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":45,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":45,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":45,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":45,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]